Optimization of design parameters for bulk micromachined silicon membranes for piezoresistive pressure sensing application

NASA Astrophysics Data System (ADS)

Belwanshi, Vinod; Topkar, Anita

2016-05-01

Finite element analysis study has been carried out to optimize the design parameters for bulk micro-machined silicon membranes for piezoresistive pressure sensing applications. The design is targeted for measurement of pressure up to 200 bar for nuclear reactor applications. The mechanical behavior of bulk micro-machined silicon membranes in terms of deflection and stress generation has been simulated. Based on the simulation results, optimization of the membrane design parameters in terms of length, width and thickness has been carried out. Subsequent to optimization of membrane geometrical parameters, the dimensions and location of the high stress concentration region for implantation of piezoresistors have been obtained for sensing of pressure using piezoresistive sensing technique.

Predictive Modeling and Optimization of Vibration-assisted AFM Tip-based Nanomachining

NASA Astrophysics Data System (ADS)

Kong, Xiangcheng

The tip-based vibration-assisted nanomachining process offers a low-cost, low-effort technique in fabricating nanometer scale 2D/3D structures in sub-100 nm regime. To understand its mechanism, as well as provide the guidelines for process planning and optimization, we have systematically studied this nanomachining technique in this work. To understand the mechanism of this nanomachining technique, we firstly analyzed the interaction between the AFM tip and the workpiece surface during the machining process. A 3D voxel-based numerical algorithm has been developed to calculate the material removal rate as well as the contact area between the AFM tip and the workpiece surface. As a critical factor to understand the mechanism of this nanomachining process, the cutting force has been analyzed and modeled. A semi-empirical model has been proposed by correlating the cutting force with the material removal rate, which was validated using experimental data from different machining conditions. With the understanding of its mechanism, we have developed guidelines for process planning of this nanomachining technique. To provide the guideline for parameter selection, the effect of machining parameters on the feature dimensions (depth and width) has been analyzed. Based on ANOVA test results, the feature width is only controlled by the XY vibration amplitude, while the feature depth is affected by several machining parameters such as setpoint force and feed rate. A semi-empirical model was first proposed to predict the machined feature depth under given machining condition. Then, to reduce the computation intensity, linear and nonlinear regression models were also proposed and validated using experimental data. Given the desired feature dimensions, feasible machining parameters could be provided using these predictive feature dimension models. As the tip wear is unavoidable during the machining process, the machining precision will gradually decrease. To maintain the machining quality, the guideline for when to change the tip should be provided. In this study, we have developed several metrics to detect tip wear, such as tip radius and the pull-off force. The effect of machining parameters on the tip wear rate has been studied using these metrics, and the machining distance before a tip must be changed has been modeled using these machining parameters. Finally, the optimization functions have been built for unit production time and unit production cost subject to realistic constraints, and the optimal machining parameters can be found by solving these functions.

Machine Learning Methods for Analysis of Metabolic Data and Metabolic Pathway Modeling

PubMed Central

Cuperlovic-Culf, Miroslava

2018-01-01

Machine learning uses experimental data to optimize clustering or classification of samples or features, or to develop, augment or verify models that can be used to predict behavior or properties of systems. It is expected that machine learning will help provide actionable knowledge from a variety of big data including metabolomics data, as well as results of metabolism models. A variety of machine learning methods has been applied in bioinformatics and metabolism analyses including self-organizing maps, support vector machines, the kernel machine, Bayesian networks or fuzzy logic. To a lesser extent, machine learning has also been utilized to take advantage of the increasing availability of genomics and metabolomics data for the optimization of metabolic network models and their analysis. In this context, machine learning has aided the development of metabolic networks, the calculation of parameters for stoichiometric and kinetic models, as well as the analysis of major features in the model for the optimal application of bioreactors. Examples of this very interesting, albeit highly complex, application of machine learning for metabolism modeling will be the primary focus of this review presenting several different types of applications for model optimization, parameter determination or system analysis using models, as well as the utilization of several different types of machine learning technologies. PMID:29324649

Machine Learning Methods for Analysis of Metabolic Data and Metabolic Pathway Modeling.

PubMed

Cuperlovic-Culf, Miroslava

2018-01-11

Machine learning uses experimental data to optimize clustering or classification of samples or features, or to develop, augment or verify models that can be used to predict behavior or properties of systems. It is expected that machine learning will help provide actionable knowledge from a variety of big data including metabolomics data, as well as results of metabolism models. A variety of machine learning methods has been applied in bioinformatics and metabolism analyses including self-organizing maps, support vector machines, the kernel machine, Bayesian networks or fuzzy logic. To a lesser extent, machine learning has also been utilized to take advantage of the increasing availability of genomics and metabolomics data for the optimization of metabolic network models and their analysis. In this context, machine learning has aided the development of metabolic networks, the calculation of parameters for stoichiometric and kinetic models, as well as the analysis of major features in the model for the optimal application of bioreactors. Examples of this very interesting, albeit highly complex, application of machine learning for metabolism modeling will be the primary focus of this review presenting several different types of applications for model optimization, parameter determination or system analysis using models, as well as the utilization of several different types of machine learning technologies.

Study on Temperature and Synthetic Compensation of Piezo-Resistive Differential Pressure Sensors by Coupled Simulated Annealing and Simplex Optimized Kernel Extreme Learning Machine

PubMed Central

Li, Ji; Hu, Guoqing; Zhou, Yonghong; Zou, Chong; Peng, Wei; Alam SM, Jahangir

2017-01-01

As a high performance-cost ratio solution for differential pressure measurement, piezo-resistive differential pressure sensors are widely used in engineering processes. However, their performance is severely affected by the environmental temperature and the static pressure applied to them. In order to modify the non-linear measuring characteristics of the piezo-resistive differential pressure sensor, compensation actions should synthetically consider these two aspects. Advantages such as nonlinear approximation capability, highly desirable generalization ability and computational efficiency make the kernel extreme learning machine (KELM) a practical approach for this critical task. Since the KELM model is intrinsically sensitive to the regularization parameter and the kernel parameter, a searching scheme combining the coupled simulated annealing (CSA) algorithm and the Nelder-Mead simplex algorithm is adopted to find an optimal KLEM parameter set. A calibration experiment at different working pressure levels was conducted within the temperature range to assess the proposed method. In comparison with other compensation models such as the back-propagation neural network (BP), radius basis neural network (RBF), particle swarm optimization optimized support vector machine (PSO-SVM), particle swarm optimization optimized least squares support vector machine (PSO-LSSVM) and extreme learning machine (ELM), the compensation results show that the presented compensation algorithm exhibits a more satisfactory performance with respect to temperature compensation and synthetic compensation problems. PMID:28422080

Study on Temperature and Synthetic Compensation of Piezo-Resistive Differential Pressure Sensors by Coupled Simulated Annealing and Simplex Optimized Kernel Extreme Learning Machine.

PubMed

Li, Ji; Hu, Guoqing; Zhou, Yonghong; Zou, Chong; Peng, Wei; Alam Sm, Jahangir

2017-04-19

As a high performance-cost ratio solution for differential pressure measurement, piezo-resistive differential pressure sensors are widely used in engineering processes. However, their performance is severely affected by the environmental temperature and the static pressure applied to them. In order to modify the non-linear measuring characteristics of the piezo-resistive differential pressure sensor, compensation actions should synthetically consider these two aspects. Advantages such as nonlinear approximation capability, highly desirable generalization ability and computational efficiency make the kernel extreme learning machine (KELM) a practical approach for this critical task. Since the KELM model is intrinsically sensitive to the regularization parameter and the kernel parameter, a searching scheme combining the coupled simulated annealing (CSA) algorithm and the Nelder-Mead simplex algorithm is adopted to find an optimal KLEM parameter set. A calibration experiment at different working pressure levels was conducted within the temperature range to assess the proposed method. In comparison with other compensation models such as the back-propagation neural network (BP), radius basis neural network (RBF), particle swarm optimization optimized support vector machine (PSO-SVM), particle swarm optimization optimized least squares support vector machine (PSO-LSSVM) and extreme learning machine (ELM), the compensation results show that the presented compensation algorithm exhibits a more satisfactory performance with respect to temperature compensation and synthetic compensation problems.

Multi-Response Optimization of WEDM Process Parameters Using Taguchi Based Desirability Function Analysis

NASA Astrophysics Data System (ADS)

Majumder, Himadri; Maity, Kalipada

2018-03-01

Shape memory alloy has a unique capability to return to its original shape after physical deformation by applying heat or thermo-mechanical or magnetic load. In this experimental investigation, desirability function analysis (DFA), a multi-attribute decision making was utilized to find out the optimum input parameter setting during wire electrical discharge machining (WEDM) of Ni-Ti shape memory alloy. Four critical machining parameters, namely pulse on time (TON), pulse off time (TOFF), wire feed (WF) and wire tension (WT) were taken as machining inputs for the experiments to optimize three interconnected responses like cutting speed, kerf width, and surface roughness. Input parameter combination TON = 120 μs., TOFF = 55 μs., WF = 3 m/min. and WT = 8 kg-F were found to produce the optimum results. The optimum process parameters for each desired response were also attained using Taguchi’s signal-to-noise ratio. Confirmation test has been done to validate the optimum machining parameter combination which affirmed DFA was a competent approach to select optimum input parameters for the ideal response quality for WEDM of Ni-Ti shape memory alloy.

The Effects of Operational Parameters on a Mono-wire Cutting System: Efficiency in Marble Processing

NASA Astrophysics Data System (ADS)

Yilmazkaya, Emre; Ozcelik, Yilmaz

2016-02-01

Mono-wire block cutting machines that cut with a diamond wire can be used for squaring natural stone blocks and the slab-cutting process. The efficient use of these machines reduces operating costs by ensuring less diamond wire wear and longer wire life at high speeds. The high investment costs of these machines will lead to their efficient use and reduce production costs by increasing plant efficiency. Therefore, there is a need to investigate the cutting performance parameters of mono-wire cutting machines in terms of rock properties and operating parameters. This study aims to investigate the effects of the wire rotational speed (peripheral speed) and wire descending speed (cutting speed), which are the operating parameters of a mono-wire cutting machine, on unit wear and unit energy, which are the performance parameters in mono-wire cutting. By using the obtained results, cuttability charts for each natural stone were created on the basis of unit wear and unit energy values, cutting optimizations were performed, and the relationships between some physical and mechanical properties of rocks and the optimum cutting parameters obtained as a result of the optimization were investigated.

Application of grey-fuzzy approach in parametric optimization of EDM process in machining of MDN 300 steel

NASA Astrophysics Data System (ADS)

Protim Das, Partha; Gupta, P.; Das, S.; Pradhan, B. B.; Chakraborty, S.

2018-01-01

Maraging steel (MDN 300) find its application in many industries as it exhibits high hardness which are very difficult to machine material. Electro discharge machining (EDM) is an extensively popular machining process which can be used in machining of such materials. Optimization of response parameters are essential for effective machining of these materials. Past researchers have already used Taguchi for obtaining the optimal responses of EDM process for this material with responses such as material removal rate (MRR), tool wear rate (TWR), relative wear ratio (RWR), and surface roughness (SR) considering discharge current, pulse on time, pulse off time, arc gap, and duty cycle as process parameters. In this paper, grey relation analysis (GRA) with fuzzy logic is applied to this multi objective optimization problem to check the responses by an implementation of the derived parametric setting. It was found that the parametric setting derived by the proposed method results in better a response than those reported by the past researchers. Obtained results are also verified using the technique for order of preference by similarity to ideal solution (TOPSIS). The predicted result also shows that there is a significant improvement in comparison to the results of past researchers.

Optimization of Maghemite (γ-Fe2O3) Nano-Powder Mixed micro-EDM of CoCrMo with Multiple Responses Using Gray Relational Analysis (GRA)

NASA Astrophysics Data System (ADS)

Mejid Elsiti, Nagwa; Noordin, M. Y.; Idris, Ani; Saed Majeed, Faraj

2017-10-01

This paper presents an optimization of process parameters of Micro-Electrical Discharge Machining (EDM) process with (γ-Fe2O3) nano-powder mixed dielectric using multi-response optimization Grey Relational Analysis (GRA) method instead of single response optimization. These parameters were optimized based on 2-Level factorial design combined with Grey Relational Analysis. The machining parameters such as peak current, gap voltage, and pulse on time were chosen for experimentation. The performance characteristics chosen for this study are material removal rate (MRR), tool wear rate (TWR), Taper and Overcut. Experiments were conducted using electrolyte copper as the tool and CoCrMo as the workpiece. Experimental results have been improved through this approach.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Fang Baolong; Department of Mathematics and Physics, Hefei University, Hefei, 230022; Song Qingming

We present a scheme to realize a special quantum cloning machine in separate cavities. The quantum cloning machine can copy the quantum information from a photon pulse to two distant atoms. Choosing the different parameters, the method can perform optimal symmetric (asymmetric) universal quantum cloning and optimal symmetric (asymmetric) phase-covariant cloning.

Optimization of process parameters in CNC turning of aluminium alloy using hybrid RSM cum TLBO approach

NASA Astrophysics Data System (ADS)

Rudrapati, R.; Sahoo, P.; Bandyopadhyay, A.

2016-09-01

The main aim of the present work is to analyse the significance of turning parameters on surface roughness in computer numerically controlled (CNC) turning operation while machining of aluminium alloy material. Spindle speed, feed rate and depth of cut have been considered as machining parameters. Experimental runs have been conducted as per Box-Behnken design method. After experimentation, surface roughness is measured by using stylus profile meter. Factor effects have been studied through analysis of variance. Mathematical modelling has been done by response surface methodology, to made relationships between the input parameters and output response. Finally, process optimization has been made by teaching learning based optimization (TLBO) algorithm. Predicted turning condition has been validated through confirmatory experiment.

Multiple performance characteristics optimization for Al 7075 on electric discharge drilling by Taguchi grey relational theory

NASA Astrophysics Data System (ADS)

Khanna, Rajesh; Kumar, Anish; Garg, Mohinder Pal; Singh, Ajit; Sharma, Neeraj

2015-12-01

Electric discharge drill machine (EDDM) is a spark erosion process to produce micro-holes in conductive materials. This process is widely used in aerospace, medical, dental and automobile industries. As for the performance evaluation of the electric discharge drilling machine, it is very necessary to study the process parameters of machine tool. In this research paper, a brass rod 2 mm diameter was selected as a tool electrode. The experiments generate output responses such as tool wear rate (TWR). The best parameters such as pulse on-time, pulse off-time and water pressure were studied for best machining characteristics. This investigation presents the use of Taguchi approach for better TWR in drilling of Al-7075. A plan of experiments, based on L27 Taguchi design method, was selected for drilling of material. Analysis of variance (ANOVA) shows the percentage contribution of the control factor in the machining of Al-7075 in EDDM. The optimal combination levels and the significant drilling parameters on TWR were obtained. The optimization results showed that the combination of maximum pulse on-time and minimum pulse off-time gives maximum MRR.

A Power Transformers Fault Diagnosis Model Based on Three DGA Ratios and PSO Optimization SVM

NASA Astrophysics Data System (ADS)

Ma, Hongzhe; Zhang, Wei; Wu, Rongrong; Yang, Chunyan

2018-03-01

In order to make up for the shortcomings of existing transformer fault diagnosis methods in dissolved gas-in-oil analysis (DGA) feature selection and parameter optimization, a transformer fault diagnosis model based on the three DGA ratios and particle swarm optimization (PSO) optimize support vector machine (SVM) is proposed. Using transforming support vector machine to the nonlinear and multi-classification SVM, establishing the particle swarm optimization to optimize the SVM multi classification model, and conducting transformer fault diagnosis combined with the cross validation principle. The fault diagnosis results show that the average accuracy of test method is better than the standard support vector machine and genetic algorithm support vector machine, and the proposed method can effectively improve the accuracy of transformer fault diagnosis is proved.

“Investigations on the machinability of Waspaloy under dry environment”

NASA Astrophysics Data System (ADS)

Deepu, J.; Kuppan, P.; SBalan, A. S.; Oyyaravelu, R.

2016-09-01

Nickel based superalloy, Waspaloy is extensively used in gas turbine, aerospace and automobile industries because of their unique combination of properties like high strength at elevated temperatures, resistance to chemical degradation and excellent wear resistance in many hostile environments. It is considered as one of the difficult to machine superalloy due to excessive tool wear and poor surface finish. The present paper is an attempt for removing cutting fluids from turning process of Waspaloy and to make the processes environmentally safe. For this purpose, the effect of machining parameters such as cutting speed and feed rate on the cutting force, cutting temperature, surface finish and tool wear were investigated barrier. Consequently, the strength and tool wear resistance and tool life increased significantly. Response Surface Methodology (RSM) has been used for developing and analyzing a mathematical model which describes the relationship between machining parameters and output variables. Subsequently ANOVA was used to check the adequacy of the regression model as well as each machining variables. The optimal cutting parameters were determined based on multi-response optimizations by composite desirability approach in order to minimize cutting force, average surface roughness and maximum flank wear. The results obtained from the experiments shown that machining of Waspaloy using coated carbide tool with special ranges of parameters, cutting fluid could be completely removed from machining process

A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach.

PubMed

Jian, Yulin; Huang, Daoyu; Yan, Jia; Lu, Kun; Huang, Ying; Wen, Tailai; Zeng, Tanyue; Zhong, Shijie; Xie, Qilong

2017-06-19

A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from the existing multiple kernel extreme learning machine (MK-ELM) algorithms, the combination coefficients of base kernels are regarded as external parameters of single-hidden layer feedforward neural networks (SLFNs). The combination coefficients of base kernels, the model parameters of each base kernel, and the regularization parameter are optimized by QPSO simultaneously before implementing the kernel extreme learning machine (KELM) with the composite kernel function. Four types of common single kernel functions (Gaussian kernel, polynomial kernel, sigmoid kernel, and wavelet kernel) are utilized to constitute different composite kernel functions. Moreover, the method is also compared with other existing classification methods: extreme learning machine (ELM), kernel extreme learning machine (KELM), k-nearest neighbors (KNN), support vector machine (SVM), multi-layer perceptron (MLP), radical basis function neural network (RBFNN), and probabilistic neural network (PNN). The results have demonstrated that the proposed QWMK-ELM outperforms the aforementioned methods, not only in precision, but also in efficiency for gas classification.

Optimal quantum cloning based on the maximin principle by using a priori information

NASA Astrophysics Data System (ADS)

Kang, Peng; Dai, Hong-Yi; Wei, Jia-Hua; Zhang, Ming

2016-10-01

We propose an optimal 1 →2 quantum cloning method based on the maximin principle by making full use of a priori information of amplitude and phase about the general cloned qubit input set, which is a simply connected region enclosed by a "longitude-latitude grid" on the Bloch sphere. Theoretically, the fidelity of the optimal quantum cloning machine derived from this method is the largest in terms of the maximin principle compared with that of any other machine. The problem solving is an optimization process that involves six unknown complex variables, six vectors in an uncertain-dimensional complex vector space, and four equality constraints. Moreover, by restricting the structure of the quantum cloning machine, the optimization problem is simplified as a three-real-parameter suboptimization problem with only one equality constraint. We obtain the explicit formula for a suboptimal quantum cloning machine. Additionally, the fidelity of our suboptimal quantum cloning machine is higher than or at least equal to that of universal quantum cloning machines and phase-covariant quantum cloning machines. It is also underlined that the suboptimal cloning machine outperforms the "belt quantum cloning machine" for some cases.

Machine Learning Force Field Parameters from Ab Initio Data

DOE Office of Scientific and Technical Information (OSTI.GOV)

Li, Ying; Li, Hui; Pickard, Frank C.

Machine learning (ML) techniques with the genetic algorithm (GA) have been applied to determine a polarizable force field parameters using only ab initio data from quantum mechanics (QM) calculations of molecular clusters at the MP2/6-31G(d,p), DFMP2(fc)/jul-cc-pVDZ, and DFMP2(fc)/jul-cc-pVTZ levels to predict experimental condensed phase properties (i.e., density and heat of vaporization). The performance of this ML/GA approach is demonstrated on 4943 dimer electrostatic potentials and 1250 cluster interaction energies for methanol. Excellent agreement between the training data set from QM calculations and the optimized force field model was achieved. The results were further improved by introducing an offset factor duringmore » the machine learning process to compensate for the discrepancy between the QM calculated energy and the energy reproduced by optimized force field, while maintaining the local “shape” of the QM energy surface. Throughout the machine learning process, experimental observables were not involved in the objective function, but were only used for model validation. The best model, optimized from the QM data at the DFMP2(fc)/jul-cc-pVTZ level, appears to perform even better than the original AMOEBA force field (amoeba09.prm), which was optimized empirically to match liquid properties. The present effort shows the possibility of using machine learning techniques to develop descriptive polarizable force field using only QM data. The ML/GA strategy to optimize force fields parameters described here could easily be extended to other molecular systems.« less

Parameter identification and optimization of slide guide joint of CNC machine tools

NASA Astrophysics Data System (ADS)

Zhou, S.; Sun, B. B.

2017-11-01

The joint surface has an important influence on the performance of CNC machine tools. In order to identify the dynamic parameters of slide guide joint, the parametric finite element model of the joint is established and optimum design method is used based on the finite element simulation and modal test. Then the mode that has the most influence on the dynamics of slip joint is found through harmonic response analysis. Take the frequency of this mode as objective, the sensitivity analysis of the stiffness of each joint surface is carried out using Latin Hypercube Sampling and Monte Carlo Simulation. The result shows that the vertical stiffness of slip joint surface constituted by the bed and the slide plate has the most obvious influence on the structure. Therefore, this stiffness is taken as the optimization variable and the optimal value is obtained through studying the relationship between structural dynamic performance and stiffness. Take the stiffness values before and after optimization into the FEM of machine tool, and it is found that the dynamic performance of the machine tool is improved.

Surface Roughness Optimization of Polyamide-6/Nanoclay Nanocomposites Using Artificial Neural Network: Genetic Algorithm Approach

PubMed Central

Moghri, Mehdi; Omidi, Mostafa; Farahnakian, Masoud

2014-01-01

During the past decade, polymer nanocomposites attracted considerable investment in research and development worldwide. One of the key factors that affect the quality of polymer nanocomposite products in machining is surface roughness. To obtain high quality products and reduce machining costs it is very important to determine the optimal machining conditions so as to achieve enhanced machining performance. The objective of this paper is to develop a predictive model using a combined design of experiments and artificial intelligence approach for optimization of surface roughness in milling of polyamide-6 (PA-6) nanocomposites. A surface roughness predictive model was developed in terms of milling parameters (spindle speed and feed rate) and nanoclay (NC) content using artificial neural network (ANN). As the present study deals with relatively small number of data obtained from full factorial design, application of genetic algorithm (GA) for ANN training is thought to be an appropriate approach for the purpose of developing accurate and robust ANN model. In the optimization phase, a GA is considered in conjunction with the explicit nonlinear function derived from the ANN to determine the optimal milling parameters for minimization of surface roughness for each PA-6 nanocomposite. PMID:24578636

Experimental Investigation – Magnetic Assisted Electro Discharge Machining

NASA Astrophysics Data System (ADS)

Kesava Reddy, Chirra; Manzoor Hussain, M.; Satyanarayana, S.; Krishna, M. V. S. Murali

2018-04-01

Emerging technology needs advanced machined parts with high strength and temperature resistance, high fatigue life at low production cost with good surface quality to fit into various industrial applications. Electro discharge machine is one of the extensively used machines to manufacture advanced machined parts which cannot be machined by other traditional machine with high precision and accuracy. Machining of DIN 17350-1.2080 (High Carbon High Chromium steel), using electro discharge machining has been discussed in this paper. In the present investigation an effort is made to use permanent magnet at various positions near the spark zone to improve surface quality of the machined surface. Taguchi methodology is used to obtain optimal choice for each machining parameter such as peak current, pulse duration, gap voltage and Servo reference voltage etc. Process parameters have significant influence on machining characteristics and surface finish. Improvement in surface finish is observed when process parameters are set at optimum condition under the influence of magnetic field at various positions.

Network Modeling and Energy-Efficiency Optimization for Advanced Machine-to-Machine Sensor Networks

PubMed Central

Jung, Sungmo; Kim, Jong Hyun; Kim, Seoksoo

2012-01-01

Wireless machine-to-machine sensor networks with multiple radio interfaces are expected to have several advantages, including high spatial scalability, low event detection latency, and low energy consumption. Here, we propose a network model design method involving network approximation and an optimized multi-tiered clustering algorithm that maximizes node lifespan by minimizing energy consumption in a non-uniformly distributed network. Simulation results show that the cluster scales and network parameters determined with the proposed method facilitate a more efficient performance compared to existing methods. PMID:23202190

Modelling and multi objective optimization of WEDM of commercially Monel super alloy using evolutionary algorithms

NASA Astrophysics Data System (ADS)

Varun, Sajja; Reddy, Kalakada Bhargav Bal; Vardhan Reddy, R. R. Vishnu

2016-09-01

In this research work, development of a multi response optimization technique has been undertaken, using traditional desirability analysis and non-traditional particle swarm optimization techniques (for different customer's priorities) in wire electrical discharge machining (WEDM). Monel 400 has been selected as work material for experimentation. The effect of key process parameters such as pulse on time (TON), pulse off time (TOFF), peak current (IP), wire feed (WF) were on material removal rate (MRR) and surface roughness(SR) in WEDM operation were investigated. Further, the responses such as MRR and SR were modelled empirically through regression analysis. The developed models can be used by the machinists to predict the MRR and SR over a wide range of input parameters. The optimization of multiple responses has been done for satisfying the priorities of multiple users by using Taguchi-desirability function method and particle swarm optimization technique. The analysis of variance (ANOVA) is also applied to investigate the effect of influential parameters. Finally, the confirmation experiments were conducted for the optimal set of machining parameters, and the betterment has been proved.

Parametric Optimization of Wire Electrical Discharge Machining of Powder Metallurgical Cold Worked Tool Steel using Taguchi Method

NASA Astrophysics Data System (ADS)

Sudhakara, Dara; Prasanthi, Guvvala

2017-04-01

Wire Cut EDM is an unconventional machining process used to build components of complex shape. The current work mainly deals with optimization of surface roughness while machining P/M CW TOOL STEEL by Wire cut EDM using Taguchi method. The process parameters of the Wire Cut EDM is ON, OFF, IP, SV, WT, and WP. L27 OA is used for to design of the experiments for conducting experimentation. In order to find out the effecting parameters on the surface roughness, ANOVA analysis is engaged. The optimum levels for getting minimum surface roughness is ON = 108 µs, OFF = 63 µs, IP = 11 A, SV = 68 V and WT = 8 g.

Optimization of Coolant Technique Conditions for Machining A319 Aluminium Alloy Using Response Surface Method (RSM)

NASA Astrophysics Data System (ADS)

Zainal Ariffin, S.; Razlan, A.; Ali, M. Mohd; Efendee, A. M.; Rahman, M. M.

2018-03-01

Background/Objectives: The paper discusses about the optimum cutting parameters with coolant techniques condition (1.0 mm nozzle orifice, wet and dry) to optimize surface roughness, temperature and tool wear in the machining process based on the selected setting parameters. The selected cutting parameters for this study were the cutting speed, feed rate, depth of cut and coolant techniques condition. Methods/Statistical Analysis Experiments were conducted and investigated based on Design of Experiment (DOE) with Response Surface Method. The research of the aggressive machining process on aluminum alloy (A319) for automotive applications is an effort to understand the machining concept, which widely used in a variety of manufacturing industries especially in the automotive industry. Findings: The results show that the dominant failure mode is the surface roughness, temperature and tool wear when using 1.0 mm nozzle orifice, increases during machining and also can be alternative minimize built up edge of the A319. The exploration for surface roughness, productivity and the optimization of cutting speed in the technical and commercial aspects of the manufacturing processes of A319 are discussed in automotive components industries for further work Applications/Improvements: The research result also beneficial in minimizing the costs incurred and improving productivity of manufacturing firms. According to the mathematical model and equations, generated by CCD based RSM, experiments were performed and cutting coolant condition technique using size nozzle can reduces tool wear, surface roughness and temperature was obtained. Results have been analyzed and optimization has been carried out for selecting cutting parameters, shows that the effectiveness and efficiency of the system can be identified and helps to solve potential problems.

Cognitive Nonlinear Radar

DTIC Science & Technology

2013-01-01

intelligently selecting waveform parameters using adaptive algorithms. The adaptive algorithms optimize the waveform parameters based on (1) the EM...the environment. 15. SUBJECT TERMS cognitive radar, adaptive sensing, spectrum sensing, multi-objective optimization, genetic algorithms, machine...detection and classification block diagram. .........................................................6 Figure 5. Genetic algorithm block diagram

A Novel Extreme Learning Machine Classification Model for e-Nose Application Based on the Multiple Kernel Approach

PubMed Central

Jian, Yulin; Huang, Daoyu; Yan, Jia; Lu, Kun; Huang, Ying; Wen, Tailai; Zeng, Tanyue; Zhong, Shijie; Xie, Qilong

2017-01-01

A novel classification model, named the quantum-behaved particle swarm optimization (QPSO)-based weighted multiple kernel extreme learning machine (QWMK-ELM), is proposed in this paper. Experimental validation is carried out with two different electronic nose (e-nose) datasets. Being different from the existing multiple kernel extreme learning machine (MK-ELM) algorithms, the combination coefficients of base kernels are regarded as external parameters of single-hidden layer feedforward neural networks (SLFNs). The combination coefficients of base kernels, the model parameters of each base kernel, and the regularization parameter are optimized by QPSO simultaneously before implementing the kernel extreme learning machine (KELM) with the composite kernel function. Four types of common single kernel functions (Gaussian kernel, polynomial kernel, sigmoid kernel, and wavelet kernel) are utilized to constitute different composite kernel functions. Moreover, the method is also compared with other existing classification methods: extreme learning machine (ELM), kernel extreme learning machine (KELM), k-nearest neighbors (KNN), support vector machine (SVM), multi-layer perceptron (MLP), radical basis function neural network (RBFNN), and probabilistic neural network (PNN). The results have demonstrated that the proposed QWMK-ELM outperforms the aforementioned methods, not only in precision, but also in efficiency for gas classification. PMID:28629202

Spiking neuron network Helmholtz machine.

PubMed

Sountsov, Pavel; Miller, Paul

2015-01-01

An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule.

Spiking neuron network Helmholtz machine

PubMed Central

Sountsov, Pavel; Miller, Paul

2015-01-01

An increasing amount of behavioral and neurophysiological data suggests that the brain performs optimal (or near-optimal) probabilistic inference and learning during perception and other tasks. Although many machine learning algorithms exist that perform inference and learning in an optimal way, the complete description of how one of those algorithms (or a novel algorithm) can be implemented in the brain is currently incomplete. There have been many proposed solutions that address how neurons can perform optimal inference but the question of how synaptic plasticity can implement optimal learning is rarely addressed. This paper aims to unify the two fields of probabilistic inference and synaptic plasticity by using a neuronal network of realistic model spiking neurons to implement a well-studied computational model called the Helmholtz Machine. The Helmholtz Machine is amenable to neural implementation as the algorithm it uses to learn its parameters, called the wake-sleep algorithm, uses a local delta learning rule. Our spiking-neuron network implements both the delta rule and a small example of a Helmholtz machine. This neuronal network can learn an internal model of continuous-valued training data sets without supervision. The network can also perform inference on the learned internal models. We show how various biophysical features of the neural implementation constrain the parameters of the wake-sleep algorithm, such as the duration of the wake and sleep phases of learning and the minimal sample duration. We examine the deviations from optimal performance and tie them to the properties of the synaptic plasticity rule. PMID:25954191

Electrocardiographic signals and swarm-based support vector machine for hypoglycemia detection.

PubMed

Nuryani, Nuryani; Ling, Steve S H; Nguyen, H T

2012-04-01

Cardiac arrhythmia relating to hypoglycemia is suggested as a cause of death in diabetic patients. This article introduces electrocardiographic (ECG) parameters for artificially induced hypoglycemia detection. In addition, a hybrid technique of swarm-based support vector machine (SVM) is introduced for hypoglycemia detection using the ECG parameters as inputs. In this technique, a particle swarm optimization (PSO) is proposed to optimize the SVM to detect hypoglycemia. In an experiment using medical data of patients with Type 1 diabetes, the introduced ECG parameters show significant contributions to the performance of the hypoglycemia detection and the proposed detection technique performs well in terms of sensitivity and specificity.

Optimisation of wire-cut EDM process parameter by Grey-based response surface methodology

NASA Astrophysics Data System (ADS)

Kumar, Amit; Soota, Tarun; Kumar, Jitendra

2018-03-01

Wire electric discharge machining (WEDM) is one of the advanced machining processes. Response surface methodology coupled with Grey relation analysis method has been proposed and used to optimise the machining parameters of WEDM. A face centred cubic design is used for conducting experiments on high speed steel (HSS) M2 grade workpiece material. The regression model of significant factors such as pulse-on time, pulse-off time, peak current, and wire feed is considered for optimising the responses variables material removal rate (MRR), surface roughness and Kerf width. The optimal condition of the machining parameter was obtained using the Grey relation grade. ANOVA is applied to determine significance of the input parameters for optimising the Grey relation grade.

Multi Response Optimization of Laser Micro Marking Process:A Grey- Fuzzy Approach

NASA Astrophysics Data System (ADS)

Shivakoti, I.; Das, P. P.; Kibria, G.; Pradhan, B. B.; Mustafa, Z.; Ghadai, R. K.

2017-07-01

The selection of optimal parametric combination for efficient machining has always become a challenging issue for the manufacturing researcher. The optimal parametric combination always provides a better machining which improves the productivity, product quality and subsequently reduces the production cost and time. The paper presents the hybrid approach of Grey relational analysis and Fuzzy logic to obtain the optimal parametric combination for better laser beam micro marking on the Gallium Nitride (GaN) work material. The response surface methodology has been implemented for design of experiment considering three parameters with their five levels. The parameter such as current, frequency and scanning speed has been considered and the mark width, mark depth and mark intensity has been considered as the process response.

Optimizing Support Vector Machine Parameters with Genetic Algorithm for Credit Risk Assessment

NASA Astrophysics Data System (ADS)

Manurung, Jonson; Mawengkang, Herman; Zamzami, Elviawaty

2017-12-01

Support vector machine (SVM) is a popular classification method known to have strong generalization capabilities. SVM can solve the problem of classification and linear regression or nonlinear kernel which can be a learning algorithm for the ability of classification and regression. However, SVM also has a weakness that is difficult to determine the optimal parameter value. SVM calculates the best linear separator on the input feature space according to the training data. To classify data which are non-linearly separable, SVM uses kernel tricks to transform the data into a linearly separable data on a higher dimension feature space. The kernel trick using various kinds of kernel functions, such as : linear kernel, polynomial, radial base function (RBF) and sigmoid. Each function has parameters which affect the accuracy of SVM classification. To solve the problem genetic algorithms are proposed to be applied as the optimal parameter value search algorithm thus increasing the best classification accuracy on SVM. Data taken from UCI repository of machine learning database: Australian Credit Approval. The results show that the combination of SVM and genetic algorithms is effective in improving classification accuracy. Genetic algorithms has been shown to be effective in systematically finding optimal kernel parameters for SVM, instead of randomly selected kernel parameters. The best accuracy for data has been upgraded from kernel Linear: 85.12%, polynomial: 81.76%, RBF: 77.22% Sigmoid: 78.70%. However, for bigger data sizes, this method is not practical because it takes a lot of time.

Mathematical simulation and optimization of cutting mode in turning of workpieces made of nickel-based heat-resistant alloy

NASA Astrophysics Data System (ADS)

Bogoljubova, M. N.; Afonasov, A. I.; Kozlov, B. N.; Shavdurov, D. E.

2018-05-01

A predictive simulation technique of optimal cutting modes in the turning of workpieces made of nickel-based heat-resistant alloys, different from the well-known ones, is proposed. The impact of various factors on the cutting process with the purpose of determining optimal parameters of machining in concordance with certain effectiveness criteria is analyzed in the paper. A mathematical model of optimization, algorithms and computer programmes, visual graphical forms reflecting dependences of the effectiveness criteria – productivity, net cost, and tool life on parameters of the technological process - have been worked out. A nonlinear model for multidimensional functions, “solution of the equation with multiple unknowns”, “a coordinate descent method” and heuristic algorithms are accepted to solve the problem of optimization of cutting mode parameters. Research shows that in machining of workpieces made from heat-resistant alloy AISI N07263, the highest possible productivity will be achieved with the following parameters: cutting speed v = 22.1 m/min., feed rate s=0.26 mm/rev; tool life T = 18 min.; net cost – 2.45 per hour.

Grey Relational Analysis Coupled with Principal Component Analysis for Optimization of Stereolithography Process to Enhance Part Quality

NASA Astrophysics Data System (ADS)

Raju, B. S.; Sekhar, U. Chandra; Drakshayani, D. N.

2017-08-01

The paper investigates optimization of stereolithography process for SL5530 epoxy resin material to enhance part quality. The major characteristics indexed for performance selected to evaluate the processes are tensile strength, Flexural strength, Impact strength and Density analysis and corresponding process parameters are Layer thickness, Orientation and Hatch spacing. In this study, the process is intrinsically with multiple parameters tuning so that grey relational analysis which uses grey relational grade as performance index is specially adopted to determine the optimal combination of process parameters. Moreover, the principal component analysis is applied to evaluate the weighting values corresponding to various performance characteristics so that their relative importance can be properly and objectively desired. The results of confirmation experiments reveal that grey relational analysis coupled with principal component analysis can effectively acquire the optimal combination of process parameters. Hence, this confirm that the proposed approach in this study can be an useful tool to improve the process parameters in stereolithography process, which is very useful information for machine designers as well as RP machine users.

Auto-SEIA: simultaneous optimization of image processing and machine learning algorithms

NASA Astrophysics Data System (ADS)

Negro Maggio, Valentina; Iocchi, Luca

2015-02-01

Object classification from images is an important task for machine vision and it is a crucial ingredient for many computer vision applications, ranging from security and surveillance to marketing. Image based object classification techniques properly integrate image processing and machine learning (i.e., classification) procedures. In this paper we present a system for automatic simultaneous optimization of algorithms and parameters for object classification from images. More specifically, the proposed system is able to process a dataset of labelled images and to return a best configuration of image processing and classification algorithms and of their parameters with respect to the accuracy of classification. Experiments with real public datasets are used to demonstrate the effectiveness of the developed system.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chen Lin; Chen Yixin

We show that no universal quantum cloning machine exists that can broadcast an arbitrary mixed qubit with a constant fidelity. Based on this result, we investigate the dependent quantum cloner in the sense that some parameter of the input qubit {rho}{sub s}({theta},{omega},{lambda}) is regarded as constant in the fidelity. For the case of constant {omega}, we establish the 1{yields}2 optimal symmetric dependent cloner with a fidelity 1/2. It is also shown that the 1{yields}M optimal quantum cloning machine for pure qubits is also optimal for mixed qubits, when {lambda} is the unique parameter in the fidelity. For general N{yields}M broadcastingmore » of mixed qubits, the situation is very different.« less

Realizing a partial general quantum cloning machine with superconducting quantum-interference devices in a cavity QED

NASA Astrophysics Data System (ADS)

Fang, Bao-Long; Yang, Zhen; Ye, Liu

2009-05-01

We propose a scheme for implementing a partial general quantum cloning machine with superconducting quantum-interference devices coupled to a nonresonant cavity. By regulating the time parameters, our system can perform optimal symmetric (asymmetric) universal quantum cloning, optimal symmetric (asymmetric) phase-covariant cloning, and optimal symmetric economical phase-covariant cloning. In the scheme the cavity is only virtually excited, thus, the cavity decay is suppressed during the cloning operations.

Selection of Wire Electrical Discharge Machining Process Parameters on Stainless Steel AISI Grade-304 using Design of Experiments Approach

NASA Astrophysics Data System (ADS)

Lingadurai, K.; Nagasivamuni, B.; Muthu Kamatchi, M.; Palavesam, J.

2012-06-01

Wire electrical discharge machining (WEDM) is a specialized thermal machining process capable of accurately machining parts of hard materials with complex shapes. Parts having sharp edges that pose difficulties to be machined by the main stream machining processes can be easily machined by WEDM process. Design of Experiments approach (DOE) has been reported in this work for stainless steel AISI grade-304 which is used in cryogenic vessels, evaporators, hospital surgical equipment, marine equipment, fasteners, nuclear vessels, feed water tubing, valves, refrigeration equipment, etc., is machined by WEDM with brass wire electrode. The DOE method is used to formulate the experimental layout, to analyze the effect of each parameter on the machining characteristics, and to predict the optimal choice for each WEDM parameter such as voltage, pulse ON, pulse OFF and wire feed. It is found that these parameters have a significant influence on machining characteristic such as metal removal rate (MRR), kerf width and surface roughness (SR). The analysis of the DOE reveals that, in general the pulse ON time significantly affects the kerf width and the wire feed rate affects SR, while, the input voltage mainly affects the MRR.

Design synthesis and optimization of permanent magnet synchronous machines based on computationally-efficient finite element analysis

NASA Astrophysics Data System (ADS)

Sizov, Gennadi Y.

In this dissertation, a model-based multi-objective optimal design of permanent magnet ac machines, supplied by sine-wave current regulated drives, is developed and implemented. The design procedure uses an efficient electromagnetic finite element-based solver to accurately model nonlinear material properties and complex geometric shapes associated with magnetic circuit design. Application of an electromagnetic finite element-based solver allows for accurate computation of intricate performance parameters and characteristics. The first contribution of this dissertation is the development of a rapid computational method that allows accurate and efficient exploration of large multi-dimensional design spaces in search of optimum design(s). The computationally efficient finite element-based approach developed in this work provides a framework of tools that allow rapid analysis of synchronous electric machines operating under steady-state conditions. In the developed modeling approach, major steady-state performance parameters such as, winding flux linkages and voltages, average, cogging and ripple torques, stator core flux densities, core losses, efficiencies and saturated machine winding inductances, are calculated with minimum computational effort. In addition, the method includes means for rapid estimation of distributed stator forces and three-dimensional effects of stator and/or rotor skew on the performance of the machine. The second contribution of this dissertation is the development of the design synthesis and optimization method based on a differential evolution algorithm. The approach relies on the developed finite element-based modeling method for electromagnetic analysis and is able to tackle large-scale multi-objective design problems using modest computational resources. Overall, computational time savings of up to two orders of magnitude are achievable, when compared to current and prevalent state-of-the-art methods. These computational savings allow one to expand the optimization problem to achieve more complex and comprehensive design objectives. The method is used in the design process of several interior permanent magnet industrial motors. The presented case studies demonstrate that the developed finite element-based approach practically eliminates the need for using less accurate analytical and lumped parameter equivalent circuit models for electric machine design optimization. The design process and experimental validation of the case-study machines are detailed in the dissertation.

Optimization and Analysis of Laser Beam Machining Parameters for Al7075-TiB2 In-situ Composite

NASA Astrophysics Data System (ADS)

Manjoth, S.; Keshavamurthy, R.; Pradeep Kumar, G. S.

2016-09-01

The paper focuses on laser beam machining (LBM) of In-situ synthesized Al7075-TiB2 metal matrix composite. Optimization and influence of laser machining process parameters on surface roughness, volumetric material removal rate (VMRR) and dimensional accuracy of composites were studied. Al7075-TiB2 metal matrix composite was synthesized by in-situ reaction technique using stir casting process. Taguchi's L9 orthogonal array was used to design experimental trials. Standoff distance (SOD) (0.3 - 0.5mm), Cutting Speed (1000 - 1200 m/hr) and Gas pressure (0.5 - 0.7 bar) were considered as variable input parameters at three different levels, while power and nozzle diameter were maintained constant with air as assisting gas. Optimized process parameters for surface roughness, volumetric material removal rate (VMRR) and dimensional accuracy were calculated by generating the main effects plot for signal noise ratio (S/N ratio) for surface roughness, VMRR and dimensional error using Minitab software (version 16). The Significant of standoff distance (SOD), cutting speed and gas pressure on surface roughness, volumetric material removal rate (VMRR) and dimensional error were calculated using analysis of variance (ANOVA) method. Results indicate that, for surface roughness, cutting speed (56.38%) is most significant parameter followed by standoff distance (41.03%) and gas pressure (2.6%). For volumetric material removal (VMRR), gas pressure (42.32%) is most significant parameter followed by cutting speed (33.60%) and standoff distance (24.06%). For dimensional error, Standoff distance (53.34%) is most significant parameter followed by cutting speed (34.12%) and gas pressure (12.53%). Further, verification experiments were carried out to confirm performance of optimized process parameters.

Computer-aided diagnosis of lung nodule using gradient tree boosting and Bayesian optimization.

PubMed

Nishio, Mizuho; Nishizawa, Mitsuo; Sugiyama, Osamu; Kojima, Ryosuke; Yakami, Masahiro; Kuroda, Tomohiro; Togashi, Kaori

2018-01-01

We aimed to evaluate a computer-aided diagnosis (CADx) system for lung nodule classification focussing on (i) usefulness of the conventional CADx system (hand-crafted imaging feature + machine learning algorithm), (ii) comparison between support vector machine (SVM) and gradient tree boosting (XGBoost) as machine learning algorithms, and (iii) effectiveness of parameter optimization using Bayesian optimization and random search. Data on 99 lung nodules (62 lung cancers and 37 benign lung nodules) were included from public databases of CT images. A variant of the local binary pattern was used for calculating a feature vector. SVM or XGBoost was trained using the feature vector and its corresponding label. Tree Parzen Estimator (TPE) was used as Bayesian optimization for parameters of SVM and XGBoost. Random search was done for comparison with TPE. Leave-one-out cross-validation was used for optimizing and evaluating the performance of our CADx system. Performance was evaluated using area under the curve (AUC) of receiver operating characteristic analysis. AUC was calculated 10 times, and its average was obtained. The best averaged AUC of SVM and XGBoost was 0.850 and 0.896, respectively; both were obtained using TPE. XGBoost was generally superior to SVM. Optimal parameters for achieving high AUC were obtained with fewer numbers of trials when using TPE, compared with random search. Bayesian optimization of SVM and XGBoost parameters was more efficient than random search. Based on observer study, AUC values of two board-certified radiologists were 0.898 and 0.822. The results show that diagnostic accuracy of our CADx system was comparable to that of radiologists with respect to classifying lung nodules.

Scale effects and a method for similarity evaluation in micro electrical discharge machining

NASA Astrophysics Data System (ADS)

Liu, Qingyu; Zhang, Qinhe; Wang, Kan; Zhu, Guang; Fu, Xiuzhuo; Zhang, Jianhua

2016-08-01

Electrical discharge machining(EDM) is a promising non-traditional micro machining technology that offers a vast array of applications in the manufacturing industry. However, scale effects occur when machining at the micro-scale, which can make it difficult to predict and optimize the machining performances of micro EDM. A new concept of "scale effects" in micro EDM is proposed, the scale effects can reveal the difference in machining performances between micro EDM and conventional macro EDM. Similarity theory is presented to evaluate the scale effects in micro EDM. Single factor experiments are conducted and the experimental results are analyzed by discussing the similarity difference and similarity precision. The results show that the output results of scale effects in micro EDM do not change linearly with discharge parameters. The values of similarity precision of machining time significantly increase when scaling-down the capacitance or open-circuit voltage. It is indicated that the lower the scale of the discharge parameter, the greater the deviation of non-geometrical similarity degree over geometrical similarity degree, which means that the micro EDM system with lower discharge energy experiences more scale effects. The largest similarity difference is 5.34 while the largest similarity precision can be as high as 114.03. It is suggested that the similarity precision is more effective in reflecting the scale effects and their fluctuation than similarity difference. Consequently, similarity theory is suitable for evaluating the scale effects in micro EDM. This proposed research offers engineering values for optimizing the machining parameters and improving the machining performances of micro EDM.

Optimization of cutting parameters in CNC turning of stainless steel 304 with TiAlN nano coated carbide cutting tool

NASA Astrophysics Data System (ADS)

Durga Prasada Rao, V.; Harsha, N.; Raghu Ram, N. S.; Navya Geethika, V.

2018-02-01

In this work, turning was performed to optimize the surface finish or roughness (Ra) of stainless steel 304 with uncoated and coated carbide tools under dry conditions. The carbide tools were coated with Titanium Aluminium Nitride (TiAlN) nano coating using Physical Vapour Deposition (PVD) method. The machining parameters, viz., cutting speed, depth of cut and feed rate which show major impact on Ra are considered during turning. The experiments are designed as per Taguchi orthogonal array and machining process is done accordingly. Then second-order regression equations have been developed on the basis of experimental results for Ra in terms of machining parameters used. Regarding the effect of machining parameters, an upward trend is observed in Ra with respect to feed rate, and as cutting speed increases the Ra value increased slightly due to chatter and vibrations. The adequacy of response variable (Ra) is tested by conducting additional experiments. The predicted Ra values are found to be a close match of their corresponding experimental values of uncoated and coated tools. The corresponding average % errors are found to be within the acceptable limits. Then the surface roughness equations of uncoated and coated tools are set as the objectives of optimization problem and are solved by using Differential Evolution (DE) algorithm. Also the tool lives of uncoated and coated tools are predicted by using Taylor’s tool life equation.

A comparison of optimal MIMO linear and nonlinear models for brain machine interfaces

NASA Astrophysics Data System (ADS)

Kim, S.-P.; Sanchez, J. C.; Rao, Y. N.; Erdogmus, D.; Carmena, J. M.; Lebedev, M. A.; Nicolelis, M. A. L.; Principe, J. C.

2006-06-01

The field of brain-machine interfaces requires the estimation of a mapping from spike trains collected in motor cortex areas to the hand kinematics of the behaving animal. This paper presents a systematic investigation of several linear (Wiener filter, LMS adaptive filters, gamma filter, subspace Wiener filters) and nonlinear models (time-delay neural network and local linear switching models) applied to datasets from two experiments in monkeys performing motor tasks (reaching for food and target hitting). Ensembles of 100-200 cortical neurons were simultaneously recorded in these experiments, and even larger neuronal samples are anticipated in the future. Due to the large size of the models (thousands of parameters), the major issue studied was the generalization performance. Every parameter of the models (not only the weights) was selected optimally using signal processing and machine learning techniques. The models were also compared statistically with respect to the Wiener filter as the baseline. Each of the optimization procedures produced improvements over that baseline for either one of the two datasets or both.

A comparison of optimal MIMO linear and nonlinear models for brain-machine interfaces.

PubMed

Kim, S-P; Sanchez, J C; Rao, Y N; Erdogmus, D; Carmena, J M; Lebedev, M A; Nicolelis, M A L; Principe, J C

2006-06-01

The field of brain-machine interfaces requires the estimation of a mapping from spike trains collected in motor cortex areas to the hand kinematics of the behaving animal. This paper presents a systematic investigation of several linear (Wiener filter, LMS adaptive filters, gamma filter, subspace Wiener filters) and nonlinear models (time-delay neural network and local linear switching models) applied to datasets from two experiments in monkeys performing motor tasks (reaching for food and target hitting). Ensembles of 100-200 cortical neurons were simultaneously recorded in these experiments, and even larger neuronal samples are anticipated in the future. Due to the large size of the models (thousands of parameters), the major issue studied was the generalization performance. Every parameter of the models (not only the weights) was selected optimally using signal processing and machine learning techniques. The models were also compared statistically with respect to the Wiener filter as the baseline. Each of the optimization procedures produced improvements over that baseline for either one of the two datasets or both.

Experimental Research and Mathematical Modeling of Parameters Effecting on Cutting Force and SurfaceRoughness in CNC Turning Process

NASA Astrophysics Data System (ADS)

Zeqiri, F.; Alkan, M.; Kaya, B.; Toros, S.

2018-01-01

In this paper, the effects of cutting parameters on cutting forces and surface roughness based on Taguchi experimental design method are determined. Taguchi L9 orthogonal array is used to investigate the effects of machining parameters. Optimal cutting conditions are determined using the signal/noise (S/N) ratio which is calculated by average surface roughness and cutting force. Using results of analysis, effects of parameters on both average surface roughness and cutting forces are calculated on Minitab 17 using ANOVA method. The material that was investigated is Inconel 625 steel for two cases with heat treatment and without heat treatment. The predicted and calculated values with measurement are very close to each other. Confirmation test of results showed that the Taguchi method was very successful in the optimization of machining parameters for maximum surface roughness and cutting forces in the CNC turning process.

Computational Fluid Dynamic Simulation of Flow in Abrasive Water Jet Machining

NASA Astrophysics Data System (ADS)

Venugopal, S.; Sathish, S.; Jothi Prakash, V. M.; Gopalakrishnan, T.

2017-03-01

Abrasive water jet cutting is one of the most recently developed non-traditional manufacturing technologies. In this machining, the abrasives are mixed with suspended liquid to form semi liquid mixture. The general nature of flow through the machining, results in fleeting wear of the nozzle which decrease the cutting performance. The inlet pressure of the abrasive water suspension has main effect on the major destruction characteristics of the inner surface of the nozzle. The aim of the project is to analyze the effect of inlet pressure on wall shear and exit kinetic energy. The analysis could be carried out by changing the taper angle of the nozzle, so as to obtain optimized process parameters for minimum nozzle wear. The two phase flow analysis would be carried by using computational fluid dynamics tool CFX. It is also used to analyze the flow characteristics of abrasive water jet machining on the inner surface of the nozzle. The availability of optimized process parameters of abrasive water jet machining (AWJM) is limited to water and experimental test can be cost prohibitive. In this case, Computational fluid dynamics analysis would provide better results.

NMR Parameters Determination through ACE Committee Machine with Genetic Implanted Fuzzy Logic and Genetic Implanted Neural Network

NASA Astrophysics Data System (ADS)

Asoodeh, Mojtaba; Bagheripour, Parisa; Gholami, Amin

2015-06-01

Free fluid porosity and rock permeability, undoubtedly the most critical parameters of hydrocarbon reservoir, could be obtained by processing of nuclear magnetic resonance (NMR) log. Despite conventional well logs (CWLs), NMR logging is very expensive and time-consuming. Therefore, idea of synthesizing NMR log from CWLs would be of a great appeal among reservoir engineers. For this purpose, three optimization strategies are followed. Firstly, artificial neural network (ANN) is optimized by virtue of hybrid genetic algorithm-pattern search (GA-PS) technique, then fuzzy logic (FL) is optimized by means of GA-PS, and eventually an alternative condition expectation (ACE) model is constructed using the concept of committee machine to combine outputs of optimized and non-optimized FL and ANN models. Results indicated that optimization of traditional ANN and FL model using GA-PS technique significantly enhances their performances. Furthermore, the ACE committee of aforementioned models produces more accurate and reliable results compared with a singular model performing alone.

CNC Machining Of The Complex Copper Electrodes

NASA Astrophysics Data System (ADS)

Popan, Ioan Alexandru; Balc, Nicolae; Popan, Alina

2015-07-01

This paper presents the machining process of the complex copper electrodes. Machining of the complex shapes in copper is difficult because this material is soft and sticky. This research presents the main steps for processing those copper electrodes at a high dimensional accuracy and a good surface quality. Special tooling solutions are required for this machining process and optimal process parameters have been found for the accurate CNC equipment, using smart CAD/CAM software.

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features

PubMed Central

Hu, Yu-Chuan; Li, Gang; Yang, Yang; Han, Yu; Sun, Ying-Zhi; Liu, Zhi-Cheng; Tian, Qiang; Han, Zi-Yang; Liu, Le-De; Hu, Bin-Quan; Qiu, Zi-Yu; Wang, Wen; Cui, Guang-Bin

2017-01-01

Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization. PMID:28599282

Optimizing a machine learning based glioma grading system using multi-parametric MRI histogram and texture features.

PubMed

Zhang, Xin; Yan, Lin-Feng; Hu, Yu-Chuan; Li, Gang; Yang, Yang; Han, Yu; Sun, Ying-Zhi; Liu, Zhi-Cheng; Tian, Qiang; Han, Zi-Yang; Liu, Le-De; Hu, Bin-Quan; Qiu, Zi-Yu; Wang, Wen; Cui, Guang-Bin

2017-07-18

Current machine learning techniques provide the opportunity to develop noninvasive and automated glioma grading tools, by utilizing quantitative parameters derived from multi-modal magnetic resonance imaging (MRI) data. However, the efficacies of different machine learning methods in glioma grading have not been investigated.A comprehensive comparison of varied machine learning methods in differentiating low-grade gliomas (LGGs) and high-grade gliomas (HGGs) as well as WHO grade II, III and IV gliomas based on multi-parametric MRI images was proposed in the current study. The parametric histogram and image texture attributes of 120 glioma patients were extracted from the perfusion, diffusion and permeability parametric maps of preoperative MRI. Then, 25 commonly used machine learning classifiers combined with 8 independent attribute selection methods were applied and evaluated using leave-one-out cross validation (LOOCV) strategy. Besides, the influences of parameter selection on the classifying performances were investigated. We found that support vector machine (SVM) exhibited superior performance to other classifiers. By combining all tumor attributes with synthetic minority over-sampling technique (SMOTE), the highest classifying accuracy of 0.945 or 0.961 for LGG and HGG or grade II, III and IV gliomas was achieved. Application of Recursive Feature Elimination (RFE) attribute selection strategy further improved the classifying accuracies. Besides, the performances of LibSVM, SMO, IBk classifiers were influenced by some key parameters such as kernel type, c, gama, K, etc. SVM is a promising tool in developing automated preoperative glioma grading system, especially when being combined with RFE strategy. Model parameters should be considered in glioma grading model optimization.

Pulmonary Nodule Recognition Based on Multiple Kernel Learning Support Vector Machine-PSO

PubMed Central

Zhu, Zhichuan; Zhao, Qingdong; Liu, Liwei; Zhang, Lijuan

2018-01-01

Pulmonary nodule recognition is the core module of lung CAD. The Support Vector Machine (SVM) algorithm has been widely used in pulmonary nodule recognition, and the algorithm of Multiple Kernel Learning Support Vector Machine (MKL-SVM) has achieved good results therein. Based on grid search, however, the MKL-SVM algorithm needs long optimization time in course of parameter optimization; also its identification accuracy depends on the fineness of grid. In the paper, swarm intelligence is introduced and the Particle Swarm Optimization (PSO) is combined with MKL-SVM algorithm to be MKL-SVM-PSO algorithm so as to realize global optimization of parameters rapidly. In order to obtain the global optimal solution, different inertia weights such as constant inertia weight, linear inertia weight, and nonlinear inertia weight are applied to pulmonary nodules recognition. The experimental results show that the model training time of the proposed MKL-SVM-PSO algorithm is only 1/7 of the training time of the MKL-SVM grid search algorithm, achieving better recognition effect. Moreover, Euclidean norm of normalized error vector is proposed to measure the proximity between the average fitness curve and the optimal fitness curve after convergence. Through statistical analysis of the average of 20 times operation results with different inertial weights, it can be seen that the dynamic inertial weight is superior to the constant inertia weight in the MKL-SVM-PSO algorithm. In the dynamic inertial weight algorithm, the parameter optimization time of nonlinear inertia weight is shorter; the average fitness value after convergence is much closer to the optimal fitness value, which is better than the linear inertial weight. Besides, a better nonlinear inertial weight is verified. PMID:29853983

Pulmonary Nodule Recognition Based on Multiple Kernel Learning Support Vector Machine-PSO.

PubMed

Li, Yang; Zhu, Zhichuan; Hou, Alin; Zhao, Qingdong; Liu, Liwei; Zhang, Lijuan

2018-01-01

Pulmonary nodule recognition is the core module of lung CAD. The Support Vector Machine (SVM) algorithm has been widely used in pulmonary nodule recognition, and the algorithm of Multiple Kernel Learning Support Vector Machine (MKL-SVM) has achieved good results therein. Based on grid search, however, the MKL-SVM algorithm needs long optimization time in course of parameter optimization; also its identification accuracy depends on the fineness of grid. In the paper, swarm intelligence is introduced and the Particle Swarm Optimization (PSO) is combined with MKL-SVM algorithm to be MKL-SVM-PSO algorithm so as to realize global optimization of parameters rapidly. In order to obtain the global optimal solution, different inertia weights such as constant inertia weight, linear inertia weight, and nonlinear inertia weight are applied to pulmonary nodules recognition. The experimental results show that the model training time of the proposed MKL-SVM-PSO algorithm is only 1/7 of the training time of the MKL-SVM grid search algorithm, achieving better recognition effect. Moreover, Euclidean norm of normalized error vector is proposed to measure the proximity between the average fitness curve and the optimal fitness curve after convergence. Through statistical analysis of the average of 20 times operation results with different inertial weights, it can be seen that the dynamic inertial weight is superior to the constant inertia weight in the MKL-SVM-PSO algorithm. In the dynamic inertial weight algorithm, the parameter optimization time of nonlinear inertia weight is shorter; the average fitness value after convergence is much closer to the optimal fitness value, which is better than the linear inertial weight. Besides, a better nonlinear inertial weight is verified.

Tuning Parameters in Heuristics by Using Design of Experiments Methods

NASA Technical Reports Server (NTRS)

Arin, Arif; Rabadi, Ghaith; Unal, Resit

2010-01-01

With the growing complexity of today's large scale problems, it has become more difficult to find optimal solutions by using exact mathematical methods. The need to find near-optimal solutions in an acceptable time frame requires heuristic approaches. In many cases, however, most heuristics have several parameters that need to be "tuned" before they can reach good results. The problem then turns into "finding best parameter setting" for the heuristics to solve the problems efficiently and timely. One-Factor-At-a-Time (OFAT) approach for parameter tuning neglects the interactions between parameters. Design of Experiments (DOE) tools can be instead employed to tune the parameters more effectively. In this paper, we seek the best parameter setting for a Genetic Algorithm (GA) to solve the single machine total weighted tardiness problem in which n jobs must be scheduled on a single machine without preemption, and the objective is to minimize the total weighted tardiness. Benchmark instances for the problem are available in the literature. To fine tune the GA parameters in the most efficient way, we compare multiple DOE models including 2-level (2k ) full factorial design, orthogonal array design, central composite design, D-optimal design and signal-to-noise (SIN) ratios. In each DOE method, a mathematical model is created using regression analysis, and solved to obtain the best parameter setting. After verification runs using the tuned parameter setting, the preliminary results for optimal solutions of multiple instances were found efficiently.

Tool geometry and damage mechanisms influencing CNC turning efficiency of Ti6Al4V

NASA Astrophysics Data System (ADS)

Suresh, Sangeeth; Hamid, Darulihsan Abdul; Yazid, M. Z. A.; Nasuha, Nurdiyanah; Ain, Siti Nurul

2017-12-01

Ti6Al4V or Grade 5 titanium alloy is widely used in the aerospace, medical, automotive and fabrication industries, due to its distinctive combination of mechanical and physical properties. Ti6Al4V has always been perverse during its machining, strangely due to the same mix of properties mentioned earlier. Ti6Al4V machining has resulted in shorter cutting tool life which has led to objectionable surface integrity and rapid failure of the parts machined. However, the proven functional relevance of this material has prompted extensive research in the optimization of machine parameters and cutting tool characteristics. Cutting tool geometry plays a vital role in ensuring dimensional and geometric accuracy in machined parts. In this study, an experimental investigation is actualized to optimize the nose radius and relief angles of the cutting tools and their interaction to different levels of machining parameters. Low elastic modulus and thermal conductivity of Ti6Al4V contribute to the rapid tool damage. The impact of these properties over the tool tips damage is studied. An experimental design approach is utilized in the CNC turning process of Ti6Al4V to statistically analyze and propose optimum levels of input parameters to lengthen the tool life and enhance surface characteristics of the machined parts. A greater tool nose radius with a straight flank, combined with low feed rates have resulted in a desirable surface integrity. The presence of relief angle has proven to aggravate tool damage and also dimensional instability in the CNC turning of Ti6Al4V.

Bifurcation analysis of eight coupled degenerate optical parametric oscillators

NASA Astrophysics Data System (ADS)

Ito, Daisuke; Ueta, Tetsushi; Aihara, Kazuyuki

2018-06-01

A degenerate optical parametric oscillator (DOPO) network realized as a coherent Ising machine can be used to solve combinatorial optimization problems. Both theoretical and experimental investigations into the performance of DOPO networks have been presented previously. However a problem remains, namely that the dynamics of the DOPO network itself can lower the search success rates of globally optimal solutions for Ising problems. This paper shows that the problem is caused by pitchfork bifurcations due to the symmetry structure of coupled DOPOs. Some two-parameter bifurcation diagrams of equilibrium points express the performance deterioration. It is shown that the emergence of non-ground states regarding local minima hampers the system from reaching the ground states corresponding to the global minimum. We then describe a parametric strategy for leading a system to the ground state by actively utilizing the bifurcation phenomena. By adjusting the parameters to break particular symmetry, we find appropriate parameter sets that allow the coherent Ising machine to obtain the globally optimal solution alone.

Minimization of energy and surface roughness of the products machined by milling

NASA Astrophysics Data System (ADS)

Belloufi, A.; Abdelkrim, M.; Bouakba, M.; Rezgui, I.

2017-08-01

Metal cutting represents a large portion in the manufacturing industries, which makes this process the largest consumer of energy. Energy consumption is an indirect source of carbon footprint, we know that CO2 emissions come from the production of energy. Therefore high energy consumption requires a large production, which leads to high cost and a large amount of CO2 emissions. At this day, a lot of researches done on the Metal cutting, but the environmental problems of the processes are rarely discussed. The right selection of cutting parameters is an effective method to reduce energy consumption because of the direct relationship between energy consumption and cutting parameters in machining processes. Therefore, one of the objectives of this research is to propose an optimization strategy suitable for machining processes (milling) to achieve the optimum cutting conditions based on the criterion of the energy consumed during the milling. In this paper the problem of energy consumed in milling is solved by an optimization method chosen. The optimization is done according to the different requirements in the process of roughing and finishing under various technological constraints.

Low optical-loss facet preparation for silica-on-silicon photonics using the ductile dicing regime

NASA Astrophysics Data System (ADS)

Carpenter, Lewis G.; Rogers, Helen L.; Cooper, Peter A.; Holmes, Christopher; Gates, James C.; Smith, Peter G. R.

2013-11-01

The efficient production of high-quality facets for low-loss coupling is a significant production issue in integrated optics, usually requiring time consuming and manually intensive lapping and polishing steps, which add considerably to device fabrication costs. The development of precision dicing saws with diamond impregnated blades has allowed optical grade surfaces to be machined in crystalline materials such as lithium niobate and garnets. In this report we investigate the optimization of dicing machine parameters to obtain optical quality surfaces in a silica-on-silicon planar device demonstrating high optical quality in a commercially important glassy material. We achieve a surface roughness of 4.9 nm (Sa) using the optimized dicing conditions. By machining a groove across a waveguide, using the optimized dicing parameters, a grating based loss measurement technique is used to measure precisely the average free space interface loss per facet caused by scattering as a consequence of surface roughness. The average interface loss per facet was calculated to be: -0.63 dB and -0.76 dB for the TE and TM polarizations, respectively.

Application of Taguchi-grey method to optimize drilling of EMS 45 steel using minimum quantity lubrication (MQL) with multiple performance characteristics

NASA Astrophysics Data System (ADS)

Soepangkat, Bobby O. P.; Suhardjono, Pramujati, Bambang

2017-06-01

Machining under minimum quantity lubrication (MQL) has drawn the attention of researchers as an alternative to the traditionally used wet and dry machining conditions with the purpose to minimize the cooling and lubricating cost, as well as to reduce cutting zone temperature, tool wear, and hole surface roughness. Drilling is one of the important operations to assemble machine components. The objective of this study was to optimize drilling parameters such as cutting feed and cutting speed, drill type and drill point angle on the thrust force, torque, hole surface roughness and tool flank wear in drilling EMS 45 tool steel using MQL. In this study, experiments were carried out as per Taguchi design of experiments while an L18 orthogonal array was used to study the influence of various combinations of drilling parameters and tool geometries on the thrust force, torque, hole surface roughness and tool flank wear. The optimum drilling parameters was determined by using grey relational grade obtained from grey relational analysis for multiple-performance characteristics. The drilling experiments were carried out by using twist drill and CNC machining center. This work is useful for optimum values selection of various drilling parameters and tool geometries that would not only minimize the thrust force and torque, but also reduce hole surface roughness and tool flank wear.

Application of high-performance computing to numerical simulation of human movement

NASA Technical Reports Server (NTRS)

Anderson, F. C.; Ziegler, J. M.; Pandy, M. G.; Whalen, R. T.

1995-01-01

We have examined the feasibility of using massively-parallel and vector-processing supercomputers to solve large-scale optimization problems for human movement. Specifically, we compared the computational expense of determining the optimal controls for the single support phase of gait using a conventional serial machine (SGI Iris 4D25), a MIMD parallel machine (Intel iPSC/860), and a parallel-vector-processing machine (Cray Y-MP 8/864). With the human body modeled as a 14 degree-of-freedom linkage actuated by 46 musculotendinous units, computation of the optimal controls for gait could take up to 3 months of CPU time on the Iris. Both the Cray and the Intel are able to reduce this time to practical levels. The optimal solution for gait can be found with about 77 hours of CPU on the Cray and with about 88 hours of CPU on the Intel. Although the overall speeds of the Cray and the Intel were found to be similar, the unique capabilities of each machine are better suited to different portions of the computational algorithm used. The Intel was best suited to computing the derivatives of the performance criterion and the constraints whereas the Cray was best suited to parameter optimization of the controls. These results suggest that the ideal computer architecture for solving very large-scale optimal control problems is a hybrid system in which a vector-processing machine is integrated into the communication network of a MIMD parallel machine.

Grinding, Machining Morphological Studies on C/SiC Composites

NASA Astrophysics Data System (ADS)

Xiao, Chun-fang; Han, Bing

2018-05-01

C/SiC composite is a typical material difficult to machine. It is hard and brittle. In machining, the cutting force is large, the material removal rate is low, the edge is prone to collapse, and the tool wear is serious. In this paper, the grinding of C/Si composites material along the direction of fiber distribution is studied respectively. The surface microstructure and mechanical properties of C/SiC composites processed by ultrasonic machining were evaluated. The change of surface quality with the change of processing parameters has also been studied. By comparing the performances of conventional grinding and ultrasonic grinding, the surface roughness and functional characteristics of the material can be improved by optimizing the processing parameters.

Application of dragonfly algorithm for optimal performance analysis of process parameters in turn-mill operations- A case study

NASA Astrophysics Data System (ADS)

Vikram, K. Arun; Ratnam, Ch; Lakshmi, VVK; Kumar, A. Sunny; Ramakanth, RT

2018-02-01

Meta-heuristic multi-response optimization methods are widely in use to solve multi-objective problems to obtain Pareto optimal solutions during optimization. This work focuses on optimal multi-response evaluation of process parameters in generating responses like surface roughness (Ra), surface hardness (H) and tool vibration displacement amplitude (Vib) while performing operations like tangential and orthogonal turn-mill processes on A-axis Computer Numerical Control vertical milling center. Process parameters like tool speed, feed rate and depth of cut are considered as process parameters machined over brass material under dry condition with high speed steel end milling cutters using Taguchi design of experiments (DOE). Meta-heuristic like Dragonfly algorithm is used to optimize the multi-objectives like ‘Ra’, ‘H’ and ‘Vib’ to identify the optimal multi-response process parameters combination. Later, the results thus obtained from multi-objective dragonfly algorithm (MODA) are compared with another multi-response optimization technique Viz. Grey relational analysis (GRA).

Rapid performance modeling and parameter regression of geodynamic models

NASA Astrophysics Data System (ADS)

Brown, J.; Duplyakin, D.

2016-12-01

Geodynamic models run in a parallel environment have many parameters with complicated effects on performance and scientifically-relevant functionals. Manually choosing an efficient machine configuration and mapping out the parameter space requires a great deal of expert knowledge and time-consuming experiments. We propose an active learning technique based on Gaussion Process Regression to automatically select experiments to map out the performance landscape with respect to scientific and machine parameters. The resulting performance model is then used to select optimal experiments for improving the accuracy of a reduced order model per unit of computational cost. We present the framework and evaluate its quality and capability using popular lithospheric dynamics models.

Automated Design of Complex Dynamic Systems

PubMed Central

Hermans, Michiel; Schrauwen, Benjamin; Bienstman, Peter; Dambre, Joni

2014-01-01

Several fields of study are concerned with uniting the concept of computation with that of the design of physical systems. For example, a recent trend in robotics is to design robots in such a way that they require a minimal control effort. Another example is found in the domain of photonics, where recent efforts try to benefit directly from the complex nonlinear dynamics to achieve more efficient signal processing. The underlying goal of these and similar research efforts is to internalize a large part of the necessary computations within the physical system itself by exploiting its inherent non-linear dynamics. This, however, often requires the optimization of large numbers of system parameters, related to both the system's structure as well as its material properties. In addition, many of these parameters are subject to fabrication variability or to variations through time. In this paper we apply a machine learning algorithm to optimize physical dynamic systems. We show that such algorithms, which are normally applied on abstract computational entities, can be extended to the field of differential equations and used to optimize an associated set of parameters which determine their behavior. We show that machine learning training methodologies are highly useful in designing robust systems, and we provide a set of both simple and complex examples using models of physical dynamical systems. Interestingly, the derived optimization method is intimately related to direct collocation a method known in the field of optimal control. Our work suggests that the application domains of both machine learning and optimal control have a largely unexplored overlapping area which envelopes a novel design methodology of smart and highly complex physical systems. PMID:24497969

Machine Learning Approach to Optimizing Combined Stimulation and Medication Therapies for Parkinson's Disease.

PubMed

Shamir, Reuben R; Dolber, Trygve; Noecker, Angela M; Walter, Benjamin L; McIntyre, Cameron C

2015-01-01

Deep brain stimulation (DBS) of the subthalamic region is an established therapy for advanced Parkinson's disease (PD). However, patients often require time-intensive post-operative management to balance their coupled stimulation and medication treatments. Given the large and complex parameter space associated with this task, we propose that clinical decision support systems (CDSS) based on machine learning algorithms could assist in treatment optimization. Develop a proof-of-concept implementation of a CDSS that incorporates patient-specific details on both stimulation and medication. Clinical data from 10 patients, and 89 post-DBS surgery visits, were used to create a prototype CDSS. The system was designed to provide three key functions: (1) information retrieval; (2) visualization of treatment, and; (3) recommendation on expected effective stimulation and drug dosages, based on three machine learning methods that included support vector machines, Naïve Bayes, and random forest. Measures of medication dosages, time factors, and symptom-specific pre-operative response to levodopa were significantly correlated with post-operative outcomes (P < 0.05) and their effect on outcomes was of similar magnitude to that of DBS. Using those results, the combined machine learning algorithms were able to accurately predict 86% (12/14) of the motor improvement scores at one year after surgery. Using patient-specific details, an appropriately parameterized CDSS could help select theoretically optimal DBS parameter settings and medication dosages that have potential to improve the clinical management of PD patients. Copyright © 2015 Elsevier Inc. All rights reserved.

Optimal design of earth-moving machine elements with cusp catastrophe theory application

NASA Astrophysics Data System (ADS)

Pitukhin, A. V.; Skobtsov, I. G.

2017-10-01

This paper deals with the optimal design problem solution for the operator of an earth-moving machine with a roll-over protective structure (ROPS) in terms of the catastrophe theory. A brief description of the catastrophe theory is presented, the cusp catastrophe is considered, control parameters are viewed as Gaussian stochastic quantities in the first part of the paper. The statement of optimal design problem is given in the second part of the paper. It includes the choice of the objective function and independent design variables, establishment of system limits. The objective function is determined as mean total cost that includes initial cost and cost of failure according to the cusp catastrophe probability. Algorithm of random search method with an interval reduction subject to side and functional constraints is given in the last part of the paper. The way of optimal design problem solution can be applied to choose rational ROPS parameters, which will increase safety and reduce production and exploitation expenses.

The Bi-Directional Prediction of Carbon Fiber Production Using a Combination of Improved Particle Swarm Optimization and Support Vector Machine.

PubMed

Xiao, Chuncai; Hao, Kuangrong; Ding, Yongsheng

2014-12-30

This paper creates a bi-directional prediction model to predict the performance of carbon fiber and the productive parameters based on a support vector machine (SVM) and improved particle swarm optimization (IPSO) algorithm (SVM-IPSO). In the SVM, it is crucial to select the parameters that have an important impact on the performance of prediction. The IPSO is proposed to optimize them, and then the SVM-IPSO model is applied to the bi-directional prediction of carbon fiber production. The predictive accuracy of SVM is mainly dependent on its parameters, and IPSO is thus exploited to seek the optimal parameters for SVM in order to improve its prediction capability. Inspired by a cell communication mechanism, we propose IPSO by incorporating information of the global best solution into the search strategy to improve exploitation, and we employ IPSO to establish the bi-directional prediction model: in the direction of the forward prediction, we consider productive parameters as input and property indexes as output; in the direction of the backward prediction, we consider property indexes as input and productive parameters as output, and in this case, the model becomes a scheme design for novel style carbon fibers. The results from a set of the experimental data show that the proposed model can outperform the radial basis function neural network (RNN), the basic particle swarm optimization (PSO) method and the hybrid approach of genetic algorithm and improved particle swarm optimization (GA-IPSO) method in most of the experiments. In other words, simulation results demonstrate the effectiveness and advantages of the SVM-IPSO model in dealing with the problem of forecasting.

Gas flow parameters in laser cutting of wood- nozzle design

Treesearch

Kali Mukherjee; Tom Grendzwell; Parwaiz A.A. Khan; Charles McMillin

1990-01-01

The Automated Lumber Processing System (ALPS) is an ongoing team research effort to optimize the yield of parts in a furniture rough mill. The process is designed to couple aspects of computer vision, computer optimization of yield, and laser cutting. This research is focused on optimizing laser wood cutting. Laser machining of lumber has the advantage over...

Honing process optimization algorithms

NASA Astrophysics Data System (ADS)

Kadyrov, Ramil R.; Charikov, Pavel N.; Pryanichnikova, Valeria V.

2018-03-01

This article considers the relevance of honing processes for creating high-quality mechanical engineering products. The features of the honing process are revealed and such important concepts as the task for optimization of honing operations, the optimal structure of the honing working cycles, stepped and stepless honing cycles, simulation of processing and its purpose are emphasized. It is noted that the reliability of the mathematical model determines the quality parameters of the honing process control. An algorithm for continuous control of the honing process is proposed. The process model reliably describes the machining of a workpiece in a sufficiently wide area and can be used to operate the CNC machine CC743.

Optimization of Machining Process Parameters for Surface Roughness of Al-Composites

NASA Astrophysics Data System (ADS)

Sharma, S.

2013-10-01

Metal matrix composites (MMCs) have become a leading material among the various types of composite materials for different applications due to their excellent engineering properties. Among the various types of composites materials, aluminum MMCs have received considerable attention in automobile and aerospace applications. These materials are known as the difficult-to-machine materials because of the hardness and abrasive nature of reinforcement element-like silicon carbide particles. In the present investigation Al-SiC composite was produced by stir casting process. The Brinell hardness of the alloy after SiC addition had increased from 74 ± 2 to 95 ± 5 respectively. The composite was machined using CNC turning center under different machining parameters such as cutting speed (S), feed rate (F), depth of cut (D) and nose radius (R). The effect of machining parameters on surface roughness (Ra) was studied using response surface methodology. Face centered composite design with three levels of each factor was used for surface roughness study of the developed composite. A response surface model for surface roughness was developed in terms of main factors (S, F, D and R) and their significant interactions (SD, SR, FD and FR). The developed model was validated by conducting experiments under different conditions. Further the model was optimized for minimum surface roughness. An error of 3-7 % was observed in the modeled and experimental results. Further, it was fond that the surface roughness of Al-alloy at optimum conditions is lower than that of Al-SiC composite.

Bayesian Optimization for Neuroimaging Pre-processing in Brain Age Classification and Prediction

PubMed Central

Lancaster, Jenessa; Lorenz, Romy; Leech, Rob; Cole, James H.

2018-01-01

Neuroimaging-based age prediction using machine learning is proposed as a biomarker of brain aging, relating to cognitive performance, health outcomes and progression of neurodegenerative disease. However, even leading age-prediction algorithms contain measurement error, motivating efforts to improve experimental pipelines. T1-weighted MRI is commonly used for age prediction, and the pre-processing of these scans involves normalization to a common template and resampling to a common voxel size, followed by spatial smoothing. Resampling parameters are often selected arbitrarily. Here, we sought to improve brain-age prediction accuracy by optimizing resampling parameters using Bayesian optimization. Using data on N = 2003 healthy individuals (aged 16–90 years) we trained support vector machines to (i) distinguish between young (<22 years) and old (>50 years) brains (classification) and (ii) predict chronological age (regression). We also evaluated generalisability of the age-regression model to an independent dataset (CamCAN, N = 648, aged 18–88 years). Bayesian optimization was used to identify optimal voxel size and smoothing kernel size for each task. This procedure adaptively samples the parameter space to evaluate accuracy across a range of possible parameters, using independent sub-samples to iteratively assess different parameter combinations to arrive at optimal values. When distinguishing between young and old brains a classification accuracy of 88.1% was achieved, (optimal voxel size = 11.5 mm3, smoothing kernel = 2.3 mm). For predicting chronological age, a mean absolute error (MAE) of 5.08 years was achieved, (optimal voxel size = 3.73 mm3, smoothing kernel = 3.68 mm). This was compared to performance using default values of 1.5 mm3 and 4mm respectively, resulting in MAE = 5.48 years, though this 7.3% improvement was not statistically significant. When assessing generalisability, best performance was achieved when applying the entire Bayesian optimization framework to the new dataset, out-performing the parameters optimized for the initial training dataset. Our study outlines the proof-of-principle that neuroimaging models for brain-age prediction can use Bayesian optimization to derive case-specific pre-processing parameters. Our results suggest that different pre-processing parameters are selected when optimization is conducted in specific contexts. This potentially motivates use of optimization techniques at many different points during the experimental process, which may improve statistical sensitivity and reduce opportunities for experimenter-led bias. PMID:29483870

Hybrid Disease Diagnosis Using Multiobjective Optimization with Evolutionary Parameter Optimization

PubMed Central

Nalluri, MadhuSudana Rao; K., Kannan; M., Manisha

2017-01-01

With the widespread adoption of e-Healthcare and telemedicine applications, accurate, intelligent disease diagnosis systems have been profoundly coveted. In recent years, numerous individual machine learning-based classifiers have been proposed and tested, and the fact that a single classifier cannot effectively classify and diagnose all diseases has been almost accorded with. This has seen a number of recent research attempts to arrive at a consensus using ensemble classification techniques. In this paper, a hybrid system is proposed to diagnose ailments using optimizing individual classifier parameters for two classifier techniques, namely, support vector machine (SVM) and multilayer perceptron (MLP) technique. We employ three recent evolutionary algorithms to optimize the parameters of the classifiers above, leading to six alternative hybrid disease diagnosis systems, also referred to as hybrid intelligent systems (HISs). Multiple objectives, namely, prediction accuracy, sensitivity, and specificity, have been considered to assess the efficacy of the proposed hybrid systems with existing ones. The proposed model is evaluated on 11 benchmark datasets, and the obtained results demonstrate that our proposed hybrid diagnosis systems perform better in terms of disease prediction accuracy, sensitivity, and specificity. Pertinent statistical tests were carried out to substantiate the efficacy of the obtained results. PMID:29065626

Identification of Synchronous Machine Stability - Parameters: AN On-Line Time-Domain Approach.

NASA Astrophysics Data System (ADS)

Le, Loc Xuan

1987-09-01

A time-domain modeling approach is described which enables the stability-study parameters of the synchronous machine to be determined directly from input-output data measured at the terminals of the machine operating under normal conditions. The transient responses due to system perturbations are used to identify the parameters of the equivalent circuit models. The described models are verified by comparing their responses with the machine responses generated from the transient stability models of a small three-generator multi-bus power system and of a single -machine infinite-bus power network. The least-squares method is used for the solution of the model parameters. As a precaution against ill-conditioned problems, the singular value decomposition (SVD) is employed for its inherent numerical stability. In order to identify the equivalent-circuit parameters uniquely, the solution of a linear optimization problem with non-linear constraints is required. Here, the SVD appears to offer a simple solution to this otherwise difficult problem. Furthermore, the SVD yields solutions with small bias and, therefore, physically meaningful parameters even in the presence of noise in the data. The question concerning the need for a more advanced model of the synchronous machine which describes subtransient and even sub-subtransient behavior is dealt with sensibly by the concept of condition number. The concept provides a quantitative measure for determining whether such an advanced model is indeed necessary. Finally, the recursive SVD algorithm is described for real-time parameter identification and tracking of slowly time-variant parameters. The algorithm is applied to identify the dynamic equivalent power system model.

An Integrated Framework for Parameter-based Optimization of Scientific Workflows.

PubMed

Kumar, Vijay S; Sadayappan, P; Mehta, Gaurang; Vahi, Karan; Deelman, Ewa; Ratnakar, Varun; Kim, Jihie; Gil, Yolanda; Hall, Mary; Kurc, Tahsin; Saltz, Joel

2009-01-01

Data analysis processes in scientific applications can be expressed as coarse-grain workflows of complex data processing operations with data flow dependencies between them. Performance optimization of these workflows can be viewed as a search for a set of optimal values in a multi-dimensional parameter space. While some performance parameters such as grouping of workflow components and their mapping to machines do not a ect the accuracy of the output, others may dictate trading the output quality of individual components (and of the whole workflow) for performance. This paper describes an integrated framework which is capable of supporting performance optimizations along multiple dimensions of the parameter space. Using two real-world applications in the spatial data analysis domain, we present an experimental evaluation of the proposed framework.

The optimization study on the tool wear of carbide cutting tool during milling Carbon Fibre Reinforced (CFRP) using Response Surface Methodology (RSM)

NASA Astrophysics Data System (ADS)

Nor Khairusshima, M. K.; Hafiz Zakwan, B. Muhammad; Suhaily, M.; Sharifah, I. S. S.; Shaffiar, N. M.; Rashid, M. A. N.

2018-01-01

Carbon Fibre Reinforced Plastic (CFRP) composite has become one of famous materials in industry, such as automotive, aeronautics, aerospace and aircraft. CFRP is attractive due to its properties, which promising better strength and high specification of mechanical properties other than its high resistance to corrosion. Other than being abrasive material due to the carbon nature, CFRP is an anisotropic material, which the knowledge of machining metal and steel cannot be applied during machining CFRP. The improper technique and parameters used to machine CFRP may result in high tool wear. This paper is to study the tool wear of 8 mm diameter carbide cutting tool during milling CFRP. To predict the suitable cutting parameters within range of 3500-6220 (rev/min), 200-245 (mm/min), and 0.4-1.8 (mm) for cutting speed, speed, feed rate and depth of cut respectively, which produce optimized result (less tool wear), Response Surface Methodology (RSM) has been used. Based on the developed mathematical model, feed rate was identified as the primary significant item that influenced tool wear. The optimized cutting parameters are cutting speed, feed and depth of cut of 3500 rev/min, 200 mm/min and 0.5 mm, respectively, with tool wear of 0.0267 mm. It is also can be observed that as the cutting speed and feed rate increased the tool wear is increasing.

Design optimization for permanent magnet machine with efficient slot per pole ratio

NASA Astrophysics Data System (ADS)

Potnuru, Upendra Kumar; Rao, P. Mallikarjuna

2018-04-01

This paper presents a methodology for the enhancement of a Brush Less Direct Current motor (BLDC) with 6Poles and 8slots. In particular; it is focused on amulti-objective optimization using a Genetic Algorithmand Grey Wolf Optimization developed in MATLAB. The optimization aims to maximize the maximum output power value and minimize the total losses of a motor. This paper presents an application of the MATLAB optimization algorithms to brushless DC (BLDC) motor design, with 7 design parameters chosen to be free. The optimal design parameters of the motor derived by GA are compared with those obtained by Grey Wolf Optimization technique. A comparative report on the specified enhancement approaches appearsthat Grey Wolf Optimization technique has a better convergence.

Integrative image segmentation optimization and machine learning approach for high quality land-use and land-cover mapping using multisource remote sensing data

NASA Astrophysics Data System (ADS)

Gibril, Mohamed Barakat A.; Idrees, Mohammed Oludare; Yao, Kouame; Shafri, Helmi Zulhaidi Mohd

2018-01-01

The growing use of optimization for geographic object-based image analysis and the possibility to derive a wide range of information about the image in textual form makes machine learning (data mining) a versatile tool for information extraction from multiple data sources. This paper presents application of data mining for land-cover classification by fusing SPOT-6, RADARSAT-2, and derived dataset. First, the images and other derived indices (normalized difference vegetation index, normalized difference water index, and soil adjusted vegetation index) were combined and subjected to segmentation process with optimal segmentation parameters obtained using combination of spatial and Taguchi statistical optimization. The image objects, which carry all the attributes of the input datasets, were extracted and related to the target land-cover classes through data mining algorithms (decision tree) for classification. To evaluate the performance, the result was compared with two nonparametric classifiers: support vector machine (SVM) and random forest (RF). Furthermore, the decision tree classification result was evaluated against six unoptimized trials segmented using arbitrary parameter combinations. The result shows that the optimized process produces better land-use land-cover classification with overall classification accuracy of 91.79%, 87.25%, and 88.69% for SVM and RF, respectively, while the results of the six unoptimized classifications yield overall accuracy between 84.44% and 88.08%. Higher accuracy of the optimized data mining classification approach compared to the unoptimized results indicates that the optimization process has significant impact on the classification quality.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Fang Baolong; Department of Mathematics and Physics, Hefei University, Hefei 230022; Yang Zhen

We propose a scheme for implementing a partial general quantum cloning machine with superconducting quantum-interference devices coupled to a nonresonant cavity. By regulating the time parameters, our system can perform optimal symmetric (asymmetric) universal quantum cloning, optimal symmetric (asymmetric) phase-covariant cloning, and optimal symmetric economical phase-covariant cloning. In the scheme the cavity is only virtually excited, thus, the cavity decay is suppressed during the cloning operations.

Optimization of turning process through the analytic flank wear modelling

NASA Astrophysics Data System (ADS)

Del Prete, A.; Franchi, R.; De Lorenzis, D.

2018-05-01

In the present work, the approach used for the optimization of the process capabilities for Oil&Gas components machining will be described. These components are machined by turning of stainless steel castings workpieces. For this purpose, a proper Design Of Experiments (DOE) plan has been designed and executed: as output of the experimentation, data about tool wear have been collected. The DOE has been designed starting from the cutting speed and feed values recommended by the tools manufacturer; the depth of cut parameter has been maintained as a constant. Wear data has been obtained by means the observation of the tool flank wear under an optical microscope: the data acquisition has been carried out at regular intervals of working times. Through a statistical data and regression analysis, analytical models of the flank wear and the tool life have been obtained. The optimization approach used is a multi-objective optimization, which minimizes the production time and the number of cutting tools used, under the constraint on a defined flank wear level. The technique used to solve the optimization problem is a Multi Objective Particle Swarm Optimization (MOPS). The optimization results, validated by the execution of a further experimental campaign, highlighted the reliability of the work and confirmed the usability of the optimized process parameters and the potential benefit for the company.

Machining process influence on the chip form and surface roughness by neuro-fuzzy technique

NASA Astrophysics Data System (ADS)

Anicic, Obrad; Jović, Srđan; Aksić, Danilo; Skulić, Aleksandar; Nedić, Bogdan

2017-04-01

The main aim of the study was to analyze the influence of six machining parameters on the chip shape formation and surface roughness as well during turning of Steel 30CrNiMo8. Three components of cutting forces were used as inputs together with cutting speed, feed rate, and depth of cut. It is crucial for the engineers to use optimal machining parameters to get the best results or to high control of the machining process. Therefore, there is need to find the machining parameters for the optimal procedure of the machining process. Adaptive neuro-fuzzy inference system (ANFIS) was used to estimate the inputs influence on the chip shape formation and surface roughness. According to the results, the cutting force in direction of the depth of cut has the highest influence on the chip form. The testing error for the cutting force in direction of the depth of cut has testing error 0.2562. This cutting force determines the depth of cut. According to the results, the depth of cut has the highest influence on the surface roughness. Also the depth of cut has the highest influence on the surface roughness. The testing error for the cutting force in direction of the depth of cut has testing error 5.2753. Generally the depth of cut and the cutting force which provides the depth of cut are the most dominant factors for chip forms and surface roughness. Any small changes in depth of cut or in cutting force which provide the depth of cut could drastically affect the chip form or surface roughness of the working material.

Machine-learned and codified synthesis parameters of oxide materials

NASA Astrophysics Data System (ADS)

Kim, Edward; Huang, Kevin; Tomala, Alex; Matthews, Sara; Strubell, Emma; Saunders, Adam; McCallum, Andrew; Olivetti, Elsa

2017-09-01

Predictive materials design has rapidly accelerated in recent years with the advent of large-scale resources, such as materials structure and property databases generated by ab initio computations. In the absence of analogous ab initio frameworks for materials synthesis, high-throughput and machine learning techniques have recently been harnessed to generate synthesis strategies for select materials of interest. Still, a community-accessible, autonomously-compiled synthesis planning resource which spans across materials systems has not yet been developed. In this work, we present a collection of aggregated synthesis parameters computed using the text contained within over 640,000 journal articles using state-of-the-art natural language processing and machine learning techniques. We provide a dataset of synthesis parameters, compiled autonomously across 30 different oxide systems, in a format optimized for planning novel syntheses of materials.

The design and improvement of radial tire molding machine

NASA Astrophysics Data System (ADS)

Wang, Wenhao; Zhang, Tao

2018-04-01

This paper presented that the high accuracy semisteel meridian tire molding machine structure configurations, combining tyre high precision characteristics, the original structure and parameter optimization, technology improvement innovation design period of opening and closing machine rotary shaping drum institutions. This way out of the shaft from the structure to the push-pull type movable shaping drum of thinking limit, compared with the specifications and shaping drum can smaller contraction, is conducive to forming the tire and reduce the tire deformation.

Multi-Response Parameter Interval Sensitivity and Optimization for the Composite Tape Winding Process.

PubMed

Deng, Bo; Shi, Yaoyao; Yu, Tao; Kang, Chao; Zhao, Pan

2018-01-31

The composite tape winding process, which utilizes a tape winding machine and prepreg tapes, provides a promising way to improve the quality of composite products. Nevertheless, the process parameters of composite tape winding have crucial effects on the tensile strength and void content, which are closely related to the performances of the winding products. In this article, two different object values of winding products, including mechanical performance (tensile strength) and a physical property (void content), were respectively calculated. Thereafter, the paper presents an integrated methodology by combining multi-parameter relative sensitivity analysis and single-parameter sensitivity analysis to obtain the optimal intervals of the composite tape winding process. First, the global multi-parameter sensitivity analysis method was applied to investigate the sensitivity of each parameter in the tape winding processing. Then, the local single-parameter sensitivity analysis method was employed to calculate the sensitivity of a single parameter within the corresponding range. Finally, the stability and instability ranges of each parameter were distinguished. Meanwhile, the authors optimized the process parameter ranges and provided comprehensive optimized intervals of the winding parameters. The verification test validated that the optimized intervals of the process parameters were reliable and stable for winding products manufacturing.

Multi-Response Parameter Interval Sensitivity and Optimization for the Composite Tape Winding Process

PubMed Central

Yu, Tao; Kang, Chao; Zhao, Pan

2018-01-01

The composite tape winding process, which utilizes a tape winding machine and prepreg tapes, provides a promising way to improve the quality of composite products. Nevertheless, the process parameters of composite tape winding have crucial effects on the tensile strength and void content, which are closely related to the performances of the winding products. In this article, two different object values of winding products, including mechanical performance (tensile strength) and a physical property (void content), were respectively calculated. Thereafter, the paper presents an integrated methodology by combining multi-parameter relative sensitivity analysis and single-parameter sensitivity analysis to obtain the optimal intervals of the composite tape winding process. First, the global multi-parameter sensitivity analysis method was applied to investigate the sensitivity of each parameter in the tape winding processing. Then, the local single-parameter sensitivity analysis method was employed to calculate the sensitivity of a single parameter within the corresponding range. Finally, the stability and instability ranges of each parameter were distinguished. Meanwhile, the authors optimized the process parameter ranges and provided comprehensive optimized intervals of the winding parameters. The verification test validated that the optimized intervals of the process parameters were reliable and stable for winding products manufacturing. PMID:29385048

Power line identification of millimeter wave radar based on PCA-GS-SVM

NASA Astrophysics Data System (ADS)

Fang, Fang; Zhang, Guifeng; Cheng, Yansheng

2017-12-01

Aiming at the problem that the existing detection method can not effectively solve the security of UAV's ultra low altitude flight caused by power line, a power line recognition method based on grid search (GS) and the principal component analysis and support vector machine (PCA-SVM) is proposed. Firstly, the candidate line of Hough transform is reduced by PCA, and the main feature of candidate line is extracted. Then, upport vector machine (SVM is) optimized by grid search method (GS). Finally, using support vector machine classifier optimized parameters to classify the candidate line. MATLAB simulation results show that this method can effectively identify the power line and noise, and has high recognition accuracy and algorithm efficiency.

Machinability of Green Powder Metallurgy Components: Part I. Characterization of the Influence of Tool Wear

NASA Astrophysics Data System (ADS)

Robert-Perron, Etienne; Blais, Carl; Pelletier, Sylvain; Thomas, Yannig

2007-06-01

The green machining process is an interesting approach for solving the mediocre machining behavior of high-performance powder metallurgy (PM) steels. This process appears as a promising method for extending tool life and reducing machining costs. Recent improvements in binder/lubricant technologies have led to high green strength systems that enable green machining. So far, tool wear has been considered negligible when characterizing the machinability of green PM specimens. This inaccurate assumption may lead to the selection of suboptimum cutting conditions. The first part of this study involves the optimization of the machining parameters to minimize the effects of tool wear on the machinability in turning of green PM components. The second part of our work compares the sintered mechanical properties of components machined in green state with other machined after sintering.

Optimization of Milling Parameters Employing Desirability Functions

NASA Astrophysics Data System (ADS)

Ribeiro, J. L. S.; Rubio, J. C. Campos; Abrão, A. M.

2011-01-01

The principal aim of this paper is to investigate the influence of tool material (one cermet and two coated carbide grades), cutting speed and feed rate on the machinability of hardened AISI H13 hot work steel, in order to identify the cutting conditions which lead to optimal performance. A multiple response optimization procedure based on tool life, surface roughness, milling forces and the machining time (required to produce a sample cavity) was employed. The results indicated that the TiCN-TiN coated carbide and cermet presented similar results concerning the global optimum values for cutting speed and feed rate per tooth, outperforming the TiN-TiCN-Al2O3 coated carbide tool.

Real-time parameter optimization based on neural network for smart injection molding

NASA Astrophysics Data System (ADS)

Lee, H.; Liau, Y.; Ryu, K.

2018-03-01

The manufacturing industry has been facing several challenges, including sustainability, performance and quality of production. Manufacturers attempt to enhance the competitiveness of companies by implementing CPS (Cyber-Physical Systems) through the convergence of IoT(Internet of Things) and ICT(Information & Communication Technology) in the manufacturing process level. Injection molding process has a short cycle time and high productivity. This features have been making it suitable for mass production. In addition, this process is used to produce precise parts in various industry fields such as automobiles, optics and medical devices. Injection molding process has a mixture of discrete and continuous variables. In order to optimized the quality, variables that is generated in the injection molding process must be considered. Furthermore, Optimal parameter setting is time-consuming work to predict the optimum quality of the product. Since the process parameter cannot be easily corrected during the process execution. In this research, we propose a neural network based real-time process parameter optimization methodology that sets optimal process parameters by using mold data, molding machine data, and response data. This paper is expected to have academic contribution as a novel study of parameter optimization during production compare with pre - production parameter optimization in typical studies.

Analysis of static and dynamic characteristic of spindle system and its structure optimization in camshaft grinding machine

NASA Astrophysics Data System (ADS)

Feng, Jianjun; Li, Chengzhe; Wu, Zhi

2017-08-01

As an important part of the valve opening and closing controller in engine, camshaft has high machining accuracy requirement in designing. Taking the high-speed camshaft grinder spindle system as the research object and the spindle system performance as the optimizing target, this paper firstly uses Solidworks to establish the three-dimensional finite element model (FEM) of spindle system, then conducts static analysis and the modal analysis by applying the established FEM in ANSYS Workbench, and finally uses the design optimization function of the ANSYS Workbench to optimize the structure parameter in the spindle system. The study results prove that the design of the spindle system fully meets the production requirements, and the performance of the optimized spindle system is promoted. Besides, this paper provides an analysis and optimization method for other grinder spindle systems.

Aircraft Engine Thrust Estimator Design Based on GSA-LSSVM

NASA Astrophysics Data System (ADS)

Sheng, Hanlin; Zhang, Tianhong

2017-08-01

In view of the necessity of highly precise and reliable thrust estimator to achieve direct thrust control of aircraft engine, based on support vector regression (SVR), as well as least square support vector machine (LSSVM) and a new optimization algorithm - gravitational search algorithm (GSA), by performing integrated modelling and parameter optimization, a GSA-LSSVM-based thrust estimator design solution is proposed. The results show that compared to particle swarm optimization (PSO) algorithm, GSA can find unknown optimization parameter better and enables the model developed with better prediction and generalization ability. The model can better predict aircraft engine thrust and thus fulfills the need of direct thrust control of aircraft engine.

Study on Performance of Integration Control by Man and Machine in Stage of Final Approaching for Spaceship Rendezvous and Docking

NASA Astrophysics Data System (ADS)

Zhou, Qianxiang; Liu, Zhongqi

With the development of manned space technology, space rendezvous and docking (RVD) technology will play a more and more important role. The astronauts’ participation in a final close period of man-machine combination control is an important way of RVD technology. Spacecraft RVD control involves control problem of a total of 12 degrees of freedom (location) and attitude which it relative to the inertial space the orbit. Therefore, in order to reduce the astronauts’ operation load and reduce the security requirements to the ground station and achieve an optimal performance of the whole man-machine system, it is need to study how to design the number of control parameters of astronaut or aircraft automatic control system. In this study, with the laboratory conditions on the ground, a method was put forward to develop an experimental system in which the performance evaluation of spaceship RVD integration control by man and machine could be completed. After the RVD precision requirements were determined, 26 male volunteers aged 20-40 took part in the performance evaluation experiments. The RVD integration control success rates and total thruster ignition time were chosen as evaluation indices. Results show that if less than three RVD parameters control tasks were finished by subject and the rest of parameters control task completed by automation, the RVD success rate would be larger than eighty-eight percent and the fuel consumption would be optimized. In addition, there were two subjects who finished the whole six RVD parameters control tasks by enough train. In conclusion, if the astronauts' role should be integrated into the RVD control, it was suitable for them to finish the heading, pitch and roll control in order to assure the man-machine system high performance. If astronauts were needed to finish all parameter control, two points should be taken into consideration, one was enough fuel and another was enough long operation time.

Analyzing the effect of cutting parameters on surface roughness and tool wear when machining nickel based hastelloy - 276

NASA Astrophysics Data System (ADS)

Khidhir, Basim A.; Mohamed, Bashir

2011-02-01

Machining parameters has an important factor on tool wear and surface finish, for that the manufacturers need to obtain optimal operating parameters with a minimum set of experiments as well as minimizing the simulations in order to reduce machining set up costs. The cutting speed is one of the most important cutting parameter to evaluate, it clearly most influences on one hand, tool life, tool stability, and cutting process quality, and on the other hand controls production flow. Due to more demanding manufacturing systems, the requirements for reliable technological information have increased. For a reliable analysis in cutting, the cutting zone (tip insert-workpiece-chip system) as the mechanics of cutting in this area are very complicated, the chip is formed in the shear plane (entrance the shear zone) and is shape in the sliding plane. The temperature contributed in the primary shear, chamfer and sticking, sliding zones are expressed as a function of unknown shear angle on the rake face and temperature modified flow stress in each zone. The experiments were carried out on a CNC lathe and surface finish and tool tip wear are measured in process. Machining experiments are conducted. Reasonable agreement is observed under turning with high depth of cut. Results of this research help to guide the design of new cutting tool materials and the studies on evaluation of machining parameters to further advance the productivity of nickel based alloy Hastelloy - 276 machining.

Applying machine learning to identify autistic adults using imitation: An exploratory study.

PubMed

Li, Baihua; Sharma, Arjun; Meng, James; Purushwalkam, Senthil; Gowen, Emma

2017-01-01

Autism spectrum condition (ASC) is primarily diagnosed by behavioural symptoms including social, sensory and motor aspects. Although stereotyped, repetitive motor movements are considered during diagnosis, quantitative measures that identify kinematic characteristics in the movement patterns of autistic individuals are poorly studied, preventing advances in understanding the aetiology of motor impairment, or whether a wider range of motor characteristics could be used for diagnosis. The aim of this study was to investigate whether data-driven machine learning based methods could be used to address some fundamental problems with regard to identifying discriminative test conditions and kinematic parameters to classify between ASC and neurotypical controls. Data was based on a previous task where 16 ASC participants and 14 age, IQ matched controls observed then imitated a series of hand movements. 40 kinematic parameters extracted from eight imitation conditions were analysed using machine learning based methods. Two optimal imitation conditions and nine most significant kinematic parameters were identified and compared with some standard attribute evaluators. To our knowledge, this is the first attempt to apply machine learning to kinematic movement parameters measured during imitation of hand movements to investigate the identification of ASC. Although based on a small sample, the work demonstrates the feasibility of applying machine learning methods to analyse high-dimensional data and suggest the potential of machine learning for identifying kinematic biomarkers that could contribute to the diagnostic classification of autism.

Cost minimizing of cutting process for CNC thermal and water-jet machines

NASA Astrophysics Data System (ADS)

Tavaeva, Anastasia; Kurennov, Dmitry

2015-11-01

This paper deals with optimization problem of cutting process for CNC thermal and water-jet machines. The accuracy of objective function parameters calculation for optimization problem is investigated. This paper shows that working tool path speed is not constant value. One depends on some parameters that are described in this paper. The relations of working tool path speed depending on the numbers of NC programs frames, length of straight cut, configuration part are presented. Based on received results the correction coefficients for working tool speed are defined. Additionally the optimization problem may be solved by using mathematical model. Model takes into account the additional restrictions of thermal cutting (choice of piercing and output tool point, precedence condition, thermal deformations). At the second part of paper the non-standard cutting techniques are considered. Ones may lead to minimizing of cutting cost and time compared with standard cutting techniques. This paper considers the effectiveness of non-standard cutting techniques application. At the end of the paper the future research works are indicated.

[Determination of process variable pH in solid-state fermentation by FT-NIR spectroscopy and extreme learning machine (ELM)].

PubMed

Liu, Guo-hai; Jiang, Hui; Xiao, Xia-hong; Zhang, Dong-juan; Mei, Cong-li; Ding, Yu-han

2012-04-01

Fourier transform near-infrared (FT-NIR) spectroscopy was attempted to determine pH, which is one of the key process parameters in solid-state fermentation of crop straws. First, near infrared spectra of 140 solid-state fermented product samples were obtained by near infrared spectroscopy system in the wavelength range of 10 000-4 000 cm(-1), and then the reference measurement results of pH were achieved by pH meter. Thereafter, the extreme learning machine (ELM) was employed to calibrate model. In the calibration model, the optimal number of PCs and the optimal number of hidden-layer nodes of ELM network were determined by the cross-validation. Experimental results showed that the optimal ELM model was achieved with 1040-1 topology construction as follows: R(p) = 0.961 8 and RMSEP = 0.104 4 in the prediction set. The research achievement could provide technological basis for the on-line measurement of the process parameters in solid-state fermentation.

Optimization of injection molding process parameters for a plastic cell phone housing component

NASA Astrophysics Data System (ADS)

Rajalingam, Sokkalingam; Vasant, Pandian; Khe, Cheng Seong; Merican, Zulkifli; Oo, Zeya

2016-11-01

To produce thin-walled plastic items, injection molding process is one of the most widely used application tools. However, to set optimal process parameters is difficult as it may cause to produce faulty items on injected mold like shrinkage. This study aims at to determine such an optimum injection molding process parameters which can reduce the fault of shrinkage on a plastic cell phone cover items. Currently used setting of machines process produced shrinkage and mis-specified length and with dimensions below the limit. Thus, for identification of optimum process parameters, maintaining closer targeted length and width setting magnitudes with minimal variations, more experiments are needed. The mold temperature, injection pressure and screw rotation speed are used as process parameters in this research. For optimal molding process parameters the Response Surface Methods (RSM) is applied. The major contributing factors influencing the responses were identified from analysis of variance (ANOVA) technique. Through verification runs it was found that the shrinkage defect can be minimized with the optimal setting found by RSM.

A new technique for rapid assessment of eutrophication status of coastal waters using a support vector machine

NASA Astrophysics Data System (ADS)

Kong, Xianyu; Che, Xiaowei; Su, Rongguo; Zhang, Chuansong; Yao, Qingzhen; Shi, Xiaoyong

2017-05-01

There is an urgent need to develop efficient evaluation tools that use easily measured variables to make rapid and timely eutrophication assessments, which are important for marine health management, and to implement eutrophication monitoring programs. In this study, an approach for rapidly assessing the eutrophication status of coastal waters with three easily measured parameters (turbidity, chlorophyll a and dissolved oxygen) was developed by the grid search (GS) optimized support vector machine (SVM), with trophic index TRIX classification results as the reference. With the optimized penalty parameter C =64 and the kernel parameter γ =1, the classification accuracy rates reached 89.3% for the training data, 88.3% for the cross-validation, and 88.5% for the validation dataset. Because the developed approach only used three easy-to-measure variables, its application could facilitate the rapid assessment of the eutrophication status of coastal waters, resulting in potential cost savings in marine monitoring programs and assisting in the provision of timely advice for marine management.

Study on the Optimization and Process Modeling of the Rotary Ultrasonic Machining of Zerodur Glass-Ceramic

NASA Astrophysics Data System (ADS)

Pitts, James Daniel

Rotary ultrasonic machining (RUM), a hybrid process combining ultrasonic machining and diamond grinding, was created to increase material removal rates for the fabrication of hard and brittle workpieces. The objective of this research was to experimentally derive empirical equations for the prediction of multiple machined surface roughness parameters for helically pocketed rotary ultrasonic machined Zerodur glass-ceramic workpieces by means of a systematic statistical experimental approach. A Taguchi parametric screening design of experiments was employed to systematically determine the RUM process parameters with the largest effect on mean surface roughness. Next empirically determined equations for the seven common surface quality metrics were developed via Box-Behnken surface response experimental trials. Validation trials were conducted resulting in predicted and experimental surface roughness in varying levels of agreement. The reductions in cutting force and tool wear associated with RUM, reported by previous researchers, was experimentally verified to also extended to helical pocketing of Zerodur glass-ceramic.

Developing Lathing Parameters for PBX 9501

DOE Office of Scientific and Technical Information (OSTI.GOV)

Woodrum, Randall Brock

This thesis presents the work performed on lathing PBX 9501 to gather and analyze cutting force and temperature data during the machining process. This data will be used to decrease federal-regulation-constrained machining time of the high explosive PBX 9501. The effects of machining parameters depth of cut, surface feet per minute, and inches per revolution on cutting force and cutting interface were evaluated. Cutting tools of tip radius 0.005 -inches and 0.05 -inches were tested to determine what effect the tool shape had on the machining process as well. A consistently repeatable relationship of temperature to changing depth of cutmore » and surface feet per minute is found, while only a weak dependence was found to changing inches per revolution. Results also show the relation of cutting force to depth of cut and inches per revolution, while weak dependence on SFM is found. Conclusions suggest rapid, shallow cuts optimize machining time for a billet of PBX 9501, while minimizing temperature increase and cutting force.« less

Additive Manufacturing in Production: A Study Case Applying Technical Requirements

NASA Astrophysics Data System (ADS)

Ituarte, Iñigo Flores; Coatanea, Eric; Salmi, Mika; Tuomi, Jukka; Partanen, Jouni

Additive manufacturing (AM) is expanding the manufacturing capabilities. However, quality of AM produced parts is dependent on a number of machine, geometry and process parameters. The variability of these parameters affects the manufacturing drastically and therefore standardized processes and harmonized methodologies need to be developed to characterize the technology for end use applications and enable the technology for manufacturing. This research proposes a composite methodology integrating Taguchi Design of Experiments, multi-objective optimization and statistical process control, to optimize the manufacturing process and fulfil multiple requirements imposed to an arbitrary geometry. The proposed methodology aims to characterize AM technology depending upon manufacturing process variables as well as to perform a comparative assessment of three AM technologies (Selective Laser Sintering, Laser Stereolithography and Polyjet). Results indicate that only one machine, laser-based Stereolithography, was feasible to fulfil simultaneously macro and micro level geometrical requirements but mechanical properties were not at required level. Future research will study a single AM system at the time to characterize AM machine technical capabilities and stimulate pre-normative initiatives of the technology for end use applications.

Parameter estimation using meta-heuristics in systems biology: a comprehensive review.

PubMed

Sun, Jianyong; Garibaldi, Jonathan M; Hodgman, Charlie

2012-01-01

This paper gives a comprehensive review of the application of meta-heuristics to optimization problems in systems biology, mainly focussing on the parameter estimation problem (also called the inverse problem or model calibration). It is intended for either the system biologist who wishes to learn more about the various optimization techniques available and/or the meta-heuristic optimizer who is interested in applying such techniques to problems in systems biology. First, the parameter estimation problems emerging from different areas of systems biology are described from the point of view of machine learning. Brief descriptions of various meta-heuristics developed for these problems follow, along with outlines of their advantages and disadvantages. Several important issues in applying meta-heuristics to the systems biology modelling problem are addressed, including the reliability and identifiability of model parameters, optimal design of experiments, and so on. Finally, we highlight some possible future research directions in this field.

Results of Investigative Tests of Gas Turbine Engine Compressor Blades Obtained by Electrochemical Machining

NASA Astrophysics Data System (ADS)

Kozhina, T. D.; Kurochkin, A. V.

2016-04-01

The paper highlights results of the investigative tests of GTE compressor Ti-alloy blades obtained by the method of electrochemical machining with oscillating tool-electrodes, carried out in order to define the optimal parameters of the ECM process providing attainment of specified blade quality parameters given in the design documentation, while providing maximal performance. The new technological methods suggested based on the results of the tests; in particular application of vibrating tool-electrodes and employment of locating elements made of high-strength materials, significantly extend the capabilities of this method.

Customer demand prediction of service-oriented manufacturing using the least square support vector machine optimized by particle swarm optimization algorithm

NASA Astrophysics Data System (ADS)

Cao, Jin; Jiang, Zhibin; Wang, Kangzhou

2017-07-01

Many nonlinear customer satisfaction-related factors significantly influence the future customer demand for service-oriented manufacturing (SOM). To address this issue and enhance the prediction accuracy, this article develops a novel customer demand prediction approach for SOM. The approach combines the phase space reconstruction (PSR) technique with the optimized least square support vector machine (LSSVM). First, the prediction sample space is reconstructed by the PSR to enrich the time-series dynamics of the limited data sample. Then, the generalization and learning ability of the LSSVM are improved by the hybrid polynomial and radial basis function kernel. Finally, the key parameters of the LSSVM are optimized by the particle swarm optimization algorithm. In a real case study, the customer demand prediction of an air conditioner compressor is implemented. Furthermore, the effectiveness and validity of the proposed approach are demonstrated by comparison with other classical predication approaches.

[A prediction model for the activity of insecticidal crystal proteins from Bacillus thuringiensis based on support vector machine].

PubMed

Lin, Yi; Cai, Fu-Ying; Zhang, Guang-Ya

2007-01-01

A quantitative structure-property relationship (QSPR) model in terms of amino acid composition and the activity of Bacillus thuringiensis insecticidal crystal proteins was established. Support vector machine (SVM) is a novel general machine-learning tool based on the structural risk minimization principle that exhibits good generalization when fault samples are few; it is especially suitable for classification, forecasting, and estimation in cases where small amounts of samples are involved such as fault diagnosis; however, some parameters of SVM are selected based on the experience of the operator, which has led to decreased efficiency of SVM in practical application. The uniform design (UD) method was applied to optimize the running parameters of SVM. It was found that the average accuracy rate approached 73% when the penalty factor was 0.01, the epsilon 0.2, the gamma 0.05, and the range 0.5. The results indicated that UD might be used an effective method to optimize the parameters of SVM and SVM and could be used as an alternative powerful modeling tool for QSPR studies of the activity of Bacillus thuringiensis (Bt) insecticidal crystal proteins. Therefore, a novel method for predicting the insecticidal activity of Bt insecticidal crystal proteins was proposed by the authors of this study.

A Genetic Algorithm Based Support Vector Machine Model for Blood-Brain Barrier Penetration Prediction

PubMed Central

Zhang, Daqing; Xiao, Jianfeng; Zhou, Nannan; Luo, Xiaomin; Jiang, Hualiang; Chen, Kaixian

2015-01-01

Blood-brain barrier (BBB) is a highly complex physical barrier determining what substances are allowed to enter the brain. Support vector machine (SVM) is a kernel-based machine learning method that is widely used in QSAR study. For a successful SVM model, the kernel parameters for SVM and feature subset selection are the most important factors affecting prediction accuracy. In most studies, they are treated as two independent problems, but it has been proven that they could affect each other. We designed and implemented genetic algorithm (GA) to optimize kernel parameters and feature subset selection for SVM regression and applied it to the BBB penetration prediction. The results show that our GA/SVM model is more accurate than other currently available log BB models. Therefore, to optimize both SVM parameters and feature subset simultaneously with genetic algorithm is a better approach than other methods that treat the two problems separately. Analysis of our log BB model suggests that carboxylic acid group, polar surface area (PSA)/hydrogen-bonding ability, lipophilicity, and molecular charge play important role in BBB penetration. Among those properties relevant to BBB penetration, lipophilicity could enhance the BBB penetration while all the others are negatively correlated with BBB penetration. PMID:26504797

Nondimensional parameter for conformal grinding: combining machine and process parameters

NASA Astrophysics Data System (ADS)

Funkenbusch, Paul D.; Takahashi, Toshio; Gracewski, Sheryl M.; Ruckman, Jeffrey L.

1999-11-01

Conformal grinding of optical materials with CNC (Computer Numerical Control) machining equipment can be used to achieve precise control over complex part configurations. However complications can arise due to the need to fabricate complex geometrical shapes at reasonable production rates. For example high machine stiffness is essential, but the need to grind 'inside' small or highly concave surfaces may require use of tooling with less than ideal stiffness characteristics. If grinding generates loads sufficient for significant tool deflection, the programmed removal depth will not be achieved. Moreover since grinding load is a function of the volumetric removal rate the amount of load deflection can vary with location on the part, potentially producing complex figure errors. In addition to machine/tool stiffness and removal rate, load generation is a function of the process parameters. For example by reducing the feed rate of the tool into the part, both the load and resultant deflection/removal error can be decreased. However this must be balanced against the need for part through put. In this paper a simple model which permits combination of machine stiffness and process parameters into a single non-dimensional parameter is adapted for a conformal grinding geometry. Errors in removal can be minimized by maintaining this parameter above a critical value. Moreover, since the value of this parameter depends on the local part geometry, it can be used to optimize process settings during grinding. For example it may be used to guide adjustment of the feed rate as a function of location on the part to eliminate figure errors while minimizing the total grinding time required.

Gradient Evolution-based Support Vector Machine Algorithm for Classification

NASA Astrophysics Data System (ADS)

Zulvia, Ferani E.; Kuo, R. J.

2018-03-01

This paper proposes a classification algorithm based on a support vector machine (SVM) and gradient evolution (GE) algorithms. SVM algorithm has been widely used in classification. However, its result is significantly influenced by the parameters. Therefore, this paper aims to propose an improvement of SVM algorithm which can find the best SVMs’ parameters automatically. The proposed algorithm employs a GE algorithm to automatically determine the SVMs’ parameters. The GE algorithm takes a role as a global optimizer in finding the best parameter which will be used by SVM algorithm. The proposed GE-SVM algorithm is verified using some benchmark datasets and compared with other metaheuristic-based SVM algorithms. The experimental results show that the proposed GE-SVM algorithm obtains better results than other algorithms tested in this paper.

Study of hole characteristics in Laser Trepan Drilling of ZTA

NASA Astrophysics Data System (ADS)

Saini, Surendra K.; Dubey, Avanish K.; Upadhyay, B. N.; Choubey, A.

2018-07-01

Zirconia Toughened Alumina ceramic is widely used for aerospace components, combustion chambers, heat exchangers, bearings and pumps mainly due to its improved mechanical and thermal properties. To make holes in thick section Zirconia Toughened Alumina ceramics is a major challenge due to its unfavorable machining characteristics. Recent researches have explored that laser machining can overcome the machining limitations of advanced materials having improved mechanical properties. In present research, authors have analyzed the effect of Laser Trepan Drilling on hole characteristics of 6.0 mm thick Zirconia Toughened Alumina. Effect of significant process parameters on hole characteristics such as hole circularity at top and bottom, hole taper, and spatter size have been studied. The optimum ranges of these parameters have been suggested on the basis of empirical modeling and optimization.

Predicting distant failure in early stage NSCLC treated with SBRT using clinical parameters.

PubMed

Zhou, Zhiguo; Folkert, Michael; Cannon, Nathan; Iyengar, Puneeth; Westover, Kenneth; Zhang, Yuanyuan; Choy, Hak; Timmerman, Robert; Yan, Jingsheng; Xie, Xian-J; Jiang, Steve; Wang, Jing

2016-06-01

The aim of this study is to predict early distant failure in early stage non-small cell lung cancer (NSCLC) treated with stereotactic body radiation therapy (SBRT) using clinical parameters by machine learning algorithms. The dataset used in this work includes 81 early stage NSCLC patients with at least 6months of follow-up who underwent SBRT between 2006 and 2012 at a single institution. The clinical parameters (n=18) for each patient include demographic parameters, tumor characteristics, treatment fraction schemes, and pretreatment medications. Three predictive models were constructed based on different machine learning algorithms: (1) artificial neural network (ANN), (2) logistic regression (LR) and (3) support vector machine (SVM). Furthermore, to select an optimal clinical parameter set for the model construction, three strategies were adopted: (1) clonal selection algorithm (CSA) based selection strategy; (2) sequential forward selection (SFS) method; and (3) statistical analysis (SA) based strategy. 5-cross-validation is used to validate the performance of each predictive model. The accuracy was assessed by area under the receiver operating characteristic (ROC) curve (AUC), sensitivity and specificity of the system was also evaluated. The AUCs for ANN, LR and SVM were 0.75, 0.73, and 0.80, respectively. The sensitivity values for ANN, LR and SVM were 71.2%, 72.9% and 83.1%, while the specificity values for ANN, LR and SVM were 59.1%, 63.6% and 63.6%, respectively. Meanwhile, the CSA based strategy outperformed SFS and SA in terms of AUC, sensitivity and specificity. Based on clinical parameters, the SVM with the CSA optimal parameter set selection strategy achieves better performance than other strategies for predicting distant failure in lung SBRT patients. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

An interval programming model for continuous improvement in micro-manufacturing

NASA Astrophysics Data System (ADS)

Ouyang, Linhan; Ma, Yizhong; Wang, Jianjun; Tu, Yiliu; Byun, Jai-Hyun

2018-03-01

Continuous quality improvement in micro-manufacturing processes relies on optimization strategies that relate an output performance to a set of machining parameters. However, when determining the optimal machining parameters in a micro-manufacturing process, the economics of continuous quality improvement and decision makers' preference information are typically neglected. This article proposes an economic continuous improvement strategy based on an interval programming model. The proposed strategy differs from previous studies in two ways. First, an interval programming model is proposed to measure the quality level, where decision makers' preference information is considered in order to determine the weight of location and dispersion effects. Second, the proposed strategy is a more flexible approach since it considers the trade-off between the quality level and the associated costs, and leaves engineers a larger decision space through adjusting the quality level. The proposed strategy is compared with its conventional counterparts using an Nd:YLF laser beam micro-drilling process.

Effective 2D-3D medical image registration using Support Vector Machine.

PubMed

Qi, Wenyuan; Gu, Lixu; Zhao, Qiang

2008-01-01

Registration of pre-operative 3D volume dataset and intra-operative 2D images gradually becomes an important technique to assist radiologists in diagnosing complicated diseases easily and quickly. In this paper, we proposed a novel 2D/3D registration framework based on Support Vector Machine (SVM) to compensate the disadvantages of generating large number of DRR images in the stage of intra-operation. Estimated similarity metric distribution could be built up from the relationship between parameters of transform and prior sparse target metric values by means of SVR method. Based on which, global optimal parameters of transform are finally searched out by an optimizer in order to guide 3D volume dataset to match intra-operative 2D image. Experiments reveal that our proposed registration method improved performance compared to conventional registration method and also provided a precise registration result efficiently.

Influence of the initial surface texture on the resulting surface roughness and waviness for micro-machining with ultra-short laser pulses (Conference Presentation)

NASA Astrophysics Data System (ADS)

Remund, Stefan M.; Jaeggi, Beat; Kramer, Thorsten; Neuenschwander, Beat

2017-03-01

The resulting surface roughness and waviness after processing with ultra-short pulsed laser radiation depend on the laser parameters as well as on the machining strategy and the scanning system. However the results depend on the material and its initial surface quality and finishing as well. The improvement of surface finishing represents effort and produces additional costs. For industrial applications it is important to reduce the preparation of a workpiece for laser micro-machining to optimize quality and reduce costs. The effects of the ablation process and the influence of the machining strategy and scanning system onto the surface roughness and waviness can be differenced due to their separate manner. By using the optimal laser parameters on an initially perfect surface, the ablation process mainly increases the roughness to a certain value for most metallic materials. However, imperfections in the scanning system causing a slight variation in the scanning speed lead to a raise of the waviness on the sample surface. For a basic understanding of the influence of grinding marks, the sample surfaces were initially furnished with regular grooves of different depths and spatial frequencies to gain a homogenous and well-defined original surface. On these surfaces the effect of different beam waists and machining strategy are investigated and the results are compared with a simulation of the process. Furthermore the behaviors of common surface finishes used in industrial applications for laser micro-machining are studied and the relation onto the resulting surface roughness and waviness is presented.

Effect of High-speed Milling tool path strategies on the surface roughness of Stavax ESR mold insert machining

NASA Astrophysics Data System (ADS)

Mebrahitom, A.; Rizuan, D.; Azmir, M.; Nassif, M.

2016-02-01

High speed milling is one of the recent technologies used to produce mould inserts due to the need for high surface finish. It is a faster machining process where it uses a small side step and a small down step combined with very high spindle speed and feed rate. In order to effectively use the HSM capabilities, optimizing the tool path strategies and machining parameters is an important issue. In this paper, six different tool path strategies have been investigated on the surface finish and machining time of a rectangular cavities of ESR Stavax material. CAD/CAM application of CATIA V5 machining module for pocket milling of the cavities was used for process planning.

Back analysis of geomechanical parameters in underground engineering using artificial bee colony.

PubMed

Zhu, Changxing; Zhao, Hongbo; Zhao, Ming

2014-01-01

Accurate geomechanical parameters are critical in tunneling excavation, design, and supporting. In this paper, a displacements back analysis based on artificial bee colony (ABC) algorithm is proposed to identify geomechanical parameters from monitored displacements. ABC was used as global optimal algorithm to search the unknown geomechanical parameters for the problem with analytical solution. To the problem without analytical solution, optimal back analysis is time-consuming, and least square support vector machine (LSSVM) was used to build the relationship between unknown geomechanical parameters and displacement and improve the efficiency of back analysis. The proposed method was applied to a tunnel with analytical solution and a tunnel without analytical solution. The results show the proposed method is feasible.

Review on CNC-Rapid Prototyping

NASA Astrophysics Data System (ADS)

Z, M. Nafis O.; Y, Nafrizuan M.; A, Munira M.; J, Kartina

2012-09-01

This article reviewed developments of Computerized Numerical Control (CNC) technology in rapid prototyping process. Rapid prototyping (RP) can be classified into three major groups; subtractive, additive and virtual. CNC rapid prototyping is grouped under the subtractive category which involves material removal from the workpiece that is larger than the final part. Richard Wysk established the use of CNC machines for rapid prototyping using sets of 2½-D tool paths from various orientations about a rotary axis to machine parts without refixturing. Since then, there are few developments on this process mainly aimed to optimized the operation and increase the process capabilities to stand equal with common additive type of RP. These developments include the integration between machining and deposition process (hybrid RP), adoption of RP to the conventional machine and optimization of the CNC rapid prototyping process based on controlled parameters. The article ended by concluding that the CNC rapid prototyping research area has a vast space for improvement as in the conventional machining processes. Further developments and findings will enhance the usage of this method and minimize the limitation of current approach in building a prototype.

Multi objective optimization model for minimizing production cost and environmental impact in CNC turning process

NASA Astrophysics Data System (ADS)

Widhiarso, Wahyu; Rosyidi, Cucuk Nur

2018-02-01

Minimizing production cost in a manufacturing company will increase the profit of the company. The cutting parameters will affect total processing time which then will affect the production cost of machining process. Besides affecting the production cost and processing time, the cutting parameters will also affect the environment. An optimization model is needed to determine the optimum cutting parameters. In this paper, we develop an optimization model to minimize the production cost and the environmental impact in CNC turning process. The model is used a multi objective optimization. Cutting speed and feed rate are served as the decision variables. Constraints considered are cutting speed, feed rate, cutting force, output power, and surface roughness. The environmental impact is converted from the environmental burden by using eco-indicator 99. Numerical example is given to show the implementation of the model and solved using OptQuest of Oracle Crystal Ball software. The results of optimization indicate that the model can be used to optimize the cutting parameters to minimize the production cost and the environmental impact.

Exploring the influence of constitutive models and associated parameters for the orthogonal machining of Ti6Al4V

NASA Astrophysics Data System (ADS)

Pervaiz, S.; Anwar, S.; Kannan, S.; Almarfadi, A.

2018-04-01

Ti6Al4V is known as difficult-to-cut material due to its inherent properties such as high hot hardness, low thermal conductivity and high chemical reactivity. Though, Ti6Al4V is utilized by industrial sectors such as aeronautics, energy generation, petrochemical and bio-medical etc. For the metal cutting community, competent and cost-effective machining of Ti6Al4V is a challenging task. To optimize cost and machining performance for the machining of Ti6Al4V, finite element based cutting simulation can be a very useful tool. The aim of this paper is to develop a finite element machining model for the simulation of Ti6Al4V machining process. The study incorporates material constitutive models namely Power Law (PL) and Johnson – Cook (JC) material models to mimic the mechanical behaviour of Ti6Al4V. The study investigates cutting temperatures, cutting forces, stresses, and plastic strains with respect to different PL and JC material models with associated parameters. In addition, the numerical study also integrates different cutting tool rake angles in the machining simulations. The simulated results will be beneficial to draw conclusions for improving the overall machining performance of Ti6Al4V.

A new Bayesian recursive technique for parameter estimation

NASA Astrophysics Data System (ADS)

Kaheil, Yasir H.; Gill, M. Kashif; McKee, Mac; Bastidas, Luis

2006-08-01

The performance of any model depends on how well its associated parameters are estimated. In the current application, a localized Bayesian recursive estimation (LOBARE) approach is devised for parameter estimation. The LOBARE methodology is an extension of the Bayesian recursive estimation (BARE) method. It is applied in this paper on two different types of models: an artificial intelligence (AI) model in the form of a support vector machine (SVM) application for forecasting soil moisture and a conceptual rainfall-runoff (CRR) model represented by the Sacramento soil moisture accounting (SAC-SMA) model. Support vector machines, based on statistical learning theory (SLT), represent the modeling task as a quadratic optimization problem and have already been used in various applications in hydrology. They require estimation of three parameters. SAC-SMA is a very well known model that estimates runoff. It has a 13-dimensional parameter space. In the LOBARE approach presented here, Bayesian inference is used in an iterative fashion to estimate the parameter space that will most likely enclose a best parameter set. This is done by narrowing the sampling space through updating the "parent" bounds based on their fitness. These bounds are actually the parameter sets that were selected by BARE runs on subspaces of the initial parameter space. The new approach results in faster convergence toward the optimal parameter set using minimum training/calibration data and fewer sets of parameter values. The efficacy of the localized methodology is also compared with the previously used BARE algorithm.

Identification of handwriting by using the genetic algorithm (GA) and support vector machine (SVM)

NASA Astrophysics Data System (ADS)

Zhang, Qigui; Deng, Kai

2016-12-01

As portable digital camera and a camera phone comes more and more popular, and equally pressing is meeting the requirements of people to shoot at any time, to identify and storage handwritten character. In this paper, genetic algorithm(GA) and support vector machine(SVM)are used for identification of handwriting. Compare with parameters-optimized method, this technique overcomes two defects: first, it's easy to trap in the local optimum; second, finding the best parameters in the larger range will affects the efficiency of classification and prediction. As the experimental results suggest, GA-SVM has a higher recognition rate.

Multiresponse Optimization of Process Parameters in Turning of GFRP Using TOPSIS Method

PubMed Central

Parida, Arun Kumar; Routara, Bharat Chandra

2014-01-01

Taguchi's design of experiment is utilized to optimize the process parameters in turning operation with dry environment. Three parameters, cutting speed (v), feed (f), and depth of cut (d), with three different levels are taken for the responses like material removal rate (MRR) and surface roughness (R a). The machining is conducted with Taguchi L9 orthogonal array, and based on the S/N analysis, the optimal process parameters for surface roughness and MRR are calculated separately. Considering the larger-the-better approach, optimal process parameters for material removal rate are cutting speed at level 3, feed at level 2, and depth of cut at level 3, that is, v 3-f 2-d 3. Similarly for surface roughness, considering smaller-the-better approach, the optimal process parameters are cutting speed at level 1, feed at level 1, and depth of cut at level 3, that is, v 1-f 1-d 3. Results of the main effects plot indicate that depth of cut is the most influencing parameter for MRR but cutting speed is the most influencing parameter for surface roughness and feed is found to be the least influencing parameter for both the responses. The confirmation test is conducted for both MRR and surface roughness separately. Finally, an attempt has been made to optimize the multiresponses using technique for order preference by similarity to ideal solution (TOPSIS) with Taguchi approach. PMID:27437503

Predictive optimized adaptive PSS in a single machine infinite bus.

PubMed

Milla, Freddy; Duarte-Mermoud, Manuel A

2016-07-01

Power System Stabilizer (PSS) devices are responsible for providing a damping torque component to generators for reducing fluctuations in the system caused by small perturbations. A Predictive Optimized Adaptive PSS (POA-PSS) to improve the oscillations in a Single Machine Infinite Bus (SMIB) power system is discussed in this paper. POA-PSS provides the optimal design parameters for the classic PSS using an optimization predictive algorithm, which adapts to changes in the inputs of the system. This approach is part of small signal stability analysis, which uses equations in an incremental form around an operating point. Simulation studies on the SMIB power system illustrate that the proposed POA-PSS approach has better performance than the classical PSS. In addition, the effort in the control action of the POA-PSS is much less than that of other approaches considered for comparison. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

Toolpath Strategy and Optimum Combination of Machining Parameter during Pocket Mill Process of Plastic Mold Steels Material

NASA Astrophysics Data System (ADS)

Wibowo, Y. T.; Baskoro, S. Y.; Manurung, V. A. T.

2018-02-01

Plastic based products spread all over the world in many aspects of life. The ability to substitute other materials is getting stronger and wider. The use of plastic materials increases and become unavoidable. Plastic based mass production requires injection process as well Mold. The milling process of plastic mold steel material was done using HSS End Mill cutting tool that is widely used in a small and medium enterprise for the reason of its ability to be re sharpened and relatively inexpensive. Study on the effect of the geometry tool states that it has an important effect on the quality improvement. Cutting speed, feed rate, depth of cut and radii are input parameters beside to the tool path strategy. This paper aims to investigate input parameter and cutting tools behaviors within some different tool path strategy. For the reason of experiments efficiency Taguchi method and ANOVA were used. Response studied is surface roughness and cutting behaviors. By achieving the expected quality, no more additional process is required. Finally, the optimal combination of machining parameters will deliver the expected roughness and of course totally reduced cutting time. However actually, SMEs do not optimally use this data for cost reduction.

The construction of support vector machine classifier using the firefly algorithm.

PubMed

Chao, Chih-Feng; Horng, Ming-Huwi

2015-01-01

The setting of parameters in the support vector machines (SVMs) is very important with regard to its accuracy and efficiency. In this paper, we employ the firefly algorithm to train all parameters of the SVM simultaneously, including the penalty parameter, smoothness parameter, and Lagrangian multiplier. The proposed method is called the firefly-based SVM (firefly-SVM). This tool is not considered the feature selection, because the SVM, together with feature selection, is not suitable for the application in a multiclass classification, especially for the one-against-all multiclass SVM. In experiments, binary and multiclass classifications are explored. In the experiments on binary classification, ten of the benchmark data sets of the University of California, Irvine (UCI), machine learning repository are used; additionally the firefly-SVM is applied to the multiclass diagnosis of ultrasonic supraspinatus images. The classification performance of firefly-SVM is also compared to the original LIBSVM method associated with the grid search method and the particle swarm optimization based SVM (PSO-SVM). The experimental results advocate the use of firefly-SVM to classify pattern classifications for maximum accuracy.

The Construction of Support Vector Machine Classifier Using the Firefly Algorithm

PubMed Central

Chao, Chih-Feng; Horng, Ming-Huwi

2015-01-01

The setting of parameters in the support vector machines (SVMs) is very important with regard to its accuracy and efficiency. In this paper, we employ the firefly algorithm to train all parameters of the SVM simultaneously, including the penalty parameter, smoothness parameter, and Lagrangian multiplier. The proposed method is called the firefly-based SVM (firefly-SVM). This tool is not considered the feature selection, because the SVM, together with feature selection, is not suitable for the application in a multiclass classification, especially for the one-against-all multiclass SVM. In experiments, binary and multiclass classifications are explored. In the experiments on binary classification, ten of the benchmark data sets of the University of California, Irvine (UCI), machine learning repository are used; additionally the firefly-SVM is applied to the multiclass diagnosis of ultrasonic supraspinatus images. The classification performance of firefly-SVM is also compared to the original LIBSVM method associated with the grid search method and the particle swarm optimization based SVM (PSO-SVM). The experimental results advocate the use of firefly-SVM to classify pattern classifications for maximum accuracy. PMID:25802511

Research on bearing fault diagnosis of large machinery based on mathematical morphology

NASA Astrophysics Data System (ADS)

Wang, Yu

2018-04-01

To study the automatic diagnosis of large machinery fault based on support vector machine, combining the four common faults of the large machinery, the support vector machine is used to classify and identify the fault. The extracted feature vectors are entered. The feature vector is trained and identified by multi - classification method. The optimal parameters of the support vector machine are searched by trial and error method and cross validation method. Then, the support vector machine is compared with BP neural network. The results show that the support vector machines are short in time and high in classification accuracy. It is more suitable for the research of fault diagnosis in large machinery. Therefore, it can be concluded that the training speed of support vector machines (SVM) is fast and the performance is good.

Investigation of a tubular dual-stator flux-switching permanent-magnet linear generator for free-piston energy converter

NASA Astrophysics Data System (ADS)

Sui, Yi; Zheng, Ping; Tong, Chengde; Yu, Bin; Zhu, Shaohong; Zhu, Jianguo

2015-05-01

This paper describes a tubular dual-stator flux-switching permanent-magnet (PM) linear generator for free-piston energy converter. The operating principle, topology, and design considerations of the machine are investigated. Combining the motion characteristic of free-piston Stirling engine, a tubular dual-stator PM linear generator is designed by finite element method. Some major structural parameters, such as the outer and inner radii of the mover, PM thickness, mover tooth width, tooth width of the outer and inner stators, etc., are optimized to improve the machine performances like thrust capability and power density. In comparison with conventional single-stator PM machines like moving-magnet linear machine and flux-switching linear machine, the proposed dual-stator flux-switching PM machine shows advantages in higher mass power density, higher volume power density, and lighter mover.

A tubular hybrid Halbach/axially-magnetized permanent-magnet linear machine

NASA Astrophysics Data System (ADS)

Sui, Yi; Liu, Yong; Cheng, Luming; Liu, Jiaqi; Zheng, Ping

2017-05-01

A single-phase tubular permanent-magnet linear machine (PMLM) with hybrid Halbach/axially-magnetized PM arrays is proposed for free-piston Stirling power generation system. Machine topology and operating principle are elaborately illustrated. With the sinusoidal speed characteristic of the free-piston Stirling engine considered, the proposed machine is designed and calculated by finite-element analysis (FEA). The main structural parameters, such as outer radius of the mover, radial length of both the axially-magnetized PMs and ferromagnetic poles, axial length of both the middle and end radially-magnetized PMs, etc., are optimized to improve both the force capability and power density. Compared with the conventional PMLMs, the proposed machine features high mass and volume power density, and has the advantages of simple control and low converter cost. The proposed machine topology is applicable to tubular PMLMs with any phases.

Irrelevance of the Power Stroke for the Directionality, Stopping Force, and Optimal Efficiency of Chemically Driven Molecular Machines

PubMed Central

Astumian, R. Dean

2015-01-01

A simple model for a chemically driven molecular walker shows that the elastic energy stored by the molecule and released during the conformational change known as the power-stroke (i.e., the free-energy difference between the pre- and post-power-stroke states) is irrelevant for determining the directionality, stopping force, and efficiency of the motor. Further, the apportionment of the dependence on the externally applied force between the forward and reverse rate constants of the power-stroke (or indeed among all rate constants) is irrelevant for determining the directionality, stopping force, and efficiency of the motor. Arguments based on the principle of microscopic reversibility demonstrate that this result is general for all chemically driven molecular machines, and even more broadly that the relative energies of the states of the motor have no role in determining the directionality, stopping force, or optimal efficiency of the machine. Instead, the directionality, stopping force, and optimal efficiency are determined solely by the relative heights of the energy barriers between the states. Molecular recognition—the ability of a molecular machine to discriminate between substrate and product depending on the state of the machine—is far more important for determining the intrinsic directionality and thermodynamics of chemo-mechanical coupling than are the details of the internal mechanical conformational motions of the machine. In contrast to the conclusions for chemical driving, a power-stroke is very important for the directionality and efficiency of light-driven molecular machines and for molecular machines driven by external modulation of thermodynamic parameters. PMID:25606678

Laser-assisted electrochemical micromachining of mould cavity on the stainless steel surface

NASA Astrophysics Data System (ADS)

Li, Xiaohai; Wang, Shuming; Wang, Dong; Tong, Han

2018-02-01

In order to fabricate the micro mould cavities with complex structures on 304 stainless steel, laser-assisted electrochemical micromachining (EMM) based on surface modification by fiber laser masking was studied,and a new device of laser-assisted EMM was developed. Laser marking on the surface of 304 stainless steel can first be realized by fiber laser heating scanning. Through analysis of X ray diffraction analysis (XRD), metal oxide layer with predefined pattern can be formed by laser marking, and phase transformation can also occur on the 304 stainless steel surface, which produce the laser masking layer with corrosion resistance. The stainless steel surface with laser masking layer is subsequently etched by EMM, the laser masking layer severs as the temporary protective layer without relying on lithography mask, the fabrication of formed electrodes is also avoided, so micro pattern cavities can fast be fabricated. The impacts on machining accuracy during EMM with laser masking were discussed to optimize machining parameters, such as machining voltage, electrolyte concentration, duty cycle of pulse power supply and electrode gap size, the typical mould cavities 23μm deep were fabricated under the optimized parameters.

Drilling High Precision Holes in Ti6Al4V Using Rotary Ultrasonic Machining and Uncertainties Underlying Cutting Force, Tool Wear, and Production Inaccuracies.

PubMed

Chowdhury, M A K; Sharif Ullah, A M M; Anwar, Saqib

2017-09-12

Ti6Al4V alloys are difficult-to-cut materials that have extensive applications in the automotive and aerospace industry. A great deal of effort has been made to develop and improve the machining operations of Ti6Al4V alloys. This paper presents an experimental study that systematically analyzes the effects of the machining conditions (ultrasonic power, feed rate, spindle speed, and tool diameter) on the performance parameters (cutting force, tool wear, overcut error, and cylindricity error), while drilling high precision holes on the workpiece made of Ti6Al4V alloys using rotary ultrasonic machining (RUM). Numerical results were obtained by conducting experiments following the design of an experiment procedure. The effects of the machining conditions on each performance parameter have been determined by constructing a set of possibility distributions (i.e., trapezoidal fuzzy numbers) from the experimental data. A possibility distribution is a probability-distribution-neural representation of uncertainty, and is effective in quantifying the uncertainty underlying physical quantities when there is a limited number of data points which is the case here. Lastly, the optimal machining conditions have been identified using these possibility distributions.

Optimal Control of Induction Machines to Minimize Transient Energy Losses

NASA Astrophysics Data System (ADS)

Plathottam, Siby Jose

Induction machines are electromechanical energy conversion devices comprised of a stator and a rotor. Torque is generated due to the interaction between the rotating magnetic field from the stator, and the current induced in the rotor conductors. Their speed and torque output can be precisely controlled by manipulating the magnitude, frequency, and phase of the three input sinusoidal voltage waveforms. Their ruggedness, low cost, and high efficiency have made them ubiquitous component of nearly every industrial application. Thus, even a small improvement in their energy efficient tend to give a large amount of electrical energy savings over the lifetime of the machine. Hence, increasing energy efficiency (reducing energy losses) in induction machines is a constrained optimization problem that has attracted attention from researchers. The energy conversion efficiency of induction machines depends on both the speed-torque operating point, as well as the input voltage waveform. It also depends on whether the machine is in the transient or steady state. Maximizing energy efficiency during steady state is a Static Optimization problem, that has been extensively studied, with commercial solutions available. On the other hand, improving energy efficiency during transients is a Dynamic Optimization problem that is sparsely studied. This dissertation exclusively focuses on improving energy efficiency during transients. This dissertation treats the transient energy loss minimization problem as an optimal control problem which consists of a dynamic model of the machine, and a cost functional. The rotor field oriented current fed model of the induction machine is selected as the dynamic model. The rotor speed and rotor d-axis flux are the state variables in the dynamic model. The stator currents referred to as d-and q-axis currents are the control inputs. A cost functional is proposed that assigns a cost to both the energy losses in the induction machine, as well as the deviations from desired speed-torque-magnetic flux setpoints. Using Pontryagin's minimum principle, a set of necessary conditions that must be satisfied by the optimal control trajectories are derived. The conditions are in the form a two-point boundary value problem, that can be solved numerically. The conjugate gradient method that was modified using the Hestenes-Stiefel formula was used to obtain the numerical solution of both the control and state trajectories. Using the distinctive shape of the numerical trajectories as inspiration, analytical expressions were derived for the state, and control trajectories. It was shown that the trajectory could be fully described by finding the solution of a one-dimensional optimization problem. The sensitivity of both the optimal trajectory and the optimal energy efficiency to different induction machine parameters were analyzed. A non-iterative solution that can use feedback for generating optimal control trajectories in real time was explored. It was found that an artificial neural network could be trained using the numerical solutions and made to emulate the optimal control trajectories with a high degree of accuracy. Hence a neural network along with a supervisory logic was implemented and used in a real-time simulation to control the Finite Element Method model of the induction machine. The results were compared with three other control regimes and the optimal control system was found to have the highest energy efficiency for the same drive cycle.

A single-phase axially-magnetized permanent-magnet oscillating machine for miniature aerospace power sources

NASA Astrophysics Data System (ADS)

Sui, Yi; Zheng, Ping; Cheng, Luming; Wang, Weinan; Liu, Jiaqi

2017-05-01

A single-phase axially-magnetized permanent-magnet (PM) oscillating machine which can be integrated with a free-piston Stirling engine to generate electric power, is investigated for miniature aerospace power sources. Machine structure, operating principle and detent force characteristic are elaborately studied. With the sinusoidal speed characteristic of the mover considered, the proposed machine is designed by 2D finite-element analysis (FEA), and some main structural parameters such as air gap diameter, dimensions of PMs, pole pitches of both stator and mover, and the pole-pitch combinations, etc., are optimized to improve both the power density and force capability. Compared with the three-phase PM linear machines, the proposed single-phase machine features less PM use, simple control and low controller cost. The power density of the proposed machine is higher than that of the three-phase radially-magnetized PM linear machine, but lower than the three-phase axially-magnetized PM linear machine.

Prediction on sunspot activity based on fuzzy information granulation and support vector machine

NASA Astrophysics Data System (ADS)

Peng, Lingling; Yan, Haisheng; Yang, Zhigang

2018-04-01

In order to analyze the range of sunspots, a combined prediction method of forecasting the fluctuation range of sunspots based on fuzzy information granulation (FIG) and support vector machine (SVM) was put forward. Firstly, employing the FIG to granulate sample data and extract va)alid information of each window, namely the minimum value, the general average value and the maximum value of each window. Secondly, forecasting model is built respectively with SVM and then cross method is used to optimize these parameters. Finally, the fluctuation range of sunspots is forecasted with the optimized SVM model. Case study demonstrates that the model have high accuracy and can effectively predict the fluctuation of sunspots.

Optimization of cutting parameters for machining time in turning process

NASA Astrophysics Data System (ADS)

Mavliutov, A. R.; Zlotnikov, E. G.

2018-03-01

This paper describes the most effective methods for nonlinear constraint optimization of cutting parameters in the turning process. Among them are Linearization Programming Method with Dual-Simplex algorithm, Interior Point method, and Augmented Lagrangian Genetic Algorithm (ALGA). Every each of them is tested on an actual example – the minimization of production rate in turning process. The computation was conducted in the MATLAB environment. The comparative results obtained from the application of these methods show: The optimal value of the linearized objective and the original function are the same. ALGA gives sufficiently accurate values, however, when the algorithm uses the Hybrid function with Interior Point algorithm, the resulted values have the maximal accuracy.

Detecting epileptic seizure with different feature extracting strategies using robust machine learning classification techniques by applying advance parameter optimization approach.

PubMed

Hussain, Lal

2018-06-01

Epilepsy is a neurological disorder produced due to abnormal excitability of neurons in the brain. The research reveals that brain activity is monitored through electroencephalogram (EEG) of patients suffered from seizure to detect the epileptic seizure. The performance of EEG detection based epilepsy require feature extracting strategies. In this research, we have extracted varying features extracting strategies based on time and frequency domain characteristics, nonlinear, wavelet based entropy and few statistical features. A deeper study was undertaken using novel machine learning classifiers by considering multiple factors. The support vector machine kernels are evaluated based on multiclass kernel and box constraint level. Likewise, for K-nearest neighbors (KNN), we computed the different distance metrics, Neighbor weights and Neighbors. Similarly, the decision trees we tuned the paramours based on maximum splits and split criteria and ensemble classifiers are evaluated based on different ensemble methods and learning rate. For training/testing tenfold Cross validation was employed and performance was evaluated in form of TPR, NPR, PPV, accuracy and AUC. In this research, a deeper analysis approach was performed using diverse features extracting strategies using robust machine learning classifiers with more advanced optimal options. Support Vector Machine linear kernel and KNN with City block distance metric give the overall highest accuracy of 99.5% which was higher than using the default parameters for these classifiers. Moreover, highest separation (AUC = 0.9991, 0.9990) were obtained at different kernel scales using SVM. Additionally, the K-nearest neighbors with inverse squared distance weight give higher performance at different Neighbors. Moreover, to distinguish the postictal heart rate oscillations from epileptic ictal subjects, and highest performance of 100% was obtained using different machine learning classifiers.

Teaching learning algorithm based optimization of kerf deviations in pulsed Nd:YAG laser cutting of Kevlar-29 composite laminates

NASA Astrophysics Data System (ADS)

Gautam, Girish Dutt; Pandey, Arun Kumar

2018-03-01

Kevlar is the most popular aramid fiber and most commonly used in different technologically advanced industries for various applications. But the precise cutting of Kevlar composite laminates is a difficult task. The conventional cutting methods face various defects such as delamination, burr formation, fiber pullout with poor surface quality and their mechanical performance is greatly affected by these defects. The laser beam machining may be an alternative of the conventional cutting processes due to its non-contact nature, requirement of low specific energy with higher production rate. But this process also faces some problems that may be minimized by operating the machine at optimum parameters levels. This research paper examines the effective utilization of the Nd:YAG laser cutting system on difficult-to-cut Kevlar-29 composite laminates. The objective of the proposed work is to find the optimum process parameters settings for getting the minimum kerf deviations at both sides. The experiments have been conducted on Kevlar-29 composite laminates having thickness 1.25 mm by using Box-Benkhen design with two center points. The experimental data have been used for the optimization by using the proposed methodology. For the optimization, Teaching learning Algorithm based approach has been employed to obtain the minimum kerf deviation at bottom and top sides. A self coded Matlab program has been developed by using the proposed methodology and this program has been used for the optimization. Finally, the confirmation tests have been performed to compare the experimental and optimum results obtained by the proposed methodology. The comparison results show that the machining performance in the laser beam cutting process has been remarkably improved through proposed approach. Finally, the influence of different laser cutting parameters such as lamp current, pulse frequency, pulse width, compressed air pressure and cutting speed on top kerf deviation and bottom kerf deviation during the Nd:YAG laser cutting of Kevlar-29 laminates have been discussed.

Energy landscapes for a machine-learning prediction of patient discharge

NASA Astrophysics Data System (ADS)

Das, Ritankar; Wales, David J.

2016-06-01

The energy landscapes framework is applied to a configuration space generated by training the parameters of a neural network. In this study the input data consists of time series for a collection of vital signs monitored for hospital patients, and the outcomes are patient discharge or continued hospitalisation. Using machine learning as a predictive diagnostic tool to identify patterns in large quantities of electronic health record data in real time is a very attractive approach for supporting clinical decisions, which have the potential to improve patient outcomes and reduce waiting times for discharge. Here we report some preliminary analysis to show how machine learning might be applied. In particular, we visualize the fitting landscape in terms of locally optimal neural networks and the connections between them in parameter space. We anticipate that these results, and analogues of thermodynamic properties for molecular systems, may help in the future design of improved predictive tools.

Computational Fluid Dynamics Analysis of Nozzle in Abrasive Water Jet Machining

NASA Astrophysics Data System (ADS)

Venugopal, S.; Chandresekaran, M.; Muthuraman, V.; Sathish, S.

2017-03-01

Abrasive water jet cutting is one of the most recently developed non-traditional manufacturing technologies. The general nature of flow through the machining, results in rapid wear of the nozzle which decrease the cutting performance. It is well known that the inlet pressure of the abrasive water suspension has main effect on the erosion characteristics of the inner surface of the nozzle. The objective of the project is to analyze the effect of inlet pressure on wall shear and exit kinetic energy. The analysis would be carried out by varying the inlet pressure of the nozzle, so as to obtain optimized process parameters for minimum nozzle wear. The two phase flow analysis would be carried by using computational fluid dynamics tool CFX. The availability of minimized process parameters such as of abrasive water jet machining (AWJM) is limited to water and experimental test can be cost prohibitive.

Prediction of multi performance characteristics of wire EDM process using grey ANFIS

NASA Astrophysics Data System (ADS)

Kumanan, Somasundaram; Nair, Anish

2017-09-01

Super alloys are used to fabricate components in ultra-supercritical power plants. These hard to machine materials are processed using non-traditional machining methods like Wire cut electrical discharge machining and needs attention. This paper details about multi performance optimization of wire EDM process using Grey ANFIS. Experiments are designed to establish the performance characteristics of wire EDM such as surface roughness, material removal rate, wire wear rate and geometric tolerances. The control parameters are pulse on time, pulse off time, current, voltage, flushing pressure, wire tension, table feed and wire speed. Grey relational analysis is employed to optimise the multi objectives. Analysis of variance of the grey grades is used to identify the critical parameters. A regression model is developed and used to generate datasets for the training of proposed adaptive neuro fuzzy inference system. The developed prediction model is tested for its prediction ability.

Optimal Parameter Selection for Support Vector Machine Based on Artificial Bee Colony Algorithm: A Case Study of Grid-Connected PV System Power Prediction.

PubMed

Gao, Xiang-Ming; Yang, Shi-Feng; Pan, San-Bo

2017-01-01

Predicting the output power of photovoltaic system with nonstationarity and randomness, an output power prediction model for grid-connected PV systems is proposed based on empirical mode decomposition (EMD) and support vector machine (SVM) optimized with an artificial bee colony (ABC) algorithm. First, according to the weather forecast data sets on the prediction date, the time series data of output power on a similar day with 15-minute intervals are built. Second, the time series data of the output power are decomposed into a series of components, including some intrinsic mode components IMFn and a trend component Res, at different scales using EMD. The corresponding SVM prediction model is established for each IMF component and trend component, and the SVM model parameters are optimized with the artificial bee colony algorithm. Finally, the prediction results of each model are reconstructed, and the predicted values of the output power of the grid-connected PV system can be obtained. The prediction model is tested with actual data, and the results show that the power prediction model based on the EMD and ABC-SVM has a faster calculation speed and higher prediction accuracy than do the single SVM prediction model and the EMD-SVM prediction model without optimization.

Hybrid ABC Optimized MARS-Based Modeling of the Milling Tool Wear from Milling Run Experimental Data

PubMed Central

García Nieto, Paulino José; García-Gonzalo, Esperanza; Ordóñez Galán, Celestino; Bernardo Sánchez, Antonio

2016-01-01

Milling cutters are important cutting tools used in milling machines to perform milling operations, which are prone to wear and subsequent failure. In this paper, a practical new hybrid model to predict the milling tool wear in a regular cut, as well as entry cut and exit cut, of a milling tool is proposed. The model was based on the optimization tool termed artificial bee colony (ABC) in combination with multivariate adaptive regression splines (MARS) technique. This optimization mechanism involved the parameter setting in the MARS training procedure, which significantly influences the regression accuracy. Therefore, an ABC–MARS-based model was successfully used here to predict the milling tool flank wear (output variable) as a function of the following input variables: the time duration of experiment, depth of cut, feed, type of material, etc. Regression with optimal hyperparameters was performed and a determination coefficient of 0.94 was obtained. The ABC–MARS-based model's goodness of fit to experimental data confirmed the good performance of this model. This new model also allowed us to ascertain the most influential parameters on the milling tool flank wear with a view to proposing milling machine's improvements. Finally, conclusions of this study are exposed. PMID:28787882

Hybrid ABC Optimized MARS-Based Modeling of the Milling Tool Wear from Milling Run Experimental Data.

PubMed

García Nieto, Paulino José; García-Gonzalo, Esperanza; Ordóñez Galán, Celestino; Bernardo Sánchez, Antonio

2016-01-28

Milling cutters are important cutting tools used in milling machines to perform milling operations, which are prone to wear and subsequent failure. In this paper, a practical new hybrid model to predict the milling tool wear in a regular cut, as well as entry cut and exit cut, of a milling tool is proposed. The model was based on the optimization tool termed artificial bee colony (ABC) in combination with multivariate adaptive regression splines (MARS) technique. This optimization mechanism involved the parameter setting in the MARS training procedure, which significantly influences the regression accuracy. Therefore, an ABC-MARS-based model was successfully used here to predict the milling tool flank wear (output variable) as a function of the following input variables: the time duration of experiment, depth of cut, feed, type of material, etc . Regression with optimal hyperparameters was performed and a determination coefficient of 0.94 was obtained. The ABC-MARS-based model's goodness of fit to experimental data confirmed the good performance of this model. This new model also allowed us to ascertain the most influential parameters on the milling tool flank wear with a view to proposing milling machine's improvements. Finally, conclusions of this study are exposed.

Optimal Parameter Selection for Support Vector Machine Based on Artificial Bee Colony Algorithm: A Case Study of Grid-Connected PV System Power Prediction

PubMed Central

2017-01-01

Predicting the output power of photovoltaic system with nonstationarity and randomness, an output power prediction model for grid-connected PV systems is proposed based on empirical mode decomposition (EMD) and support vector machine (SVM) optimized with an artificial bee colony (ABC) algorithm. First, according to the weather forecast data sets on the prediction date, the time series data of output power on a similar day with 15-minute intervals are built. Second, the time series data of the output power are decomposed into a series of components, including some intrinsic mode components IMFn and a trend component Res, at different scales using EMD. The corresponding SVM prediction model is established for each IMF component and trend component, and the SVM model parameters are optimized with the artificial bee colony algorithm. Finally, the prediction results of each model are reconstructed, and the predicted values of the output power of the grid-connected PV system can be obtained. The prediction model is tested with actual data, and the results show that the power prediction model based on the EMD and ABC-SVM has a faster calculation speed and higher prediction accuracy than do the single SVM prediction model and the EMD-SVM prediction model without optimization. PMID:28912803

Parametric optimization of multiple quality characteristics in laser cutting of Inconel-718 by using hybrid approach of multiple regression analysis and genetic algorithm

NASA Astrophysics Data System (ADS)

Shrivastava, Prashant Kumar; Pandey, Arun Kumar

2018-06-01

Inconel-718 has found high demand in different industries due to their superior mechanical properties. The traditional cutting methods are facing difficulties for cutting these alloys due to their low thermal potential, lower elasticity and high chemical compatibility at inflated temperature. The challenges of machining and/or finishing of unusual shapes and/or sizes in these materials have also faced by traditional machining. Laser beam cutting may be applied for the miniaturization and ultra-precision cutting and/or finishing by appropriate control of different process parameter. This paper present multi-objective optimization the kerf deviation, kerf width and kerf taper in the laser cutting of Incone-718 sheet. The second order regression models have been developed for different quality characteristics by using the experimental data obtained through experimentation. The regression models have been used as objective function for multi-objective optimization based on the hybrid approach of multiple regression analysis and genetic algorithm. The comparison of optimization results to experimental results shows an improvement of 88%, 10.63% and 42.15% in kerf deviation, kerf width and kerf taper, respectively. Finally, the effects of different process parameters on quality characteristics have also been discussed.

Design and Analysis of a Sensor System for Cutting Force Measurement in Machining Processes

PubMed Central

Liang, Qiaokang; Zhang, Dan; Coppola, Gianmarc; Mao, Jianxu; Sun, Wei; Wang, Yaonan; Ge, Yunjian

2016-01-01

Multi-component force sensors have infiltrated a wide variety of automation products since the 1970s. However, one seldom finds full-component sensor systems available in the market for cutting force measurement in machine processes. In this paper, a new six-component sensor system with a compact monolithic elastic element (EE) is designed and developed to detect the tangential cutting forces Fx, Fy and Fz (i.e., forces along x-, y-, and z-axis) as well as the cutting moments Mx, My and Mz (i.e., moments about x-, y-, and z-axis) simultaneously. Optimal structural parameters of the EE are carefully designed via simulation-driven optimization. Moreover, a prototype sensor system is fabricated, which is applied to a 5-axis parallel kinematic machining center. Calibration experimental results demonstrate that the system is capable of measuring cutting forces and moments with good linearity while minimizing coupling error. Both the Finite Element Analysis (FEA) and calibration experimental studies validate the high performance of the proposed sensor system that is expected to be adopted into machining processes. PMID:26751451

Design and Analysis of a Sensor System for Cutting Force Measurement in Machining Processes.

PubMed

Liang, Qiaokang; Zhang, Dan; Coppola, Gianmarc; Mao, Jianxu; Sun, Wei; Wang, Yaonan; Ge, Yunjian

2016-01-07

Multi-component force sensors have infiltrated a wide variety of automation products since the 1970s. However, one seldom finds full-component sensor systems available in the market for cutting force measurement in machine processes. In this paper, a new six-component sensor system with a compact monolithic elastic element (EE) is designed and developed to detect the tangential cutting forces Fx, Fy and Fz (i.e., forces along x-, y-, and z-axis) as well as the cutting moments Mx, My and Mz (i.e., moments about x-, y-, and z-axis) simultaneously. Optimal structural parameters of the EE are carefully designed via simulation-driven optimization. Moreover, a prototype sensor system is fabricated, which is applied to a 5-axis parallel kinematic machining center. Calibration experimental results demonstrate that the system is capable of measuring cutting forces and moments with good linearity while minimizing coupling error. Both the Finite Element Analysis (FEA) and calibration experimental studies validate the high performance of the proposed sensor system that is expected to be adopted into machining processes.

Cell-cycle research with synchronous cultures: an evaluation

NASA Technical Reports Server (NTRS)

Helmstetter, C. E.; Thornton, M.; Grover, N. B.

2001-01-01

The baby-machine system, which produces new-born Escherichia coli cells from cultures immobilized on a membrane, was developed many years ago in an attempt to attain optimal synchrony with minimal disturbance of steady-state growth. In the present article, we put forward a model to describe the behaviour of cells produced by this method, and provide quantitative evaluation of the parameters involved, at each of four different growth rates. Considering the high level of selection achievable with this technique and the natural dispersion in interdivision times, we believe that the output of the baby machine is probably close to optimal in terms of both quality and persistence of synchrony. We show that considerable information on events in the cell cycle can be obtained from populations with age distributions very much broader than those achieved with the baby machine and differing only modestly from steady state. The data presented here, together with the long and fruitful history of findings employing the baby-machine technique, suggest that minimisation of stress on cells is the single most important factor for successful cell-cycle analysis.

Relevance Vector Machine and Support Vector Machine Classifier Analysis of Scanning Laser Polarimetry Retinal Nerve Fiber Layer Measurements

PubMed Central

Bowd, Christopher; Medeiros, Felipe A.; Zhang, Zuohua; Zangwill, Linda M.; Hao, Jiucang; Lee, Te-Won; Sejnowski, Terrence J.; Weinreb, Robert N.; Goldbaum, Michael H.

2010-01-01

Purpose To classify healthy and glaucomatous eyes using relevance vector machine (RVM) and support vector machine (SVM) learning classifiers trained on retinal nerve fiber layer (RNFL) thickness measurements obtained by scanning laser polarimetry (SLP). Methods Seventy-two eyes of 72 healthy control subjects (average age = 64.3 ± 8.8 years, visual field mean deviation =−0.71 ± 1.2 dB) and 92 eyes of 92 patients with glaucoma (average age = 66.9 ± 8.9 years, visual field mean deviation =−5.32 ± 4.0 dB) were imaged with SLP with variable corneal compensation (GDx VCC; Laser Diagnostic Technologies, San Diego, CA). RVM and SVM learning classifiers were trained and tested on SLP-determined RNFL thickness measurements from 14 standard parameters and 64 sectors (approximately 5.6° each) obtained in the circumpapillary area under the instrument-defined measurement ellipse (total 78 parameters). Tenfold cross-validation was used to train and test RVM and SVM classifiers on unique subsets of the full 164-eye data set and areas under the receiver operating characteristic (AUROC) curve for the classification of eyes in the test set were generated. AUROC curve results from RVM and SVM were compared to those for 14 SLP software-generated global and regional RNFL thickness parameters. Also reported was the AUROC curve for the GDx VCC software-generated nerve fiber indicator (NFI). Results The AUROC curves for RVM and SVM were 0.90 and 0.91, respectively, and increased to 0.93 and 0.94 when the training sets were optimized with sequential forward and backward selection (resulting in reduced dimensional data sets). AUROC curves for optimized RVM and SVM were significantly larger than those for all individual SLP parameters. The AUROC curve for the NFI was 0.87. Conclusions Results from RVM and SVM trained on SLP RNFL thickness measurements are similar and provide accurate classification of glaucomatous and healthy eyes. RVM may be preferable to SVM, because it provides a Bayesian-derived probability of glaucoma as an output. These results suggest that these machine learning classifiers show good potential for glaucoma diagnosis. PMID:15790898

Optimization of Straight Cylindrical Turning Using Artificial Bee Colony (ABC) Algorithm

NASA Astrophysics Data System (ADS)

Prasanth, Rajanampalli Seshasai Srinivasa; Hans Raj, Kandikonda

2017-04-01

Artificial bee colony (ABC) algorithm, that mimics the intelligent foraging behavior of honey bees, is increasingly gaining acceptance in the field of process optimization, as it is capable of handling nonlinearity, complexity and uncertainty. Straight cylindrical turning is a complex and nonlinear machining process which involves the selection of appropriate cutting parameters that affect the quality of the workpiece. This paper presents the estimation of optimal cutting parameters of the straight cylindrical turning process using the ABC algorithm. The ABC algorithm is first tested on four benchmark problems of numerical optimization and its performance is compared with genetic algorithm (GA) and ant colony optimization (ACO) algorithm. Results indicate that, the rate of convergence of ABC algorithm is better than GA and ACO. Then, the ABC algorithm is used to predict optimal cutting parameters such as cutting speed, feed rate, depth of cut and tool nose radius to achieve good surface finish. Results indicate that, the ABC algorithm estimated a comparable surface finish when compared with real coded genetic algorithm and differential evolution algorithm.

Optimization and Simulation of Plastic Injection Process using Genetic Algorithm and Moldflow

NASA Astrophysics Data System (ADS)

Martowibowo, Sigit Yoewono; Kaswadi, Agung

2017-03-01

The use of plastic-based products is continuously increasing. The increasing demands for thinner products, lower production costs, yet higher product quality has triggered an increase in the number of research projects on plastic molding processes. An important branch of such research is focused on mold cooling system. Conventional cooling systems are most widely used because they are easy to make by using conventional machining processes. However, the non-uniform cooling processes are considered as one of their weaknesses. Apart from the conventional systems, there are also conformal cooling systems that are designed for faster and more uniform plastic mold cooling. In this study, the conformal cooling system is applied for the production of bowl-shaped product made of PP AZ564. Optimization is conducted to initiate machine setup parameters, namely, the melting temperature, injection pressure, holding pressure and holding time. The genetic algorithm method and Moldflow were used to optimize the injection process parameters at a minimum cycle time. It is found that, an optimum injection molding processes could be obtained by setting the parameters to the following values: T M = 180 °C; P inj = 20 MPa; P hold = 16 MPa and t hold = 8 s, with a cycle time of 14.11 s. Experiments using the conformal cooling system yielded an average cycle time of 14.19 s. The studied conformal cooling system yielded a volumetric shrinkage of 5.61% and the wall shear stress was found at 0.17 MPa. The difference between the cycle time obtained through simulations and experiments using the conformal cooling system was insignificant (below 1%). Thus, combining process parameters optimization and simulations by using genetic algorithm method with Moldflow can be considered as valid.

Multi-objective component sizing of a power-split plug-in hybrid electric vehicle powertrain using Pareto-based natural optimization machines

NASA Astrophysics Data System (ADS)

Mozaffari, Ahmad; Vajedi, Mahyar; Chehresaz, Maryyeh; Azad, Nasser L.

2016-03-01

The urgent need to meet increasingly tight environmental regulations and new fuel economy requirements has motivated system science researchers and automotive engineers to take advantage of emerging computational techniques to further advance hybrid electric vehicle and plug-in hybrid electric vehicle (PHEV) designs. In particular, research has focused on vehicle powertrain system design optimization, to reduce the fuel consumption and total energy cost while improving the vehicle's driving performance. In this work, two different natural optimization machines, namely the synchronous self-learning Pareto strategy and the elitism non-dominated sorting genetic algorithm, are implemented for component sizing of a specific power-split PHEV platform with a Toyota plug-in Prius as the baseline vehicle. To do this, a high-fidelity model of the Toyota plug-in Prius is employed for the numerical experiments using the Autonomie simulation software. Based on the simulation results, it is demonstrated that Pareto-based algorithms can successfully optimize the design parameters of the vehicle powertrain.

Minimization of the hole overcut and cylindricity errors during rotary ultrasonic drilling of Ti-6Al-4V

NASA Astrophysics Data System (ADS)

Nasr, M.; Anwar, S.; El-Tamimi, A.; Pervaiz, S.

2018-04-01

Titanium and its alloys e.g. Ti6Al4V have widespread applications in aerospace, automotive and medical industry. At the same time titanium and its alloys are regarded as difficult to machine materials due to their high strength and low thermal conductivity. Significant efforts have been dispensed to improve the accuracy of the machining processes for Ti6Al4V. The current study present the use of the rotary ultrasonic drilling (RUD) process for machining high quality holes in Ti6Al4V. The study takes into account the effects of the main RUD input parameters including spindle speed, ultrasonic power, feed rate and tool diameter on the key output responses related to the accuracy of the drilled holes including cylindricity and overcut errors. Analysis of variance (ANOVA) was employed to study the influence of the input parameters on cylindricity and overcut error. Later, regression models were developed to find the optimal set of input parameters to minimize the cylindricity and overcut errors.

An effective parameter optimization technique for vibration flow field characterization of PP melts via LS-SVM combined with SALS in an electromagnetism dynamic extruder

NASA Astrophysics Data System (ADS)

Xian, Guangming

2018-03-01

A method for predicting the optimal vibration field parameters by least square support vector machine (LS-SVM) is presented in this paper. One convenient and commonly used technique for characterizing the the vibration flow field of polymer melts films is small angle light scattering (SALS) in a visualized slit die of the electromagnetism dynamic extruder. The optimal value of vibration vibration frequency, vibration amplitude, and the maximum light intensity projection area can be obtained by using LS-SVM for prediction. For illustrating this method and show its validity, the flowing material is used with polypropylene (PP) and fifteen samples are tested at the rotation speed of screw at 36rpm. This paper first describes the apparatus of SALS to perform the experiments, then gives the theoretical basis of this new method, and detail the experimental results for parameter prediction of vibration flow field. It is demonstrated that it is possible to use the method of SALS and obtain detailed information on optimal parameter of vibration flow field of PP melts by LS-SVM.

BEAM OPTIMIZATION STUDY FOR AN X-RAY FEL OSCILLATOR AT THE LCLS-II

DOE Office of Scientific and Technical Information (OSTI.GOV)

Qin, Weilun; Huang, S.; Liu, K.X.

2016-06-01

The 4 GeV LCLS-II superconducting linac with high repetition beam rate enables the possibility to drive an X-Ray FEL oscillator at harmonic frequencies *. Compared to the regular LCLS-II machine setup, the oscillator mode requires a much longer bunch length with a relatively lower current. Also a flat longitudinal phase space distribution is critical to maintain the FEL gain since the X-ray cavity has extremely narrow bandwidth. In this paper, we study the longitudinal phase space optimization including shaping the initial beam from the injector and optimizing the bunch compressor and dechirper parameters. We obtain a bunch with a flatmore » energy chirp over 400 fs in the core part with current above 100 A. The optimization was based on LiTrack and Elegant simulations using LCLS-II beam parameters.« less

A novel single-phase flux-switching permanent magnet linear generator used for free-piston Stirling engine

NASA Astrophysics Data System (ADS)

Zheng, Ping; Sui, Yi; Tong, Chengde; Bai, Jingang; Yu, Bin; Lin, Fei

2014-05-01

This paper investigates a novel single-phase flux-switching permanent-magnet (PM) linear machine used for free-piston Stirling engines. The machine topology and operating principle are studied. A flux-switching PM linear machine is designed based on the quasi-sinusoidal speed characteristic of the resonant piston. Considering the performance of back electromotive force and thrust capability, some leading structural parameters, including the air gap length, the PM thickness, the ratio of the outer radius of mover to that of stator, the mover tooth width, the stator tooth width, etc., are optimized by finite element analysis. Compared with conventional three-phase moving-magnet linear machine, the proposed single-phase flux-switching topology shows advantages in less PM use, lighter mover, and higher volume power density.

Optimal structure and parameter learning of Ising models

DOE PAGES

Lokhov, Andrey; Vuffray, Marc Denis; Misra, Sidhant; ...

2018-03-16

Reconstruction of the structure and parameters of an Ising model from binary samples is a problem of practical importance in a variety of disciplines, ranging from statistical physics and computational biology to image processing and machine learning. The focus of the research community shifted toward developing universal reconstruction algorithms that are both computationally efficient and require the minimal amount of expensive data. Here, we introduce a new method, interaction screening, which accurately estimates model parameters using local optimization problems. The algorithm provably achieves perfect graph structure recovery with an information-theoretically optimal number of samples, notably in the low-temperature regime, whichmore » is known to be the hardest for learning. Here, the efficacy of interaction screening is assessed through extensive numerical tests on synthetic Ising models of various topologies with different types of interactions, as well as on real data produced by a D-Wave quantum computer. Finally, this study shows that the interaction screening method is an exact, tractable, and optimal technique that universally solves the inverse Ising problem.« less

Optimal structure and parameter learning of Ising models

DOE Office of Scientific and Technical Information (OSTI.GOV)

Lokhov, Andrey; Vuffray, Marc Denis; Misra, Sidhant

Reconstruction of the structure and parameters of an Ising model from binary samples is a problem of practical importance in a variety of disciplines, ranging from statistical physics and computational biology to image processing and machine learning. The focus of the research community shifted toward developing universal reconstruction algorithms that are both computationally efficient and require the minimal amount of expensive data. Here, we introduce a new method, interaction screening, which accurately estimates model parameters using local optimization problems. The algorithm provably achieves perfect graph structure recovery with an information-theoretically optimal number of samples, notably in the low-temperature regime, whichmore » is known to be the hardest for learning. Here, the efficacy of interaction screening is assessed through extensive numerical tests on synthetic Ising models of various topologies with different types of interactions, as well as on real data produced by a D-Wave quantum computer. Finally, this study shows that the interaction screening method is an exact, tractable, and optimal technique that universally solves the inverse Ising problem.« less

Computation of the Distribution of the Fiber-Matrix Interface Cracks in the Edge Trimming of CFRP

NASA Astrophysics Data System (ADS)

Wang, Fu-ji; Zhang, Bo-yu; Ma, Jian-wei; Bi, Guang-jian; Hu, Hai-bo

2018-04-01

Edge trimming is commonly used to bring the CFRP components to right dimension and shape in aerospace industries. However, various forms of undesirable machining damage occur frequently which will significantly decrease the material performance of CFRP. The damage is difficult to predict and control due to the complicated changing laws, causing unsatisfactory machining quality of CFRP components. Since the most of damage has the same essence: the fiber-matrix interface cracks, this study aims to calculate the distribution of them in edge trimming of CFRP, thereby to obtain the effects of the machining parameters, which could be helpful to guide the optimal selection of the machining parameters in engineering. Through the orthogonal cutting experiments, the quantitative relation between the fiber-matrix interface crack depth and the fiber cutting angle, cutting depth as well as cutting speed is established. According to the analysis on material removal process on any location of the workpiece in edge trimming, the instantaneous cutting parameters are calculated, and the formation process of the fiber-matrix interface crack is revealed. Finally, the computational method for the fiber-matrix interface cracks in edge trimming of CFRP is proposed. Upon the computational results, it is found that the fiber orientations of CFRP workpieces is the most significant factor on the fiber-matrix interface cracks, which can not only change the depth of them from micrometers to millimeters, but control the distribution image of them. Other machining parameters, only influence the fiber-matrix interface cracks depth but have little effect on the distribution image.

Optimal nonlinear information processing capacity in delay-based reservoir computers

NASA Astrophysics Data System (ADS)

Grigoryeva, Lyudmila; Henriques, Julie; Larger, Laurent; Ortega, Juan-Pablo

2015-09-01

Reservoir computing is a recently introduced brain-inspired machine learning paradigm capable of excellent performances in the processing of empirical data. We focus in a particular kind of time-delay based reservoir computers that have been physically implemented using optical and electronic systems and have shown unprecedented data processing rates. Reservoir computing is well-known for the ease of the associated training scheme but also for the problematic sensitivity of its performance to architecture parameters. This article addresses the reservoir design problem, which remains the biggest challenge in the applicability of this information processing scheme. More specifically, we use the information available regarding the optimal reservoir working regimes to construct a functional link between the reservoir parameters and its performance. This function is used to explore various properties of the device and to choose the optimal reservoir architecture, thus replacing the tedious and time consuming parameter scannings used so far in the literature.

Optimal nonlinear information processing capacity in delay-based reservoir computers.

PubMed

Grigoryeva, Lyudmila; Henriques, Julie; Larger, Laurent; Ortega, Juan-Pablo

2015-09-11

Reservoir computing is a recently introduced brain-inspired machine learning paradigm capable of excellent performances in the processing of empirical data. We focus in a particular kind of time-delay based reservoir computers that have been physically implemented using optical and electronic systems and have shown unprecedented data processing rates. Reservoir computing is well-known for the ease of the associated training scheme but also for the problematic sensitivity of its performance to architecture parameters. This article addresses the reservoir design problem, which remains the biggest challenge in the applicability of this information processing scheme. More specifically, we use the information available regarding the optimal reservoir working regimes to construct a functional link between the reservoir parameters and its performance. This function is used to explore various properties of the device and to choose the optimal reservoir architecture, thus replacing the tedious and time consuming parameter scannings used so far in the literature.

Optimal nonlinear information processing capacity in delay-based reservoir computers

PubMed Central

Grigoryeva, Lyudmila; Henriques, Julie; Larger, Laurent; Ortega, Juan-Pablo

2015-01-01

Reservoir computing is a recently introduced brain-inspired machine learning paradigm capable of excellent performances in the processing of empirical data. We focus in a particular kind of time-delay based reservoir computers that have been physically implemented using optical and electronic systems and have shown unprecedented data processing rates. Reservoir computing is well-known for the ease of the associated training scheme but also for the problematic sensitivity of its performance to architecture parameters. This article addresses the reservoir design problem, which remains the biggest challenge in the applicability of this information processing scheme. More specifically, we use the information available regarding the optimal reservoir working regimes to construct a functional link between the reservoir parameters and its performance. This function is used to explore various properties of the device and to choose the optimal reservoir architecture, thus replacing the tedious and time consuming parameter scannings used so far in the literature. PMID:26358528

a Gsa-Svm Hybrid System for Classification of Binary Problems

NASA Astrophysics Data System (ADS)

Sarafrazi, Soroor; Nezamabadi-pour, Hossein; Barahman, Mojgan

2011-06-01

This paperhybridizesgravitational search algorithm (GSA) with support vector machine (SVM) and made a novel GSA-SVM hybrid system to improve the classification accuracy in binary problems. GSA is an optimization heuristic toolused to optimize the value of SVM kernel parameter (in this paper, radial basis function (RBF) is chosen as the kernel function). The experimental results show that this newapproach can achieve high classification accuracy and is comparable to or better than the particle swarm optimization (PSO)-SVM and genetic algorithm (GA)-SVM, which are two hybrid systems for classification.

Thermodynamic metrics and optimal paths.

PubMed

Sivak, David A; Crooks, Gavin E

2012-05-11

A fundamental problem in modern thermodynamics is how a molecular-scale machine performs useful work, while operating away from thermal equilibrium without excessive dissipation. To this end, we derive a friction tensor that induces a Riemannian manifold on the space of thermodynamic states. Within the linear-response regime, this metric structure controls the dissipation of finite-time transformations, and bestows optimal protocols with many useful properties. We discuss the connection to the existing thermodynamic length formalism, and demonstrate the utility of this metric by solving for optimal control parameter protocols in a simple nonequilibrium model.

Thermocouple and infrared sensor-based measurement of temperature distribution in metal cutting.

PubMed

Kus, Abdil; Isik, Yahya; Cakir, M Cemal; Coşkun, Salih; Özdemir, Kadir

2015-01-12

In metal cutting, the magnitude of the temperature at the tool-chip interface is a function of the cutting parameters. This temperature directly affects production; therefore, increased research on the role of cutting temperatures can lead to improved machining operations. In this study, tool temperature was estimated by simultaneous temperature measurement employing both a K-type thermocouple and an infrared radiation (IR) pyrometer to measure the tool-chip interface temperature. Due to the complexity of the machining processes, the integration of different measuring techniques was necessary in order to obtain consistent temperature data. The thermal analysis results were compared via the ANSYS finite element method. Experiments were carried out in dry machining using workpiece material of AISI 4140 alloy steel that was heat treated by an induction process to a hardness of 50 HRC. A PVD TiAlN-TiN-coated WNVG 080404-IC907 carbide insert was used during the turning process. The results showed that with increasing cutting speed, feed rate and depth of cut, the tool temperature increased; the cutting speed was found to be the most effective parameter in assessing the temperature rise. The heat distribution of the cutting tool, tool-chip interface and workpiece provided effective and useful data for the optimization of selected cutting parameters during orthogonal machining.

Thermocouple and Infrared Sensor-Based Measurement of Temperature Distribution in Metal Cutting

PubMed Central

Kus, Abdil; Isik, Yahya; Cakir, M. Cemal; Coşkun, Salih; Özdemir, Kadir

2015-01-01

In metal cutting, the magnitude of the temperature at the tool-chip interface is a function of the cutting parameters. This temperature directly affects production; therefore, increased research on the role of cutting temperatures can lead to improved machining operations. In this study, tool temperature was estimated by simultaneous temperature measurement employing both a K-type thermocouple and an infrared radiation (IR) pyrometer to measure the tool-chip interface temperature. Due to the complexity of the machining processes, the integration of different measuring techniques was necessary in order to obtain consistent temperature data. The thermal analysis results were compared via the ANSYS finite element method. Experiments were carried out in dry machining using workpiece material of AISI 4140 alloy steel that was heat treated by an induction process to a hardness of 50 HRC. A PVD TiAlN-TiN-coated WNVG 080404-IC907 carbide insert was used during the turning process. The results showed that with increasing cutting speed, feed rate and depth of cut, the tool temperature increased; the cutting speed was found to be the most effective parameter in assessing the temperature rise. The heat distribution of the cutting tool, tool-chip interface and workpiece provided effective and useful data for the optimization of selected cutting parameters during orthogonal machining. PMID:25587976

Support Vector Machine Based on Adaptive Acceleration Particle Swarm Optimization

PubMed Central

Abdulameer, Mohammed Hasan; Othman, Zulaiha Ali

2014-01-01

Existing face recognition methods utilize particle swarm optimizer (PSO) and opposition based particle swarm optimizer (OPSO) to optimize the parameters of SVM. However, the utilization of random values in the velocity calculation decreases the performance of these techniques; that is, during the velocity computation, we normally use random values for the acceleration coefficients and this creates randomness in the solution. To address this problem, an adaptive acceleration particle swarm optimization (AAPSO) technique is proposed. To evaluate our proposed method, we employ both face and iris recognition based on AAPSO with SVM (AAPSO-SVM). In the face and iris recognition systems, performance is evaluated using two human face databases, YALE and CASIA, and the UBiris dataset. In this method, we initially perform feature extraction and then recognition on the extracted features. In the recognition process, the extracted features are used for SVM training and testing. During the training and testing, the SVM parameters are optimized with the AAPSO technique, and in AAPSO, the acceleration coefficients are computed using the particle fitness values. The parameters in SVM, which are optimized by AAPSO, perform efficiently for both face and iris recognition. A comparative analysis between our proposed AAPSO-SVM and the PSO-SVM technique is presented. PMID:24790584

DOE Office of Scientific and Technical Information (OSTI.GOV)

Belley, M; Schmidt, M; Knutson, N

Purpose: Physics second-checks for external beam radiation therapy are performed, in-part, to verify that the machine parameters in the Record-and-Verify (R&V) system that will ultimately be sent to the LINAC exactly match the values initially calculated by the Treatment Planning System (TPS). While performing the second-check, a large portion of the physicists’ time is spent navigating and arranging display windows to locate and compare the relevant numerical values (MLC position, collimator rotation, field size, MU, etc.). Here, we describe the development of a software tool that guides the physicist by aggregating and succinctly displaying machine parameter data relevant to themore » physics second-check process. Methods: A data retrieval software tool was developed using Python to aggregate data and generate a list of machine parameters that are commonly verified during the physics second-check process. This software tool imported values from (i) the TPS RT Plan DICOM file and (ii) the MOSAIQ (R&V) Structured Query Language (SQL) database. The machine parameters aggregated for this study included: MLC positions, X&Y jaw positions, collimator rotation, gantry rotation, MU, dose rate, wedges and accessories, cumulative dose, energy, machine name, couch angle, and more. Results: A GUI interface was developed to generate a side-by-side display of the aggregated machine parameter values for each field, and presented to the physicist for direct visual comparison. This software tool was tested for 3D conformal, static IMRT, sliding window IMRT, and VMAT treatment plans. Conclusion: This software tool facilitated the data collection process needed in order for the physicist to conduct a second-check, thus yielding an optimized second-check workflow that was both more user friendly and time-efficient. Utilizing this software tool, the physicist was able to spend less time searching through the TPS PDF plan document and the R&V system and focus the second-check efforts on assessing the patient-specific plan-quality.« less

Laser cutting: industrial relevance, process optimization, and laser safety

NASA Astrophysics Data System (ADS)

Haferkamp, Heinz; Goede, Martin; von Busse, Alexander; Thuerk, Oliver

1998-09-01

Compared to other technological relevant laser machining processes, up to now laser cutting is the application most frequently used. With respect to the large amount of possible fields of application and the variety of different materials that can be machined, this technology has reached a stable position within the world market of material processing. Reachable machining quality for laser beam cutting is influenced by various laser and process parameters. Process integrated quality techniques have to be applied to ensure high-quality products and a cost effective use of the laser manufacturing plant. Therefore, rugged and versatile online process monitoring techniques at an affordable price would be desirable. Methods for the characterization of single plant components (e.g. laser source and optical path) have to be substituted by an omnivalent control system, capable of process data acquisition and analysis as well as the automatic adaptation of machining and laser parameters to changes in process and ambient conditions. At the Laser Zentrum Hannover eV, locally highly resolved thermographic measurements of the temperature distribution within the processing zone using cost effective measuring devices are performed. Characteristic values for cutting quality and plunge control as well as for the optimization of the surface roughness at the cutting edges can be deducted from the spatial distribution of the temperature field and the measured temperature gradients. Main influencing parameters on the temperature characteristic within the cutting zone are the laser beam intensity and pulse duration in pulse operation mode. For continuous operation mode, the temperature distribution is mainly determined by the laser output power related to the cutting velocity. With higher cutting velocities temperatures at the cutting front increase, reaching their maximum at the optimum cutting velocity. Here absorption of the incident laser radiation is drastically increased due to the angle between the normal of the cutting front and the laser beam axis. Beneath process optimization and control further work is focused on the characterization of particulate and gaseous laser generated air contaminants and adequate safety precautions like exhaust and filter systems.

Two-speed phacoemulsification for soft cataracts using optimized parameters and procedure step toolbar with the CENTURION Vision System and Balanced Tip.

PubMed

Davison, James A

2015-01-01

To present a cause of posterior capsule aspiration and a technique using optimized parameters to prevent it from happening when operating soft cataracts. A prospective list of posterior capsule aspiration cases was kept over 4,062 consecutive cases operated with the Alcon CENTURION machine and Balanced Tip. Video analysis of one case of posterior capsule aspiration was accomplished. A surgical technique was developed using empirically derived machine parameters and customized setting-selection procedure step toolbar to reduce the pace of aspiration of soft nuclear quadrants in order to prevent capsule aspiration. Two cases out of 3,238 experienced posterior capsule aspiration before use of the soft quadrant technique. Video analysis showed an attractive vortex effect with capsule aspiration occurring in 1/5 of a second. A soft quadrant removal setting was empirically derived which had a slower pace and seemed more controlled with no capsule aspiration occurring in the subsequent 824 cases. The setting featured simultaneous linear control from zero to preset maximums for: aspiration flow, 20 mL/min; and vacuum, 400 mmHg, with the addition of torsional tip amplitude up to 20% after the fluidic maximums were achieved. A new setting selection procedure step toolbar was created to increase intraoperative flexibility by providing instantaneous shifting between the soft and normal settings. A technique incorporating a reduced pace for soft quadrant acquisition and aspiration can be accomplished through the use of a dedicated setting of integrated machine parameters. Toolbar placement of the procedure button next to the normal setting procedure button provides the opportunity to instantaneously alternate between the two settings. Simultaneous surgeon control over vacuum, aspiration flow, and torsional tip motion may make removal of soft nuclear quadrants more efficient and safer.

ANN Surface Roughness Optimization of AZ61 Magnesium Alloy Finish Turning: Minimum Machining Times at Prime Machining Costs

PubMed Central

Erdakov, Ivan Nikolaevich; Taha, Mohamed~Adel; Soliman, Mahmoud Sayed; El Rayes, Magdy Mostafa

2018-01-01

Magnesium alloys are widely used in aerospace vehicles and modern cars, due to their rapid machinability at high cutting speeds. A novel Edgeworth–Pareto optimization of an artificial neural network (ANN) is presented in this paper for surface roughness (Ra) prediction of one component in computer numerical control (CNC) turning over minimal machining time (Tm) and at prime machining costs (C). An ANN is built in the Matlab programming environment, based on a 4-12-3 multi-layer perceptron (MLP), to predict Ra, Tm, and C, in relation to cutting speed, vc, depth of cut, ap, and feed per revolution, fr. For the first time, a profile of an AZ61 alloy workpiece after finish turning is constructed using an ANN for the range of experimental values vc, ap, and fr. The global minimum length of a three-dimensional estimation vector was defined with the following coordinates: Ra = 0.087 μm, Tm = 0.358 min/cm3, C = $8.2973. Likewise, the corresponding finish-turning parameters were also estimated: cutting speed vc = 250 m/min, cutting depth ap = 1.0 mm, and feed per revolution fr = 0.08 mm/rev. The ANN model achieved a reliable prediction accuracy of ±1.35% for surface roughness. PMID:29772670

Heidelberg retina tomograph measurements of the optic disc and parapapillary retina for detecting glaucoma analyzed by machine learning classifiers.

PubMed

Zangwill, Linda M; Chan, Kwokleung; Bowd, Christopher; Hao, Jicuang; Lee, Te-Won; Weinreb, Robert N; Sejnowski, Terrence J; Goldbaum, Michael H

2004-09-01

To determine whether topographical measurements of the parapapillary region analyzed by machine learning classifiers can detect early to moderate glaucoma better than similarly processed measurements obtained within the disc margin and to improve methods for optimization of machine learning classifier feature selection. One eye of each of 95 patients with early to moderate glaucomatous visual field damage and of each of 135 normal subjects older than 40 years participating in the longitudinal Diagnostic Innovations in Glaucoma Study (DIGS) were included. Heidelberg Retina Tomograph (HRT; Heidelberg Engineering, Dossenheim, Germany) mean height contour was measured in 36 equal sectors, both along the disc margin and in the parapapillary region (at a mean contour line radius of 1.7 mm). Each sector was evaluated individually and in combination with other sectors. Gaussian support vector machine (SVM) learning classifiers were used to interpret HRT sector measurements along the disc margin and in the parapapillary region, to differentiate between eyes with normal and glaucomatous visual fields and to compare the results with global and regional HRT parameter measurements. The area under the receiver operating characteristic (ROC) curve was used to measure diagnostic performance of the HRT parameters and to evaluate the cross-validation strategies and forward selection and backward elimination optimization techniques that were used to generate the reduced feature sets. The area under the ROC curve for mean height contour of the 36 sectors along the disc margin was larger than that for the mean height contour in the parapapillary region (0.97 and 0.85, respectively). Of the 36 individual sectors along the disc margin, those in the inferior region between 240 degrees and 300 degrees, had the largest area under the ROC curve (0.85-0.91). With SVM Gaussian techniques, the regional parameters showed the best ability to discriminate between normal eyes and eyes with glaucomatous visual field damage, followed by the global parameters, mean height contour measures along the disc margin, and mean height contour measures in the parapapillary region. The area under the ROC curve was 0.98, 0.94, 0.93, and 0.85, respectively. Cross-validation and optimization techniques demonstrated that good discrimination (99% of peak area under the ROC curve) can be obtained with a reduced number of HRT parameters. Mean height contour measurements along the disc margin discriminated between normal and glaucomatous eyes better than measurements obtained in the parapapillary region. Copyright Association for Research in Vision and Ophthalmology

Heidelberg Retina Tomograph Measurements of the Optic Disc and Parapapillary Retina for Detecting Glaucoma Analyzed by Machine Learning Classifiers

PubMed Central

Zangwill, Linda M.; Chan, Kwokleung; Bowd, Christopher; Hao, Jicuang; Lee, Te-Won; Weinreb, Robert N.; Sejnowski, Terrence J.; Goldbaum, Michael H.

2010-01-01

Purpose To determine whether topographical measurements of the parapapillary region analyzed by machine learning classifiers can detect early to moderate glaucoma better than similarly processed measurements obtained within the disc margin and to improve methods for optimization of machine learning classifier feature selection. Methods One eye of each of 95 patients with early to moderate glaucomatous visual field damage and of each of 135 normal subjects older than 40 years participating in the longitudinal Diagnostic Innovations in Glaucoma Study (DIGS) were included. Heidelberg Retina Tomograph (HRT; Heidelberg Engineering, Dossenheim, Germany) mean height contour was measured in 36 equal sectors, both along the disc margin and in the parapapillary region (at a mean contour line radius of 1.7 mm). Each sector was evaluated individually and in combination with other sectors. Gaussian support vector machine (SVM) learning classifiers were used to interpret HRT sector measurements along the disc margin and in the parapapillary region, to differentiate between eyes with normal and glaucomatous visual fields and to compare the results with global and regional HRT parameter measurements. The area under the receiver operating characteristic (ROC) curve was used to measure diagnostic performance of the HRT parameters and to evaluate the cross-validation strategies and forward selection and backward elimination optimization techniques that were used to generate the reduced feature sets. Results The area under the ROC curve for mean height contour of the 36 sectors along the disc margin was larger than that for the mean height contour in the parapapillary region (0.97 and 0.85, respectively). Of the 36 individual sectors along the disc margin, those in the inferior region between 240° and 300°, had the largest area under the ROC curve (0.85–0.91). With SVM Gaussian techniques, the regional parameters showed the best ability to discriminate between normal eyes and eyes with glaucomatous visual field damage, followed by the global parameters, mean height contour measures along the disc margin, and mean height contour measures in the parapapillary region. The area under the ROC curve was 0.98, 0.94, 0.93, and 0.85, respectively. Cross-validation and optimization techniques demonstrated that good discrimination (99% of peak area under the ROC curve) can be obtained with a reduced number of HRT parameters. Conclusions Mean height contour measurements along the disc margin discriminated between normal and glaucomatous eyes better than measurements obtained in the parapapillary region. PMID:15326133

Identification of Shearer Cutting Patterns Using Vibration Signals Based on a Least Squares Support Vector Machine with an Improved Fruit Fly Optimization Algorithm

PubMed Central

Si, Lei; Wang, Zhongbin; Liu, Xinhua; Tan, Chao; Liu, Ze; Xu, Jing

2016-01-01

Shearers play an important role in fully mechanized coal mining face and accurately identifying their cutting pattern is very helpful for improving the automation level of shearers and ensuring the safety of coal mining. The least squares support vector machine (LSSVM) has been proven to offer strong potential in prediction and classification issues, particularly by employing an appropriate meta-heuristic algorithm to determine the values of its two parameters. However, these meta-heuristic algorithms have the drawbacks of being hard to understand and reaching the global optimal solution slowly. In this paper, an improved fly optimization algorithm (IFOA) to optimize the parameters of LSSVM was presented and the LSSVM coupled with IFOA (IFOA-LSSVM) was used to identify the shearer cutting pattern. The vibration acceleration signals of five cutting patterns were collected and the special state features were extracted based on the ensemble empirical mode decomposition (EEMD) and the kernel function. Some examples on the IFOA-LSSVM model were further presented and the results were compared with LSSVM, PSO-LSSVM, GA-LSSVM and FOA-LSSVM models in detail. The comparison results indicate that the proposed approach was feasible, efficient and outperformed the others. Finally, an industrial application example at the coal mining face was demonstrated to specify the effect of the proposed system. PMID:26771615

Full-band error control and crack-free surface fabrication techniques for ultra-precision fly cutting of large-aperture KDP crystals

NASA Astrophysics Data System (ADS)

Zhang, F. H.; Wang, S. F.; An, C. H.; Wang, J.; Xu, Q.

2017-06-01

Large-aperture potassium dihydrogen phosphate (KDP) crystals are widely used in the laser path of inertial confinement fusion (ICF) systems. The most common method of manufacturing half-meter KDP crystals is ultra-precision fly cutting. When processing KDP crystals by ultra-precision fly cutting, the dynamic characteristics of the fly cutting machine and fluctuations in the fly cutting environment are translated into surface errors at different spatial frequency bands. These machining errors should be suppressed effectively to guarantee that KDP crystals meet the full-band machining accuracy specified in the evaluation index. In this study, the anisotropic machinability of KDP crystals and the causes of typical surface errors in ultra-precision fly cutting of the material are investigated. The structures of the fly cutting machine and existing processing parameters are optimized to improve the machined surface quality. The findings are theoretically and practically important in the development of high-energy laser systems in China.

Performance study of a data flow architecture

NASA Technical Reports Server (NTRS)

Adams, George

1985-01-01

Teams of scientists studied data flow concepts, static data flow machine architecture, and the VAL language. Each team mapped its application onto the machine and coded it in VAL. The principal findings of the study were: (1) Five of the seven applications used the full power of the target machine. The galactic simulation and multigrid fluid flow teams found that a significantly smaller version of the machine (16 processing elements) would suffice. (2) A number of machine design parameters including processing element (PE) function unit numbers, array memory size and bandwidth, and routing network capability were found to be crucial for optimal machine performance. (3) The study participants readily acquired VAL programming skills. (4) Participants learned that application-based performance evaluation is a sound method of evaluating new computer architectures, even those that are not fully specified. During the course of the study, participants developed models for using computers to solve numerical problems and for evaluating new architectures. These models form the bases for future evaluation studies.

Optimization of Surface Roughness Parameters of Al-6351 Alloy in EDC Process: A Taguchi Coupled Fuzzy Logic Approach

NASA Astrophysics Data System (ADS)

Kar, Siddhartha; Chakraborty, Sujoy; Dey, Vidyut; Ghosh, Subrata Kumar

2017-10-01

This paper investigates the application of Taguchi method with fuzzy logic for multi objective optimization of roughness parameters in electro discharge coating process of Al-6351 alloy with powder metallurgical compacted SiC/Cu tool. A Taguchi L16 orthogonal array was employed to investigate the roughness parameters by varying tool parameters like composition and compaction load and electro discharge machining parameters like pulse-on time and peak current. Crucial roughness parameters like Centre line average roughness, Average maximum height of the profile and Mean spacing of local peaks of the profile were measured on the coated specimen. The signal to noise ratios were fuzzified to optimize the roughness parameters through a single comprehensive output measure (COM). Best COM obtained with lower values of compaction load, pulse-on time and current and 30:70 (SiC:Cu) composition of tool. Analysis of variance is carried out and a significant COM model is observed with peak current yielding highest contribution followed by pulse-on time, compaction load and composition. The deposited layer is characterised by X-Ray Diffraction analysis which confirmed the presence of tool materials on the work piece surface.

Optimization of Machining Parameters of Milling Operation by Application of Semi-synthetic oil based Nano cutting Fluids

NASA Astrophysics Data System (ADS)

Giri Prasad, M. J.; Abhishek Raaj, A. S.; Rishi Kumar, R.; Gladson, Frank; M, Gautham

2016-09-01

The present study is concerned with resolving the problems pertaining to the conventional cutting fluids. Two samples of nano cutting fluids were prepared by dispersing 0.01 vol% of MWCNTs and a mixture of 0.01 vol% of MWCNTs and 0.01 vol% of nano ZnO in the soluble oil. The thermophysical properties such as the kinematic viscosity, density, flash point and the tribological properties of the prepared nano cutting fluid samples were experimentally investigated and were compared with those of plain soluble oil. In addition to this, a milling process was carried by varying the process parameters and by application of different samples of cutting fluids and an attempt was made to determine optimal cutting condition using the Taguchi optimization technique.

Parameters selection in gene selection using Gaussian kernel support vector machines by genetic algorithm.

PubMed

Mao, Yong; Zhou, Xiao-Bo; Pi, Dao-Ying; Sun, You-Xian; Wong, Stephen T C

2005-10-01

In microarray-based cancer classification, gene selection is an important issue owing to the large number of variables and small number of samples as well as its non-linearity. It is difficult to get satisfying results by using conventional linear statistical methods. Recursive feature elimination based on support vector machine (SVM RFE) is an effective algorithm for gene selection and cancer classification, which are integrated into a consistent framework. In this paper, we propose a new method to select parameters of the aforementioned algorithm implemented with Gaussian kernel SVMs as better alternatives to the common practice of selecting the apparently best parameters by using a genetic algorithm to search for a couple of optimal parameter. Fast implementation issues for this method are also discussed for pragmatic reasons. The proposed method was tested on two representative hereditary breast cancer and acute leukaemia datasets. The experimental results indicate that the proposed method performs well in selecting genes and achieves high classification accuracies with these genes.

A Hybrid Short-Term Traffic Flow Prediction Model Based on Singular Spectrum Analysis and Kernel Extreme Learning Machine.

PubMed

Shang, Qiang; Lin, Ciyun; Yang, Zhaosheng; Bing, Qichun; Zhou, Xiyang

2016-01-01

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS). Because of the uncertainty and nonlinearity, short-term traffic flow prediction is a challenging task. In order to improve the accuracy of short-time traffic flow prediction, a hybrid model (SSA-KELM) is proposed based on singular spectrum analysis (SSA) and kernel extreme learning machine (KELM). SSA is used to filter out the noise of traffic flow time series. Then, the filtered traffic flow data is used to train KELM model, the optimal input form of the proposed model is determined by phase space reconstruction, and parameters of the model are optimized by gravitational search algorithm (GSA). Finally, case validation is carried out using the measured data of an expressway in Xiamen, China. And the SSA-KELM model is compared with several well-known prediction models, including support vector machine, extreme learning machine, and single KLEM model. The experimental results demonstrate that performance of the proposed model is superior to that of the comparison models. Apart from accuracy improvement, the proposed model is more robust.

A Hybrid Short-Term Traffic Flow Prediction Model Based on Singular Spectrum Analysis and Kernel Extreme Learning Machine

PubMed Central

Lin, Ciyun; Yang, Zhaosheng; Bing, Qichun; Zhou, Xiyang

2016-01-01

Short-term traffic flow prediction is one of the most important issues in the field of intelligent transport system (ITS). Because of the uncertainty and nonlinearity, short-term traffic flow prediction is a challenging task. In order to improve the accuracy of short-time traffic flow prediction, a hybrid model (SSA-KELM) is proposed based on singular spectrum analysis (SSA) and kernel extreme learning machine (KELM). SSA is used to filter out the noise of traffic flow time series. Then, the filtered traffic flow data is used to train KELM model, the optimal input form of the proposed model is determined by phase space reconstruction, and parameters of the model are optimized by gravitational search algorithm (GSA). Finally, case validation is carried out using the measured data of an expressway in Xiamen, China. And the SSA-KELM model is compared with several well-known prediction models, including support vector machine, extreme learning machine, and single KLEM model. The experimental results demonstrate that performance of the proposed model is superior to that of the comparison models. Apart from accuracy improvement, the proposed model is more robust. PMID:27551829

A Comparison Study of Machine Learning Based Algorithms for Fatigue Crack Growth Calculation.

PubMed

Wang, Hongxun; Zhang, Weifang; Sun, Fuqiang; Zhang, Wei

2017-05-18

The relationships between the fatigue crack growth rate ( d a / d N ) and stress intensity factor range ( Δ K ) are not always linear even in the Paris region. The stress ratio effects on fatigue crack growth rate are diverse in different materials. However, most existing fatigue crack growth models cannot handle these nonlinearities appropriately. The machine learning method provides a flexible approach to the modeling of fatigue crack growth because of its excellent nonlinear approximation and multivariable learning ability. In this paper, a fatigue crack growth calculation method is proposed based on three different machine learning algorithms (MLAs): extreme learning machine (ELM), radial basis function network (RBFN) and genetic algorithms optimized back propagation network (GABP). The MLA based method is validated using testing data of different materials. The three MLAs are compared with each other as well as the classical two-parameter model ( K * approach). The results show that the predictions of MLAs are superior to those of K * approach in accuracy and effectiveness, and the ELM based algorithms show overall the best agreement with the experimental data out of the three MLAs, for its global optimization and extrapolation ability.

Research on torsional vibration modelling and control of printing cylinder based on particle swarm optimization

NASA Astrophysics Data System (ADS)

Wang, Y. M.; Xu, W. C.; Wu, S. Q.; Chai, C. W.; Liu, X.; Wang, S. H.

2018-03-01

The torsional oscillation is the dominant vibration form for the impression cylinder of printing machine (printing cylinder for short), directly restricting the printing speed up and reducing the quality of the prints. In order to reduce torsional vibration, the active control method for the printing cylinder is obtained. Taking the excitation force and moment from the cylinder gap and gripper teeth open & closing cam mechanism as variable parameters, authors establish the dynamic mathematical model of torsional vibration for the printing cylinder. The torsional active control method is based on Particle Swarm Optimization(PSO) algorithm to optimize input parameters for the serve motor. Furthermore, the input torque of the printing cylinder is optimized, and then compared with the numerical simulation results. The conclusions are that torsional vibration active control based on PSO is an availability method to the torsional vibration of printing cylinder.

Feature Selection and Parameters Optimization of SVM Using Particle Swarm Optimization for Fault Classification in Power Distribution Systems.

PubMed

Cho, Ming-Yuan; Hoang, Thi Thom

2017-01-01

Fast and accurate fault classification is essential to power system operations. In this paper, in order to classify electrical faults in radial distribution systems, a particle swarm optimization (PSO) based support vector machine (SVM) classifier has been proposed. The proposed PSO based SVM classifier is able to select appropriate input features and optimize SVM parameters to increase classification accuracy. Further, a time-domain reflectometry (TDR) method with a pseudorandom binary sequence (PRBS) stimulus has been used to generate a dataset for purposes of classification. The proposed technique has been tested on a typical radial distribution network to identify ten different types of faults considering 12 given input features generated by using Simulink software and MATLAB Toolbox. The success rate of the SVM classifier is over 97%, which demonstrates the effectiveness and high efficiency of the developed method.

Application of multi response optimization with grey relational analysis and fuzzy logic method

NASA Astrophysics Data System (ADS)

Winarni, Sri; Wahyu Indratno, Sapto

2018-01-01

Multi-response optimization is an optimization process by considering multiple responses simultaneously. The purpose of this research is to get the optimum point on multi-response optimization process using grey relational analysis and fuzzy logic method. The optimum point is determined from the Fuzzy-GRG (Grey Relational Grade) variable which is the conversion of the Signal to Noise Ratio of the responses involved. The case study used in this research are case optimization of electrical process parameters in electrical disharge machining. It was found that the combination of treatments resulting to optimum MRR and SR was a 70 V gap voltage factor, peak current 9 A and duty factor 0.8.

Model-Based Collaborative Filtering Analysis of Student Response Data: Machine-Learning Item Response Theory

ERIC Educational Resources Information Center

Bergner, Yoav; Droschler, Stefan; Kortemeyer, Gerd; Rayyan, Saif; Seaton, Daniel; Pritchard, David E.

2012-01-01

We apply collaborative filtering (CF) to dichotomously scored student response data (right, wrong, or no interaction), finding optimal parameters for each student and item based on cross-validated prediction accuracy. The approach is naturally suited to comparing different models, both unidimensional and multidimensional in ability, including a…

Shielded cables with optimal braided shields

NASA Astrophysics Data System (ADS)

Homann, E.

1991-01-01

Extensive tests were done in order to determine what factors govern the design of braids with good shielding effectiveness. The results are purely empirical and relate to the geometrical relationships between the braid parameters. The influence of various parameters on the shape of the transfer impedance versus frequency curve were investigated step by step. It was found that the optical coverage had been overestimated in the past. Good shielding effectiveness results not from high optical coverage as such, but from the proper type of coverage, which is a function of the braid angle and the element width. These dependences were measured for the ordinary range of braid angles (20 to 40 degrees). They apply to all plaiting machines and all gages of braid wire. The design rules are largely the same for bright, tinned, silver-plated and even lacquered copper wires. A new type of braid, which has marked advantages over the conventional design, was proposed. With the 'mixed-element' technique, an optimal braid design can be specified on any plaiting machine, for any possible cable diameter, and for any desired angle. This is not possible for the conventional type of braid.

A Comprehensive Understanding of Machine and Material Behaviors During Inertia Friction Welding

NASA Astrophysics Data System (ADS)

Tung, Daniel J.

Inertia Friction Welding (IFW), a critical process to many industries, currently relies on trial-and-error experimentation to optimize process parameters. Although this Edisonian approach is very effective, the high time and dollar costs incurred during process development are the driving force for better design approaches. Thermal-stress finite element modeling has been increasingly used to aid in process development in the literature; however, several fundamental questions on machine and material behaviors remain unanswered. The work presented here aims produce an analytical foundation to significantly reduce the costly physical experimentation currently required to design the inertia welding of production parts. Particularly, the work is centered around the following two major areas. First, machine behavior during IFW, which critically determines deformation and heating, had not been well understood to date. In order to properly characterize the IFW machine behavior, a novel method based on torque measurements was invented to measure machine efficiency, i.e. the ratio of the initial kinetic energy of the flywheel to that contributing to workpiece heating and deformation. The measured efficiency was validated by both simple energy balance calculations and more sophisticated finite element modeling. For the first time, the efficiency dependence on both process parameters (flywheel size, initial rotational velocity, axial load, and surface roughness) and materials (1018 steel, Low Solvus High Refractory LSHR and Waspaloy) was quantified using the torque based measurement method. The effect of process parameters on machine efficiency was analyzed to establish simple-to-use yet powerful equations for selection and optimization of IFW process parameters for making welds; however, design criteria such as geometry and material optimization were not addressed. Second, there had been a lack of understanding of the bond formation during IFW. In the present research, an interrupted welding study was developed utilizing purposefully-designed dissimilar metal couples to investigate bond formation for this specific material combination. The inertia welding process was interrupted at various times as the flywheel velocity decreased. The fraction of areas with intermixed metals was quantified to reveal the bond formation during IFW. The results revealed a relationship between the upset and the fraction of bonded material, which, interestingly, was found to be consistent to that established for roll bonding literature. The relationship is critical to studying the bonding mechanism and surface interactions during IFW. Moreover, it is essential to accurately interpret the modeling results to determine the extent of bonding using the computed strains near the workpiece interface. With this method developed, similar data can now be collected for additional similar and dissimilar material combinations. In summary, in the quest to develop, validate, and execute a modeling framework to study the inertia friction weldability of different alloy systems, particularly Fe- and Ni-base alloys, many new discoveries have been made to enhance the body of knowledge surrounding IFW. The data and trends discussed in this dissertation constitute a physics-based framework to understand the machine and material behaviors during IFW. Such a physics-based framework is essential to significantly reduce the costly trial-and-error experimentation currently required to successfully and consistently perform the inertia welding of production parts.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sivak, David; Crooks, Gavin

A fundamental problem in modern thermodynamics is how a molecular-scale machine performs useful work, while operating away from thermal equilibrium without excessive dissipation. To this end, we derive a friction tensor that induces a Riemannian manifold on the space of thermodynamic states. Within the linear-response regime, this metric structure controls the dissipation of finite-time transformations, and bestows optimal protocols with many useful properties. We discuss the connection to the existing thermodynamic length formalism, and demonstrate the utility of this metric by solving for optimal control parameter protocols in a simple nonequilibrium model.

Global linear-irreversible principle for optimization in finite-time thermodynamics

NASA Astrophysics Data System (ADS)

Johal, Ramandeep S.

2018-03-01

There is intense effort into understanding the universal properties of finite-time models of thermal machines —at optimal performance— such as efficiency at maximum power, coefficient of performance at maximum cooling power, and other such criteria. In this letter, a global principle consistent with linear irreversible thermodynamics is proposed for the whole cycle —without considering details of irreversibilities in the individual steps of the cycle. This helps to express the total duration of the cycle as τ \\propto {\\bar{Q}^2}/{Δ_\\text{tot}S} , where \\bar{Q} models the effective heat transferred through the machine during the cycle, and Δ_ \\text{tot} S is the total entropy generated. By taking \\bar{Q} in the form of simple algebraic means (such as arithmetic and geometric means) over the heats exchanged by the reservoirs, the present approach is able to predict various standard expressions for figures of merit at optimal performance, as well as the bounds respected by them. It simplifies the optimization procedure to a one-parameter optimization, and provides a fresh perspective on the issue of universality at optimal performance, for small difference in reservoir temperatures. As an illustration, we compare the performance of a partially optimized four-step endoreversible cycle with the present approach.

Density-based penalty parameter optimization on C-SVM.

PubMed

Liu, Yun; Lian, Jie; Bartolacci, Michael R; Zeng, Qing-An

2014-01-01

The support vector machine (SVM) is one of the most widely used approaches for data classification and regression. SVM achieves the largest distance between the positive and negative support vectors, which neglects the remote instances away from the SVM interface. In order to avoid a position change of the SVM interface as the result of an error system outlier, C-SVM was implemented to decrease the influences of the system's outliers. Traditional C-SVM holds a uniform parameter C for both positive and negative instances; however, according to the different number proportions and the data distribution, positive and negative instances should be set with different weights for the penalty parameter of the error terms. Therefore, in this paper, we propose density-based penalty parameter optimization of C-SVM. The experiential results indicated that our proposed algorithm has outstanding performance with respect to both precision and recall.

TOPSIS based parametric optimization of laser micro-drilling of TBC coated nickel based superalloy

NASA Astrophysics Data System (ADS)

Parthiban, K.; Duraiselvam, Muthukannan; Manivannan, R.

2018-06-01

The technique for order of preference by similarity ideal solution (TOPSIS) approach was used for optimizing the process parameters of laser micro-drilling of nickel superalloy C263 with Thermal Barrier Coating (TBC). Plasma spraying was used to deposit the TBC and a pico-second Nd:YAG pulsed laser was used to drill the specimens. Drilling angle, laser scan speed and number of passes were considered as input parameters. Based on the machining conditions, Taguchi L8 orthogonal array was used for conducting the experimental runs. The surface roughness and surface crack density (SCD) were considered as the output measures. The surface roughness was measured using 3D White Light Interferometer (WLI) and the crack density was measured using Scanning Electron Microscope (SEM). The optimized result achieved from this approach suggests reduced surface roughness and surface crack density. The holes drilled at an inclination angle of 45°, laser scan speed of 3 mm/s and 400 number of passes found to be optimum. From the Analysis of variance (ANOVA), inclination angle and number of passes were identified as the major influencing parameter. The optimized parameter combination exhibited a 19% improvement in surface finish and 12% reduction in SCD.

Optimal Equilibria and Plasma Parameter Evolutions for the Ignitor Experiment*

NASA Astrophysics Data System (ADS)

Airoldi, A.; Cenacchi, G.; Coppi, B.

2011-10-01

In view of the operation of the Ignitor machine in both the H and the I-regime, optimal equilibrium configurations that can sustain plasma currents Ip up to 10 MA with a double X-point have been identified. In fact, the emergence of the I-regime in double X-point configurations has not been observed experimentally yet. The characteristics of the magnetic equilibrium configurations that can be produced play a crucial role in the performance of the machine. Therefore, particular care has been devoted to the study of plasma equilibria relevant to the main phases of the discharge evolution. A series of simulations to be utilized for the control of the relevant (sub-ignited) plasma parameters has been carried out using the JETTO transport code considering different values of the plasma current and, correspondingly, of the magnetic field. Special attention has been devoted to non-igniting experiments with Ip = 5 MA and BT = 8 T, where BT is the toroidal magnetic field, as they can be performed with much better duty cycles and longer duration than experiments aimed at reaching the most extreme plasma parameters and ignition in particular. The results of the relevant analyses with a discussion of the adopted transport coefficients is presented. * Sponsored in part by ENEA and the U.S. DOE.

Application of Taguchi Method for Analyzing Factors Affecting the Performance of Coated Carbide Tool When Turning FCD700 in Dry Cutting Condition

NASA Astrophysics Data System (ADS)

Ghani, Jaharah A.; Mohd Rodzi, Mohd Nor Azmi; Zaki Nuawi, Mohd; Othman, Kamal; Rahman, Mohd. Nizam Ab.; Haron, Che Hassan Che; Deros, Baba Md

2011-01-01

Machining is one of the most important manufacturing processes in these modern industries especially for finishing an automotive component after the primary manufacturing processes such as casting and forging. In this study the turning parameters of dry cutting environment (without air, normal air and chilled air), various cutting speed, and feed rate are evaluated using a Taguchi optimization methodology. An orthogonal array L27 (313), signal-to-noise (S/N) ratio and analysis of variance (ANOVA) are employed to analyze the effect of these turning parameters on the performance of a coated carbide tool. The results show that the tool life is affected by the cutting speed, feed rate and cutting environment with contribution of 38%, 32% and 27% respectively. Whereas for the surface roughness, the feed rate is significantly controlled the machined surface produced by 77%, followed by the cutting environment of 19%. The cutting speed is found insignificant in controlling the machined surface produced. The study shows that the dry cutting environment factor should be considered in order to produce longer tool life as well as for obtaining a good machined surface.

Study on effect of tool electrodes on surface finish during electrical discharge machining of Nitinol

NASA Astrophysics Data System (ADS)

Sahu, Anshuman Kumar; Chatterjee, Suman; Nayak, Praveen Kumar; Sankar Mahapatra, Siba

2018-03-01

Electrical discharge machining (EDM) is a non-traditional machining process which is widely used in machining of difficult-to-machine materials. EDM process can produce complex and intrinsic shaped component made of difficult-to-machine materials, largely applied in aerospace, biomedical, die and mold making industries. To meet the required applications, the EDMed components need to possess high accuracy and excellent surface finish. In this work, EDM process is performed using Nitinol as work piece material and AlSiMg prepared by selective laser sintering (SLS) as tool electrode along with conventional copper and graphite electrodes. The SLS is a rapid prototyping (RP) method to produce complex metallic parts by additive manufacturing (AM) process. Experiments have been carried out varying different process parameters like open circuit voltage (V), discharge current (Ip), duty cycle (τ), pulse-on-time (Ton) and tool material. The surface roughness parameter like average roughness (Ra), maximum height of the profile (Rt) and average height of the profile (Rz) are measured using surface roughness measuring instrument (Talysurf). To reduce the number of experiments, design of experiment (DOE) approach like Taguchi’s L27 orthogonal array has been chosen. The surface properties of the EDM specimen are optimized by desirability function approach and the best parametric setting is reported for the EDM process. Type of tool happens to be the most significant parameter followed by interaction of tool type and duty cycle, duty cycle, discharge current and voltage. Better surface finish of EDMed specimen can be obtained with low value of voltage (V), discharge current (Ip), duty cycle (τ) and pulse on time (Ton) along with the use of AlSiMg RP electrode.

Comparative study of coated and uncoated tool inserts with dry machining of EN47 steel using Taguchi L9 optimization technique

NASA Astrophysics Data System (ADS)

Vasu, M.; Shivananda, Nayaka H.

2018-04-01

EN47 steel samples are machined on a self-centered lathe using Chemical Vapor Deposition of coated TiCN/Al2O3/TiN and uncoated tungsten carbide tool inserts, with nose radius 0.8mm. Results are compared with each other and optimized using statistical tool. Input (cutting) parameters that are considered in this work are feed rate (f), cutting speed (Vc), and depth of cut (ap), the optimization criteria are based on the Taguchi (L9) orthogonal array. ANOVA method is adopted to evaluate the statistical significance and also percentage contribution for each model. Multiple response characteristics namely cutting force (Fz), tool tip temperature (T) and surface roughness (Ra) are evaluated. The results discovered that coated tool insert (TiCN/Al2O3/TiN) exhibits 1.27 and 1.29 times better than the uncoated tool insert for tool tip temperature and surface roughness respectively. A slight increase in cutting force was observed for coated tools.

Towards a generalized energy prediction model for machine tools

PubMed Central

Bhinge, Raunak; Park, Jinkyoo; Law, Kincho H.; Dornfeld, David A.; Helu, Moneer; Rachuri, Sudarsan

2017-01-01

Energy prediction of machine tools can deliver many advantages to a manufacturing enterprise, ranging from energy-efficient process planning to machine tool monitoring. Physics-based, energy prediction models have been proposed in the past to understand the energy usage pattern of a machine tool. However, uncertainties in both the machine and the operating environment make it difficult to predict the energy consumption of the target machine reliably. Taking advantage of the opportunity to collect extensive, contextual, energy-consumption data, we discuss a data-driven approach to develop an energy prediction model of a machine tool in this paper. First, we present a methodology that can efficiently and effectively collect and process data extracted from a machine tool and its sensors. We then present a data-driven model that can be used to predict the energy consumption of the machine tool for machining a generic part. Specifically, we use Gaussian Process (GP) Regression, a non-parametric machine-learning technique, to develop the prediction model. The energy prediction model is then generalized over multiple process parameters and operations. Finally, we apply this generalized model with a method to assess uncertainty intervals to predict the energy consumed to machine any part using a Mori Seiki NVD1500 machine tool. Furthermore, the same model can be used during process planning to optimize the energy-efficiency of a machining process. PMID:28652687

Towards a generalized energy prediction model for machine tools.

PubMed

Bhinge, Raunak; Park, Jinkyoo; Law, Kincho H; Dornfeld, David A; Helu, Moneer; Rachuri, Sudarsan

2017-04-01

Energy prediction of machine tools can deliver many advantages to a manufacturing enterprise, ranging from energy-efficient process planning to machine tool monitoring. Physics-based, energy prediction models have been proposed in the past to understand the energy usage pattern of a machine tool. However, uncertainties in both the machine and the operating environment make it difficult to predict the energy consumption of the target machine reliably. Taking advantage of the opportunity to collect extensive, contextual, energy-consumption data, we discuss a data-driven approach to develop an energy prediction model of a machine tool in this paper. First, we present a methodology that can efficiently and effectively collect and process data extracted from a machine tool and its sensors. We then present a data-driven model that can be used to predict the energy consumption of the machine tool for machining a generic part. Specifically, we use Gaussian Process (GP) Regression, a non-parametric machine-learning technique, to develop the prediction model. The energy prediction model is then generalized over multiple process parameters and operations. Finally, we apply this generalized model with a method to assess uncertainty intervals to predict the energy consumed to machine any part using a Mori Seiki NVD1500 machine tool. Furthermore, the same model can be used during process planning to optimize the energy-efficiency of a machining process.

Global Detection of Live Virtual Machine Migration Based on Cellular Neural Networks

PubMed Central

Xie, Kang; Yang, Yixian; Zhang, Ling; Jing, Maohua; Xin, Yang; Li, Zhongxian

2014-01-01

In order to meet the demands of operation monitoring of large scale, autoscaling, and heterogeneous virtual resources in the existing cloud computing, a new method of live virtual machine (VM) migration detection algorithm based on the cellular neural networks (CNNs), is presented. Through analyzing the detection process, the parameter relationship of CNN is mapped as an optimization problem, in which improved particle swarm optimization algorithm based on bubble sort is used to solve the problem. Experimental results demonstrate that the proposed method can display the VM migration processing intuitively. Compared with the best fit heuristic algorithm, this approach reduces the processing time, and emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI) implementation allowing the VM migration detection to be performed better. PMID:24959631

Global detection of live virtual machine migration based on cellular neural networks.

PubMed

Xie, Kang; Yang, Yixian; Zhang, Ling; Jing, Maohua; Xin, Yang; Li, Zhongxian

2014-01-01

In order to meet the demands of operation monitoring of large scale, autoscaling, and heterogeneous virtual resources in the existing cloud computing, a new method of live virtual machine (VM) migration detection algorithm based on the cellular neural networks (CNNs), is presented. Through analyzing the detection process, the parameter relationship of CNN is mapped as an optimization problem, in which improved particle swarm optimization algorithm based on bubble sort is used to solve the problem. Experimental results demonstrate that the proposed method can display the VM migration processing intuitively. Compared with the best fit heuristic algorithm, this approach reduces the processing time, and emerging evidence has indicated that this new approach is affordable to parallelism and analog very large scale integration (VLSI) implementation allowing the VM migration detection to be performed better.

Efficacy of Code Optimization on Cache-Based Processors

NASA Technical Reports Server (NTRS)

VanderWijngaart, Rob F.; Saphir, William C.; Chancellor, Marisa K. (Technical Monitor)

1997-01-01

In this paper a number of techniques for improving the cache performance of a representative piece of numerical software is presented. Target machines are popular processors from several vendors: MIPS R5000 (SGI Indy), MIPS R8000 (SGI PowerChallenge), MIPS R10000 (SGI Origin), DEC Alpha EV4 + EV5 (Cray T3D & T3E), IBM RS6000 (SP Wide-node), Intel PentiumPro (Ames' Whitney), Sun UltraSparc (NERSC's NOW). The optimizations all attempt to increase the locality of memory accesses. But they meet with rather varied and often counterintuitive success on the different computing platforms. We conclude that it may be genuinely impossible to obtain portable performance on the current generation of cache-based machines. At the least, it appears that the performance of modern commodity processors cannot be described with parameters defining the cache alone.

Laser beam machining of polycrystalline diamond for cutting tool manufacturing

NASA Astrophysics Data System (ADS)

Wyszyński, Dominik; Ostrowski, Robert; Zwolak, Marek; Bryk, Witold

2017-10-01

The paper concerns application of DPSS Nd: YAG 532nm pulse laser source for machining of polycrystalline WC based diamond inserts (PCD). The goal of the research was to determine optimal laser cutting parameters for cutting tool shaping. Basic criteria to reach the goal was cutting edge quality (minimalization of finishing operations), material removal rate (time and cost efficiency), choice of laser beam characteristics (polarization, power, focused beam diameter). The research was planned and realised and analysed according to design of experiment rules (DOE). The analysis of the cutting edge was prepared with use of Alicona Infinite Focus measurement system.

Tool wear modeling using abductive networks

NASA Astrophysics Data System (ADS)

Masory, Oren

1992-09-01

A tool wear model based on Abductive Networks, which consists of a network of `polynomial' nodes, is described. The model relates the cutting parameters, components of the cutting force, and machining time to flank wear. Thus real time measurements of the cutting force can be used to monitor the machining process. The model is obtained by a training process in which the connectivity between the network's nodes and the polynomial coefficients of each node are determined by optimizing a performance criteria. Actual wear measurements of coated and uncoated carbide inserts were used for training and evaluating the established model.

Classification of toxicity effects of biotransformed hepatic drugs using whale optimized support vector machines.

PubMed

Tharwat, Alaa; Moemen, Yasmine S; Hassanien, Aboul Ella

2017-04-01

Measuring toxicity is an important step in drug development. Nevertheless, the current experimental methods used to estimate the drug toxicity are expensive and time-consuming, indicating that they are not suitable for large-scale evaluation of drug toxicity in the early stage of drug development. Hence, there is a high demand to develop computational models that can predict the drug toxicity risks. In this study, we used a dataset that consists of 553 drugs that biotransformed in liver. The toxic effects were calculated for the current data, namely, mutagenic, tumorigenic, irritant and reproductive effect. Each drug is represented by 31 chemical descriptors (features). The proposed model consists of three phases. In the first phase, the most discriminative subset of features is selected using rough set-based methods to reduce the classification time while improving the classification performance. In the second phase, different sampling methods such as Random Under-Sampling, Random Over-Sampling and Synthetic Minority Oversampling Technique (SMOTE), BorderLine SMOTE and Safe Level SMOTE are used to solve the problem of imbalanced dataset. In the third phase, the Support Vector Machines (SVM) classifier is used to classify an unknown drug into toxic or non-toxic. SVM parameters such as the penalty parameter and kernel parameter have a great impact on the classification accuracy of the model. In this paper, Whale Optimization Algorithm (WOA) has been proposed to optimize the parameters of SVM, so that the classification error can be reduced. The experimental results proved that the proposed model achieved high sensitivity to all toxic effects. Overall, the high sensitivity of the WOA+SVM model indicates that it could be used for the prediction of drug toxicity in the early stage of drug development. Copyright © 2017 Elsevier Inc. All rights reserved.

Study of the Effect of Lubricant Emulsion Percentage and Tool Material on Surface Roughness in Machining of EN-AC 48000 Alloy

NASA Astrophysics Data System (ADS)

Soltani, E.; Shahali, H.; Zarepour, H.

2011-01-01

In this paper, the effect of machining parameters, namely, lubricant emulsion percentage and tool material on surface roughness has been studied in machining process of EN-AC 48000 aluminum alloy. EN-AC 48000 aluminum alloy is an important alloy in industries. Machining of this alloy is of vital importance due to built-up edge and tool wear. A L9 Taguchi standard orthogonal array has been applied as experimental design to investigate the effect of the factors and their interaction. Nine machining tests have been carried out with three random replications resulting in 27 experiments. Three type of cutting tools including coated carbide (CD1810), uncoated carbide (H10), and polycrystalline diamond (CD10) have been used in this research. Emulsion percentage of lubricant is selected at three levels including 3%, 5% and 10%. Statistical analysis has been employed to study the effect of factors and their interactions using ANOVA method. Moreover, the optimal factors level has been achieved through signal to noise ratio (S/N) analysis. Also, a regression model has been provided to predict the surface roughness. Finally, the results of the confirmation tests have been presented to verify the adequacy of the predictive model. In this research, surface quality was improved by 9% using lubricant and statistical optimization method.

ANN Surface Roughness Optimization of AZ61 Magnesium Alloy Finish Turning: Minimum Machining Times at Prime Machining Costs.

PubMed

Abbas, Adel Taha; Pimenov, Danil Yurievich; Erdakov, Ivan Nikolaevich; Taha, Mohamed Adel; Soliman, Mahmoud Sayed; El Rayes, Magdy Mostafa

2018-05-16

Magnesium alloys are widely used in aerospace vehicles and modern cars, due to their rapid machinability at high cutting speeds. A novel Edgeworth⁻Pareto optimization of an artificial neural network (ANN) is presented in this paper for surface roughness ( Ra ) prediction of one component in computer numerical control (CNC) turning over minimal machining time ( T m ) and at prime machining costs ( C ). An ANN is built in the Matlab programming environment, based on a 4-12-3 multi-layer perceptron (MLP), to predict Ra , T m , and C , in relation to cutting speed, v c , depth of cut, a p , and feed per revolution, f r . For the first time, a profile of an AZ61 alloy workpiece after finish turning is constructed using an ANN for the range of experimental values v c , a p , and f r . The global minimum length of a three-dimensional estimation vector was defined with the following coordinates: Ra = 0.087 μm, T m = 0.358 min/cm³, C = $8.2973. Likewise, the corresponding finish-turning parameters were also estimated: cutting speed v c = 250 m/min, cutting depth a p = 1.0 mm, and feed per revolution f r = 0.08 mm/rev. The ANN model achieved a reliable prediction accuracy of ±1.35% for surface roughness.

SVM-RFE based feature selection and Taguchi parameters optimization for multiclass SVM classifier.

PubMed

Huang, Mei-Ling; Hung, Yung-Hsiang; Lee, W M; Li, R K; Jiang, Bo-Ru

2014-01-01

Recently, support vector machine (SVM) has excellent performance on classification and prediction and is widely used on disease diagnosis or medical assistance. However, SVM only functions well on two-group classification problems. This study combines feature selection and SVM recursive feature elimination (SVM-RFE) to investigate the classification accuracy of multiclass problems for Dermatology and Zoo databases. Dermatology dataset contains 33 feature variables, 1 class variable, and 366 testing instances; and the Zoo dataset contains 16 feature variables, 1 class variable, and 101 testing instances. The feature variables in the two datasets were sorted in descending order by explanatory power, and different feature sets were selected by SVM-RFE to explore classification accuracy. Meanwhile, Taguchi method was jointly combined with SVM classifier in order to optimize parameters C and γ to increase classification accuracy for multiclass classification. The experimental results show that the classification accuracy can be more than 95% after SVM-RFE feature selection and Taguchi parameter optimization for Dermatology and Zoo databases.

SVM-RFE Based Feature Selection and Taguchi Parameters Optimization for Multiclass SVM Classifier

PubMed Central

Huang, Mei-Ling; Hung, Yung-Hsiang; Lee, W. M.; Li, R. K.; Jiang, Bo-Ru

2014-01-01

Recently, support vector machine (SVM) has excellent performance on classification and prediction and is widely used on disease diagnosis or medical assistance. However, SVM only functions well on two-group classification problems. This study combines feature selection and SVM recursive feature elimination (SVM-RFE) to investigate the classification accuracy of multiclass problems for Dermatology and Zoo databases. Dermatology dataset contains 33 feature variables, 1 class variable, and 366 testing instances; and the Zoo dataset contains 16 feature variables, 1 class variable, and 101 testing instances. The feature variables in the two datasets were sorted in descending order by explanatory power, and different feature sets were selected by SVM-RFE to explore classification accuracy. Meanwhile, Taguchi method was jointly combined with SVM classifier in order to optimize parameters C and γ to increase classification accuracy for multiclass classification. The experimental results show that the classification accuracy can be more than 95% after SVM-RFE feature selection and Taguchi parameter optimization for Dermatology and Zoo databases. PMID:25295306

Molecular Dynamics Modeling and Simulation of Diamond Cutting of Cerium.

PubMed

Zhang, Junjie; Zheng, Haibing; Shuai, Maobing; Li, Yao; Yang, Yang; Sun, Tao

2017-12-01

The coupling between structural phase transformations and dislocations induces challenges in understanding the deformation behavior of metallic cerium at the nanoscale. In the present work, we elucidate the underlying mechanism of cerium under ultra-precision diamond cutting by means of molecular dynamics modeling and simulations. The molecular dynamics model of diamond cutting of cerium is established by assigning empirical potentials to describe atomic interactions and evaluating properties of two face-centered cubic cerium phases. Subsequent molecular dynamics simulations reveal that dislocation slip dominates the plastic deformation of cerium under the cutting process. In addition, the analysis based on atomic radial distribution functions demonstrates that there are trivial phase transformations from the γ-Ce to the δ-Ce occurred in both machined surface and formed chip. Following investigations on machining parameter dependence reveal the optimal machining conditions for achieving high quality of machined surface of cerium.

Molecular Dynamics Modeling and Simulation of Diamond Cutting of Cerium

NASA Astrophysics Data System (ADS)

Zhang, Junjie; Zheng, Haibing; Shuai, Maobing; Li, Yao; Yang, Yang; Sun, Tao

2017-07-01

The coupling between structural phase transformations and dislocations induces challenges in understanding the deformation behavior of metallic cerium at the nanoscale. In the present work, we elucidate the underlying mechanism of cerium under ultra-precision diamond cutting by means of molecular dynamics modeling and simulations. The molecular dynamics model of diamond cutting of cerium is established by assigning empirical potentials to describe atomic interactions and evaluating properties of two face-centered cubic cerium phases. Subsequent molecular dynamics simulations reveal that dislocation slip dominates the plastic deformation of cerium under the cutting process. In addition, the analysis based on atomic radial distribution functions demonstrates that there are trivial phase transformations from the γ-Ce to the δ-Ce occurred in both machined surface and formed chip. Following investigations on machining parameter dependence reveal the optimal machining conditions for achieving high quality of machined surface of cerium.

Intelligent Hybrid Vehicle Power Control - Part 1: Machine Learning of Optimal Vehicle Power

DTIC Science & Technology

2012-06-30

time window ),[ tWt DT : vave, vmax, vmin, ac, vst and vend, where the first four parameters are, respectively, the average speed, maximum speed...minimum speed and average acceleration, during the time period ),[ tWt DT , vst is the vehicle speed at )( DTWt  , and vend is the vehicle

Deploying response surface methodology (RSM) and glowworm swarm optimization (GSO) in optimizing warpage on a mobile phone cover

NASA Astrophysics Data System (ADS)

Lee, X. N.; Fathullah, M.; Shayfull, Z.; Nasir, S. M.; Hazwan, M. H. M.; Shazzuan, S.

2017-09-01

Plastic injection moulding is a popular manufacturing method not only it is reliable, but also efficient and cost saving. It able to produce plastic part with detailed features and complex geometry. However, defects in injection moulding process degrades the quality and aesthetic of the injection moulded product. The most common defect occur in the process is warpage. Inappropriate process parameter setting of injection moulding machine is one of the reason that leads to the occurrence of warpage. The aims of this study were to improve the quality of injection moulded part by investigating the optimal parameters in minimizing warpage using Response Surface Methodology (RSM) and Glowworm Swarm Optimization (GSO). Subsequent to this, the most significant parameter was identified and recommended parameters setting was compared with the optimized parameter setting using RSM and GSO. In this research, the mobile phone case was selected as case study. The mould temperature, melt temperature, packing pressure, packing time and cooling time were selected as variables whereas warpage in y-direction was selected as responses in this research. The simulation was carried out by using Autodesk Moldflow Insight 2012. In addition, the RSM was performed by using Design Expert 7.0 whereas the GSO was utilized by using MATLAB. The warpage in y direction recommended by RSM were reduced by 70 %. The warpages recommended by GSO were decreased by 61 % in y direction. The resulting warpages under optimal parameter setting by RSM and GSO were validated by simulation in AMI 2012. RSM performed better than GSO in solving warpage issue.

A review on application of nanofluid MQL in machining

NASA Astrophysics Data System (ADS)

Rifat, Mustafa; Rahman, Md. Habibor; Das, Debashish

2017-12-01

Heat generation is an inevitable phenomenon during machining. To eradicate heat oriented detrimental effects like surface burning, tool wear and so on-different types of cooling system are being used. Traditional flood cooling method is the most widely used technique; however the consumption rate of coolant is very high. Moreover, if it is not deposited or recycled properly, it may also cause environmental hazard. Minimum Quantity Lubrication (MQL), on the other hand, sprays lubricant which decreases the frictional force and heat produced during machining. Nanofluid MQL is the incorporation of especially engineered nanoparticles into the lubricant that increases the heat carrying capacity. In this paper, four manufacturing processes (grinding, turning, milling, and drilling) and the effect of using nanofluid MQL in them are studied and summarized. Parameters that are considered in this study are cutting force, surface roughness, machining temperature, tool wear and environmental aspects. It can be observed that using nanofluids in an optimized manner can be beneficial to the machining processes because of their superior characteristics.

Performance evaluation of the croissant production line with reparable machines

NASA Astrophysics Data System (ADS)

Tsarouhas, Panagiotis H.

2015-03-01

In this study, the analytical probability models for an automated serial production system, bufferless that consists of n-machines in series with common transfer mechanism and control system was developed. Both time to failure and time to repair a failure are assumed to follow exponential distribution. Applying those models, the effect of system parameters on system performance in actual croissant production line was studied. The production line consists of six workstations with different numbers of reparable machines in series. Mathematical models of the croissant production line have been developed using Markov process. The strength of this study is in the classification of the whole system in states, representing failures of different machines. Failure and repair data from the actual production environment have been used to estimate reliability and maintainability for each machine, workstation, and the entire line is based on analytical models. The analysis provides a useful insight into the system's behaviour, helps to find design inherent faults and suggests optimal modifications to upgrade the system and improve its performance.

An Efficient Method Coupling Kernel Principal Component Analysis with Adjoint-Based Optimal Control and Its Goal-Oriented Extensions

NASA Astrophysics Data System (ADS)

Thimmisetty, C.; Talbot, C.; Tong, C. H.; Chen, X.

2016-12-01

The representativeness of available data poses a significant fundamental challenge to the quantification of uncertainty in geophysical systems. Furthermore, the successful application of machine learning methods to geophysical problems involving data assimilation is inherently constrained by the extent to which obtainable data represent the problem considered. We show how the adjoint method, coupled with optimization based on methods of machine learning, can facilitate the minimization of an objective function defined on a space of significantly reduced dimension. By considering uncertain parameters as constituting a stochastic process, the Karhunen-Loeve expansion and its nonlinear extensions furnish an optimal basis with respect to which optimization using L-BFGS can be carried out. In particular, we demonstrate that kernel PCA can be coupled with adjoint-based optimal control methods to successfully determine the distribution of material parameter values for problems in the context of channelized deformable media governed by the equations of linear elasticity. Since certain subsets of the original data are characterized by different features, the convergence rate of the method in part depends on, and may be limited by, the observations used to furnish the kernel principal component basis. By determining appropriate weights for realizations of the stochastic random field, then, one may accelerate the convergence of the method. To this end, we present a formulation of Weighted PCA combined with a gradient-based means using automatic differentiation to iteratively re-weight observations concurrent with the determination of an optimal reduced set control variables in the feature space. We demonstrate how improvements in the accuracy and computational efficiency of the weighted linear method can be achieved over existing unweighted kernel methods, and discuss nonlinear extensions of the algorithm.

A study on the performance comparison of metaheuristic algorithms on the learning of neural networks

NASA Astrophysics Data System (ADS)

Lai, Kee Huong; Zainuddin, Zarita; Ong, Pauline

2017-08-01

The learning or training process of neural networks entails the task of finding the most optimal set of parameters, which includes translation vectors, dilation parameter, synaptic weights, and bias terms. Apart from the traditional gradient descent-based methods, metaheuristic methods can also be used for this learning purpose. Since the inception of genetic algorithm half a century ago, the last decade witnessed the explosion of a variety of novel metaheuristic algorithms, such as harmony search algorithm, bat algorithm, and whale optimization algorithm. Despite the proof of the no free lunch theorem in the discipline of optimization, a survey in the literature of machine learning gives contrasting results. Some researchers report that certain metaheuristic algorithms are superior to the others, whereas some others argue that different metaheuristic algorithms give comparable performance. As such, this paper aims to investigate if a certain metaheuristic algorithm will outperform the other algorithms. In this work, three metaheuristic algorithms, namely genetic algorithms, particle swarm optimization, and harmony search algorithm are considered. The algorithms are incorporated in the learning of neural networks and their classification results on the benchmark UCI machine learning data sets are compared. It is found that all three metaheuristic algorithms give similar and comparable performance, as captured in the average overall classification accuracy. The results corroborate the findings reported in the works done by previous researchers. Several recommendations are given, which include the need of statistical analysis to verify the results and further theoretical works to support the obtained empirical results.

Learning Multisensory Integration and Coordinate Transformation via Density Estimation

PubMed Central

Sabes, Philip N.

2013-01-01

Sensory processing in the brain includes three key operations: multisensory integration—the task of combining cues into a single estimate of a common underlying stimulus; coordinate transformations—the change of reference frame for a stimulus (e.g., retinotopic to body-centered) effected through knowledge about an intervening variable (e.g., gaze position); and the incorporation of prior information. Statistically optimal sensory processing requires that each of these operations maintains the correct posterior distribution over the stimulus. Elements of this optimality have been demonstrated in many behavioral contexts in humans and other animals, suggesting that the neural computations are indeed optimal. That the relationships between sensory modalities are complex and plastic further suggests that these computations are learned—but how? We provide a principled answer, by treating the acquisition of these mappings as a case of density estimation, a well-studied problem in machine learning and statistics, in which the distribution of observed data is modeled in terms of a set of fixed parameters and a set of latent variables. In our case, the observed data are unisensory-population activities, the fixed parameters are synaptic connections, and the latent variables are multisensory-population activities. In particular, we train a restricted Boltzmann machine with the biologically plausible contrastive-divergence rule to learn a range of neural computations not previously demonstrated under a single approach: optimal integration; encoding of priors; hierarchical integration of cues; learning when not to integrate; and coordinate transformation. The model makes testable predictions about the nature of multisensory representations. PMID:23637588

Kernel machines for epilepsy diagnosis via EEG signal classification: a comparative study.

PubMed

Lima, Clodoaldo A M; Coelho, André L V

2011-10-01

We carry out a systematic assessment on a suite of kernel-based learning machines while coping with the task of epilepsy diagnosis through automatic electroencephalogram (EEG) signal classification. The kernel machines investigated include the standard support vector machine (SVM), the least squares SVM, the Lagrangian SVM, the smooth SVM, the proximal SVM, and the relevance vector machine. An extensive series of experiments was conducted on publicly available data, whose clinical EEG recordings were obtained from five normal subjects and five epileptic patients. The performance levels delivered by the different kernel machines are contrasted in terms of the criteria of predictive accuracy, sensitivity to the kernel function/parameter value, and sensitivity to the type of features extracted from the signal. For this purpose, 26 values for the kernel parameter (radius) of two well-known kernel functions (namely, Gaussian and exponential radial basis functions) were considered as well as 21 types of features extracted from the EEG signal, including statistical values derived from the discrete wavelet transform, Lyapunov exponents, and combinations thereof. We first quantitatively assess the impact of the choice of the wavelet basis on the quality of the features extracted. Four wavelet basis functions were considered in this study. Then, we provide the average accuracy (i.e., cross-validation error) values delivered by 252 kernel machine configurations; in particular, 40%/35% of the best-calibrated models of the standard and least squares SVMs reached 100% accuracy rate for the two kernel functions considered. Moreover, we show the sensitivity profiles exhibited by a large sample of the configurations whereby one can visually inspect their levels of sensitiveness to the type of feature and to the kernel function/parameter value. Overall, the results evidence that all kernel machines are competitive in terms of accuracy, with the standard and least squares SVMs prevailing more consistently. Moreover, the choice of the kernel function and parameter value as well as the choice of the feature extractor are critical decisions to be taken, albeit the choice of the wavelet family seems not to be so relevant. Also, the statistical values calculated over the Lyapunov exponents were good sources of signal representation, but not as informative as their wavelet counterparts. Finally, a typical sensitivity profile has emerged among all types of machines, involving some regions of stability separated by zones of sharp variation, with some kernel parameter values clearly associated with better accuracy rates (zones of optimality). Copyright © 2011 Elsevier B.V. All rights reserved.

Combatting nonlinear phase noise in coherent optical systems with an optimized decision processor based on machine learning

NASA Astrophysics Data System (ADS)

Wang, Danshi; Zhang, Min; Cai, Zhongle; Cui, Yue; Li, Ze; Han, Huanhuan; Fu, Meixia; Luo, Bin

2016-06-01

An effective machine learning algorithm, the support vector machine (SVM), is presented in the context of a coherent optical transmission system. As a classifier, the SVM can create nonlinear decision boundaries to mitigate the distortions caused by nonlinear phase noise (NLPN). Without any prior information or heuristic assumptions, the SVM can learn and capture the link properties from only a few training data. Compared with the maximum likelihood estimation (MLE) algorithm, a lower bit-error rate (BER) is achieved by the SVM for a given launch power; moreover, the launch power dynamic range (LPDR) is increased by 3.3 dBm for 8 phase-shift keying (8 PSK), 1.2 dBm for QPSK, and 0.3 dBm for BPSK. The maximum transmission distance corresponding to a BER of 1 ×10-3 is increased by 480 km for the case of 8 PSK. The larger launch power range and longer transmission distance improve the tolerance to amplitude and phase noise, which demonstrates the feasibility of the SVM in digital signal processing for M-PSK formats. Meanwhile, in order to apply the SVM method to 16 quadratic amplitude modulation (16 QAM) detection, we propose a parameter optimization scheme. By utilizing a cross-validation and grid-search techniques, the optimal parameters of SVM can be selected, thus leading to the LPDR improvement by 2.8 dBm. Additionally, we demonstrate that the SVM is also effective in combating the laser phase noise combined with the inphase and quadrature (I/Q) modulator imperfections, but the improvement is insignificant for the linear noise and separate I/Q imbalance. The computational complexity of SVM is also discussed. The relatively low complexity makes it possible for SVM to implement the real-time processing.

Impedance learning for robotic contact tasks using natural actor-critic algorithm.

PubMed

Kim, Byungchan; Park, Jooyoung; Park, Shinsuk; Kang, Sungchul

2010-04-01

Compared with their robotic counterparts, humans excel at various tasks by using their ability to adaptively modulate arm impedance parameters. This ability allows us to successfully perform contact tasks even in uncertain environments. This paper considers a learning strategy of motor skill for robotic contact tasks based on a human motor control theory and machine learning schemes. Our robot learning method employs impedance control based on the equilibrium point control theory and reinforcement learning to determine the impedance parameters for contact tasks. A recursive least-square filter-based episodic natural actor-critic algorithm is used to find the optimal impedance parameters. The effectiveness of the proposed method was tested through dynamic simulations of various contact tasks. The simulation results demonstrated that the proposed method optimizes the performance of the contact tasks in uncertain conditions of the environment.

Optimization of Process Parameters of Pulsed Electro Deposition Technique for Nanocrystalline Nickel Coating Using Gray Relational Analysis (GRA)

NASA Astrophysics Data System (ADS)

Venkatesh, C.; Sundara Moorthy, N.; Venkatesan, R.; Aswinprasad, V.

The moving parts of any mechanism and machine parts are always subjected to a significant wear due to the development of friction. It is an utmost important aspect to address the wear problems in present environment. But the complexity goes on increasing to replace the worn out parts if they are very precise. Technology advancement in surface engineering ensures the minimum surface wear with the introduction of polycrystalline nano nickel coating. The enhanced tribological property of the nano nickel coating was achieved by the development of grain size and hardness of the surface. In this study, it has been decided to focus on the optimized parameters of the pulsed electro deposition to develop such a coating. Taguchi’s method coupled gray relational analysis was employed by considering the pulse frequency, average current density and duty cycle as the chief process parameters. The grain size and hardness were considered as responses. Totally, nine experiments were conducted as per L9 design of experiment. Additionally, response graph method has been applied to determine the most significant parameter to influence both the responses. In order to improve the degree of validation, confirmation test and predicted gray grade were carried out with the optimized parameters. It has been observed that there was significant improvement in gray grade for the optimal parameters.

Construction of Pancreatic Cancer Classifier Based on SVM Optimized by Improved FOA

PubMed Central

Ma, Xiaoqi

2015-01-01

A novel method is proposed to establish the pancreatic cancer classifier. Firstly, the concept of quantum and fruit fly optimal algorithm (FOA) are introduced, respectively. Then FOA is improved by quantum coding and quantum operation, and a new smell concentration determination function is defined. Finally, the improved FOA is used to optimize the parameters of support vector machine (SVM) and the classifier is established by optimized SVM. In order to verify the effectiveness of the proposed method, SVM and other classification methods have been chosen as the comparing methods. The experimental results show that the proposed method can improve the classifier performance and cost less time. PMID:26543867

Improved teaching-learning-based and JAYA optimization algorithms for solving flexible flow shop scheduling problems

NASA Astrophysics Data System (ADS)

Buddala, Raviteja; Mahapatra, Siba Sankar

2017-11-01

Flexible flow shop (or a hybrid flow shop) scheduling problem is an extension of classical flow shop scheduling problem. In a simple flow shop configuration, a job having `g' operations is performed on `g' operation centres (stages) with each stage having only one machine. If any stage contains more than one machine for providing alternate processing facility, then the problem becomes a flexible flow shop problem (FFSP). FFSP which contains all the complexities involved in a simple flow shop and parallel machine scheduling problems is a well-known NP-hard (Non-deterministic polynomial time) problem. Owing to high computational complexity involved in solving these problems, it is not always possible to obtain an optimal solution in a reasonable computation time. To obtain near-optimal solutions in a reasonable computation time, a large variety of meta-heuristics have been proposed in the past. However, tuning algorithm-specific parameters for solving FFSP is rather tricky and time consuming. To address this limitation, teaching-learning-based optimization (TLBO) and JAYA algorithm are chosen for the study because these are not only recent meta-heuristics but they do not require tuning of algorithm-specific parameters. Although these algorithms seem to be elegant, they lose solution diversity after few iterations and get trapped at the local optima. To alleviate such drawback, a new local search procedure is proposed in this paper to improve the solution quality. Further, mutation strategy (inspired from genetic algorithm) is incorporated in the basic algorithm to maintain solution diversity in the population. Computational experiments have been conducted on standard benchmark problems to calculate makespan and computational time. It is found that the rate of convergence of TLBO is superior to JAYA. From the results, it is found that TLBO and JAYA outperform many algorithms reported in the literature and can be treated as efficient methods for solving the FFSP.

Using evolutionary computation to optimize an SVM used in detecting buried objects in FLIR imagery

NASA Astrophysics Data System (ADS)

Paino, Alex; Popescu, Mihail; Keller, James M.; Stone, Kevin

2013-06-01

In this paper we describe an approach for optimizing the parameters of a Support Vector Machine (SVM) as part of an algorithm used to detect buried objects in forward looking infrared (FLIR) imagery captured by a camera installed on a moving vehicle. The overall algorithm consists of a spot-finding procedure (to look for potential targets) followed by the extraction of several features from the neighborhood of each spot. The features include local binary pattern (LBP) and histogram of oriented gradients (HOG) as these are good at detecting texture classes. Finally, we project and sum each hit into UTM space along with its confidence value (obtained from the SVM), producing a confidence map for ROC analysis. In this work, we use an Evolutionary Computation Algorithm (ECA) to optimize various parameters involved in the system, such as the combination of features used, parameters on the Canny edge detector, the SVM kernel, and various HOG and LBP parameters. To validate our approach, we compare results obtained from an SVM using parameters obtained through our ECA technique with those previously selected by hand through several iterations of "guess and check".

Learning About Climate and Atmospheric Models Through Machine Learning

NASA Astrophysics Data System (ADS)

Lucas, D. D.

2017-12-01

From the analysis of ensemble variability to improving simulation performance, machine learning algorithms can play a powerful role in understanding the behavior of atmospheric and climate models. To learn about model behavior, we create training and testing data sets through ensemble techniques that sample different model configurations and values of input parameters, and then use supervised machine learning to map the relationships between the inputs and outputs. Following this procedure, we have used support vector machines, random forests, gradient boosting and other methods to investigate a variety of atmospheric and climate model phenomena. We have used machine learning to predict simulation crashes, estimate the probability density function of climate sensitivity, optimize simulations of the Madden Julian oscillation, assess the impacts of weather and emissions uncertainty on atmospheric dispersion, and quantify the effects of model resolution changes on precipitation. This presentation highlights recent examples of our applications of machine learning to improve the understanding of climate and atmospheric models. This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344.

Derivative Free Optimization of Complex Systems with the Use of Statistical Machine Learning Models

DTIC Science & Technology

2015-09-12

AFRL-AFOSR-VA-TR-2015-0278 DERIVATIVE FREE OPTIMIZATION OF COMPLEX SYSTEMS WITH THE USE OF STATISTICAL MACHINE LEARNING MODELS Katya Scheinberg...COMPLEX SYSTEMS WITH THE USE OF STATISTICAL MACHINE LEARNING MODELS 5a.  CONTRACT NUMBER 5b.  GRANT NUMBER FA9550-11-1-0239 5c.  PROGRAM ELEMENT...developed, which has been the focus of our research. 15. SUBJECT TERMS optimization, Derivative-Free Optimization, Statistical Machine Learning 16. SECURITY

Investigation of Carbon Fiber Reinforced Plastics Machining Using 355 nm Picosecond Pulsed Laser

NASA Astrophysics Data System (ADS)

Hu, Jun; Zhu, Dezhi

2018-06-01

Carbon fiber reinforced plastics (CFRP) has been widely used in the aircraft industry and automobile industry owing to its superior properties. In this paper, a Nd:YVO4 picosecond pulsed system emitting at 355 nm has been used for CFRP machining experiments to determine optimum milling conditions. Milling parameters including laser power, milling speed and hatch distance were optimized by using box-behnken design of response surface methodology (RSM). Material removal rate was influenced by laser beam overlap ratio which affects mechanical denudation. The results in heat affected zones (HAZ) and milling quality were discussed through the machined surface observed with scanning electron microscope. A re-focusing technique based on the experiment with different focal planes was proposed and milling mechanism was also analyzed in details.

TEA CO2 laser machining of CFRP composite

NASA Astrophysics Data System (ADS)

Salama, A.; Li, L.; Mativenga, P.; Whitehead, D.

2016-05-01

Carbon fibre-reinforced polymer (CFRP) composites have found wide applications in the aerospace, marine, sports and automotive industries owing to their lightweight and acceptable mechanical properties compared to the commonly used metallic materials. Machining of CFRP composites using lasers can be challenging due to inhomogeneity in the material properties and structures, which can lead to thermal damages during laser processing. In the previous studies, Nd:YAG, diode-pumped solid-state, CO2 (continuous wave), disc and fibre lasers were used in cutting CFRP composites and the control of damages such as the size of heat-affected zones (HAZs) remains a challenge. In this paper, a short-pulsed (8 μs) transversely excited atmospheric pressure CO2 laser was used, for the first time, to machine CFRP composites. The laser has high peak powers (up to 250 kW) and excellent absorption by both the carbon fibre and the epoxy binder. Design of experiment and statistical modelling, based on response surface methodology, was used to understand the interactions between the process parameters such as laser fluence, repetition rate and cutting speed and their effects on the cut quality characteristics including size of HAZ, machining depth and material removal rate (MRR). Based on this study, process parameter optimization was carried out to minimize the HAZ and maximize the MRR. A discussion is given on the potential applications and comparisons to other lasers in machining CFRP.

A study on stimulation of DC high voltage power of LCC series parallel resonant in projectile velocity measurement system

NASA Astrophysics Data System (ADS)

Lu, Dong-dong; Gu, Jin-liang; Luo, Hong-e.; Xia, Yan

2017-10-01

According to specific requirements of the X-ray machine system for measuring velocity of outfield projectile, a DC high voltage power supply system is designed for the high voltage or the smaller current. The system comprises: a series resonant circuit is selected as a full-bridge inverter circuit; a high-frequency zero-current soft switching of a high-voltage power supply is realized by PWM output by STM32; a nanocrystalline alloy transformer is chosen as a high-frequency booster transformer; and the related parameters of an LCC series-parallel resonant are determined according to the preset parameters of the transformer. The concrete method includes: a LCC series parallel resonant circuit and a voltage doubling circuit are stimulated by using MULTISM and MATLAB; selecting an optimal solution and an optimal parameter of all parts after stimulation analysis; and finally verifying the correctness of the parameter by stimulation of the whole system. Through stimulation analysis, the output voltage of the series-parallel resonant circuit gets to 10KV in 28s: then passing through the voltage doubling circuit, the output voltage gets to 120KV in one hour. According to the system, the wave range of the output voltage is so small as to provide the stable X-ray supply for the X-ray machine for measuring velocity of outfield projectile. It is fast in charging and high in efficiency.

Quantification of microscopic surface features of single point diamond turned optics with subsequent chemical polishing

NASA Astrophysics Data System (ADS)

Cardenas, Nelson; Kyrish, Matthew; Taylor, Daniel; Fraelich, Margaret; Lechuga, Oscar; Claytor, Richard; Claytor, Nelson

2015-03-01

Electro-Chemical Polishing is routinely used in the anodizing industry to achieve specular surface finishes of various metals products prior to anodizing. Electro-Chemical polishing functions by leveling the microscopic peaks and valleys of the substrate, thereby increasing specularity and reducing light scattering. The rate of attack is dependent of the physical characteristics (height, depth, and width) of the microscopic structures that constitute the surface finish. To prepare the sample, mechanical polishing such as buffing or grinding is typically required before etching. This type of mechanical polishing produces random microscopic structures at varying depths and widths, thus the electropolishing parameters are determined in an ad hoc basis. Alternatively, single point diamond turning offers excellent repeatability and highly specific control of substrate polishing parameters. While polishing, the diamond tool leaves behind an associated tool mark, which is related to the diamond tool geometry and machining parameters. Machine parameters such as tool cutting depth, speed and step over can be changed in situ, thus providing control of the spatial frequency of the microscopic structures characteristic of the surface topography of the substrate. By combining single point diamond turning with subsequent electro-chemical etching, ultra smooth polishing of both rotationally symmetric and free form mirrors and molds is possible. Additionally, machining parameters can be set to optimize post polishing for increased surface quality and reduced processing times. In this work, we present a study of substrate surface finish based on diamond turning tool mark spatial frequency with subsequent electro-chemical polishing.

Machine Learning Techniques for Global Sensitivity Analysis in Climate Models

NASA Astrophysics Data System (ADS)

Safta, C.; Sargsyan, K.; Ricciuto, D. M.

2017-12-01

Climate models studies are not only challenged by the compute intensive nature of these models but also by the high-dimensionality of the input parameter space. In our previous work with the land model components (Sargsyan et al., 2014) we identified subsets of 10 to 20 parameters relevant for each QoI via Bayesian compressive sensing and variance-based decomposition. Nevertheless the algorithms were challenged by the nonlinear input-output dependencies for some of the relevant QoIs. In this work we will explore a combination of techniques to extract relevant parameters for each QoI and subsequently construct surrogate models with quantified uncertainty necessary to future developments, e.g. model calibration and prediction studies. In the first step, we will compare the skill of machine-learning models (e.g. neural networks, support vector machine) to identify the optimal number of classes in selected QoIs and construct robust multi-class classifiers that will partition the parameter space in regions with smooth input-output dependencies. These classifiers will be coupled with techniques aimed at building sparse and/or low-rank surrogate models tailored to each class. Specifically we will explore and compare sparse learning techniques with low-rank tensor decompositions. These models will be used to identify parameters that are important for each QoI. Surrogate accuracy requirements are higher for subsequent model calibration studies and we will ascertain the performance of this workflow for multi-site ALM simulation ensembles.

Gradient-based adaptation of general gaussian kernels.

PubMed

Glasmachers, Tobias; Igel, Christian

2005-10-01

Gradient-based optimizing of gaussian kernel functions is considered. The gradient for the adaptation of scaling and rotation of the input space is computed to achieve invariance against linear transformations. This is done by using the exponential map as a parameterization of the kernel parameter manifold. By restricting the optimization to a constant trace subspace, the kernel size can be controlled. This is, for example, useful to prevent overfitting when minimizing radius-margin generalization performance measures. The concepts are demonstrated by training hard margin support vector machines on toy data.

Optimizing taxonomic classification of marker-gene amplicon sequences with QIIME 2's q2-feature-classifier plugin.

PubMed

Bokulich, Nicholas A; Kaehler, Benjamin D; Rideout, Jai Ram; Dillon, Matthew; Bolyen, Evan; Knight, Rob; Huttley, Gavin A; Gregory Caporaso, J

2018-05-17

Taxonomic classification of marker-gene sequences is an important step in microbiome analysis. We present q2-feature-classifier ( https://github.com/qiime2/q2-feature-classifier ), a QIIME 2 plugin containing several novel machine-learning and alignment-based methods for taxonomy classification. We evaluated and optimized several commonly used classification methods implemented in QIIME 1 (RDP, BLAST, UCLUST, and SortMeRNA) and several new methods implemented in QIIME 2 (a scikit-learn naive Bayes machine-learning classifier, and alignment-based taxonomy consensus methods based on VSEARCH, and BLAST+) for classification of bacterial 16S rRNA and fungal ITS marker-gene amplicon sequence data. The naive-Bayes, BLAST+-based, and VSEARCH-based classifiers implemented in QIIME 2 meet or exceed the species-level accuracy of other commonly used methods designed for classification of marker gene sequences that were evaluated in this work. These evaluations, based on 19 mock communities and error-free sequence simulations, including classification of simulated "novel" marker-gene sequences, are available in our extensible benchmarking framework, tax-credit ( https://github.com/caporaso-lab/tax-credit-data ). Our results illustrate the importance of parameter tuning for optimizing classifier performance, and we make recommendations regarding parameter choices for these classifiers under a range of standard operating conditions. q2-feature-classifier and tax-credit are both free, open-source, BSD-licensed packages available on GitHub.

Breast Cancer Recognition Using a Novel Hybrid Intelligent Method

PubMed Central

Addeh, Jalil; Ebrahimzadeh, Ata

2012-01-01

Breast cancer is the second largest cause of cancer deaths among women. At the same time, it is also among the most curable cancer types if it can be diagnosed early. This paper presents a novel hybrid intelligent method for recognition of breast cancer tumors. The proposed method includes three main modules: the feature extraction module, the classifier module, and the optimization module. In the feature extraction module, fuzzy features are proposed as the efficient characteristic of the patterns. In the classifier module, because of the promising generalization capability of support vector machines (SVM), a SVM-based classifier is proposed. In support vector machine training, the hyperparameters have very important roles for its recognition accuracy. Therefore, in the optimization module, the bees algorithm (BA) is proposed for selecting appropriate parameters of the classifier. The proposed system is tested on Wisconsin Breast Cancer database and simulation results show that the recommended system has a high accuracy. PMID:23626945

Two-speed phacoemulsification for soft cataracts using optimized parameters and procedure step toolbar with the CENTURION Vision System and Balanced Tip

PubMed Central

Davison, James A

2015-01-01

Purpose To present a cause of posterior capsule aspiration and a technique using optimized parameters to prevent it from happening when operating soft cataracts. Patients and methods A prospective list of posterior capsule aspiration cases was kept over 4,062 consecutive cases operated with the Alcon CENTURION machine and Balanced Tip. Video analysis of one case of posterior capsule aspiration was accomplished. A surgical technique was developed using empirically derived machine parameters and customized setting-selection procedure step toolbar to reduce the pace of aspiration of soft nuclear quadrants in order to prevent capsule aspiration. Results Two cases out of 3,238 experienced posterior capsule aspiration before use of the soft quadrant technique. Video analysis showed an attractive vortex effect with capsule aspiration occurring in 1/5 of a second. A soft quadrant removal setting was empirically derived which had a slower pace and seemed more controlled with no capsule aspiration occurring in the subsequent 824 cases. The setting featured simultaneous linear control from zero to preset maximums for: aspiration flow, 20 mL/min; and vacuum, 400 mmHg, with the addition of torsional tip amplitude up to 20% after the fluidic maximums were achieved. A new setting selection procedure step toolbar was created to increase intraoperative flexibility by providing instantaneous shifting between the soft and normal settings. Conclusion A technique incorporating a reduced pace for soft quadrant acquisition and aspiration can be accomplished through the use of a dedicated setting of integrated machine parameters. Toolbar placement of the procedure button next to the normal setting procedure button provides the opportunity to instantaneously alternate between the two settings. Simultaneous surgeon control over vacuum, aspiration flow, and torsional tip motion may make removal of soft nuclear quadrants more efficient and safer. PMID:26355695

The influence of negative training set size on machine learning-based virtual screening.

PubMed

Kurczab, Rafał; Smusz, Sabina; Bojarski, Andrzej J

2014-01-01

The paper presents a thorough analysis of the influence of the number of negative training examples on the performance of machine learning methods. The impact of this rather neglected aspect of machine learning methods application was examined for sets containing a fixed number of positive and a varying number of negative examples randomly selected from the ZINC database. An increase in the ratio of positive to negative training instances was found to greatly influence most of the investigated evaluating parameters of ML methods in simulated virtual screening experiments. In a majority of cases, substantial increases in precision and MCC were observed in conjunction with some decreases in hit recall. The analysis of dynamics of those variations let us recommend an optimal composition of training data. The study was performed on several protein targets, 5 machine learning algorithms (SMO, Naïve Bayes, Ibk, J48 and Random Forest) and 2 types of molecular fingerprints (MACCS and CDK FP). The most effective classification was provided by the combination of CDK FP with SMO or Random Forest algorithms. The Naïve Bayes models appeared to be hardly sensitive to changes in the number of negative instances in the training set. In conclusion, the ratio of positive to negative training instances should be taken into account during the preparation of machine learning experiments, as it might significantly influence the performance of particular classifier. What is more, the optimization of negative training set size can be applied as a boosting-like approach in machine learning-based virtual screening.

The influence of negative training set size on machine learning-based virtual screening

PubMed Central

2014-01-01

Background The paper presents a thorough analysis of the influence of the number of negative training examples on the performance of machine learning methods. Results The impact of this rather neglected aspect of machine learning methods application was examined for sets containing a fixed number of positive and a varying number of negative examples randomly selected from the ZINC database. An increase in the ratio of positive to negative training instances was found to greatly influence most of the investigated evaluating parameters of ML methods in simulated virtual screening experiments. In a majority of cases, substantial increases in precision and MCC were observed in conjunction with some decreases in hit recall. The analysis of dynamics of those variations let us recommend an optimal composition of training data. The study was performed on several protein targets, 5 machine learning algorithms (SMO, Naïve Bayes, Ibk, J48 and Random Forest) and 2 types of molecular fingerprints (MACCS and CDK FP). The most effective classification was provided by the combination of CDK FP with SMO or Random Forest algorithms. The Naïve Bayes models appeared to be hardly sensitive to changes in the number of negative instances in the training set. Conclusions In conclusion, the ratio of positive to negative training instances should be taken into account during the preparation of machine learning experiments, as it might significantly influence the performance of particular classifier. What is more, the optimization of negative training set size can be applied as a boosting-like approach in machine learning-based virtual screening. PMID:24976867

Deriving global parameter estimates for the Noah land surface model using FLUXNET and machine learning

NASA Astrophysics Data System (ADS)

Chaney, Nathaniel W.; Herman, Jonathan D.; Ek, Michael B.; Wood, Eric F.

2016-11-01

With their origins in numerical weather prediction and climate modeling, land surface models aim to accurately partition the surface energy balance. An overlooked challenge in these schemes is the role of model parameter uncertainty, particularly at unmonitored sites. This study provides global parameter estimates for the Noah land surface model using 85 eddy covariance sites in the global FLUXNET network. The at-site parameters are first calibrated using a Latin Hypercube-based ensemble of the most sensitive parameters, determined by the Sobol method, to be the minimum stomatal resistance (rs,min), the Zilitinkevich empirical constant (Czil), and the bare soil evaporation exponent (fxexp). Calibration leads to an increase in the mean Kling-Gupta Efficiency performance metric from 0.54 to 0.71. These calibrated parameter sets are then related to local environmental characteristics using the Extra-Trees machine learning algorithm. The fitted Extra-Trees model is used to map the optimal parameter sets over the globe at a 5 km spatial resolution. The leave-one-out cross validation of the mapped parameters using the Noah land surface model suggests that there is the potential to skillfully relate calibrated model parameter sets to local environmental characteristics. The results demonstrate the potential to use FLUXNET to tune the parameterizations of surface fluxes in land surface models and to provide improved parameter estimates over the globe.

An improved chaotic fruit fly optimization based on a mutation strategy for simultaneous feature selection and parameter optimization for SVM and its applications.

PubMed

Ye, Fei; Lou, Xin Yuan; Sun, Lin Fu

2017-01-01

This paper proposes a new support vector machine (SVM) optimization scheme based on an improved chaotic fly optimization algorithm (FOA) with a mutation strategy to simultaneously perform parameter setting turning for the SVM and feature selection. In the improved FOA, the chaotic particle initializes the fruit fly swarm location and replaces the expression of distance for the fruit fly to find the food source. However, the proposed mutation strategy uses two distinct generative mechanisms for new food sources at the osphresis phase, allowing the algorithm procedure to search for the optimal solution in both the whole solution space and within the local solution space containing the fruit fly swarm location. In an evaluation based on a group of ten benchmark problems, the proposed algorithm's performance is compared with that of other well-known algorithms, and the results support the superiority of the proposed algorithm. Moreover, this algorithm is successfully applied in a SVM to perform both parameter setting turning for the SVM and feature selection to solve real-world classification problems. This method is called chaotic fruit fly optimization algorithm (CIFOA)-SVM and has been shown to be a more robust and effective optimization method than other well-known methods, particularly in terms of solving the medical diagnosis problem and the credit card problem.

An improved chaotic fruit fly optimization based on a mutation strategy for simultaneous feature selection and parameter optimization for SVM and its applications

PubMed Central

Lou, Xin Yuan; Sun, Lin Fu

2017-01-01

This paper proposes a new support vector machine (SVM) optimization scheme based on an improved chaotic fly optimization algorithm (FOA) with a mutation strategy to simultaneously perform parameter setting turning for the SVM and feature selection. In the improved FOA, the chaotic particle initializes the fruit fly swarm location and replaces the expression of distance for the fruit fly to find the food source. However, the proposed mutation strategy uses two distinct generative mechanisms for new food sources at the osphresis phase, allowing the algorithm procedure to search for the optimal solution in both the whole solution space and within the local solution space containing the fruit fly swarm location. In an evaluation based on a group of ten benchmark problems, the proposed algorithm’s performance is compared with that of other well-known algorithms, and the results support the superiority of the proposed algorithm. Moreover, this algorithm is successfully applied in a SVM to perform both parameter setting turning for the SVM and feature selection to solve real-world classification problems. This method is called chaotic fruit fly optimization algorithm (CIFOA)-SVM and has been shown to be a more robust and effective optimization method than other well-known methods, particularly in terms of solving the medical diagnosis problem and the credit card problem. PMID:28369096

Contributions a la caracterisation et a l'amelioration de l'usinabilite de pieces d'acier elaborees par metallurgie des poudres

NASA Astrophysics Data System (ADS)

Boilard, Patrick

Even though powder metallurgy (P/M) is a near net shape process, a large number of parts still require one or more machining operations during the course of their elaboration and/or their finishing. The main objectives of the work presented in this thesis are centered on the elaboration of blends with enhanced machinability, as well as helping with the definition and in the characterization of the machinability of P/M parts. Enhancing machinability can be done in various ways, through the use of machinability additives and by decreasing the amount of porosity of the parts. These different ways of enhancing machinability have been investigated thoroughly, by systematically planning and preparing series of samples in order to obtain valid and repeatable results leading to meaningful conclusions relevant to the P/M domain. Results obtained during the course of the work are divided into three main chapters: (1) the effect of machining parameters on machinability, (2) the effect of additives on machinability, and (3) the development and the characterization of high density parts obtained by liquid phase sintering. Regarding the effect of machining parameters on machinability, studies were performed on parameters such as rotating speed, feed, tool position and diameter of the tool. Optimal cutting parameters are found for drilling operations performed on a standard FC-0208 blend, for different machinability criteria. Moreover, study of material removal rates shows the sensitivity of the machinability criteria for different machining parameters and indicates that thrust force is more regular than tool wear and slope of the drillability curve in the characterization of machinability. The chapter discussing the effect of various additives on machinability reveals many interesting results. First, work carried out on MoS2 additions reveals the dissociation of this additive and the creation of metallic sulphides (namely CuxS sulphides) when copper is present. Results also show that it is possible to reduce the amount of MoS2 in the blend so as to lower the dimensional change and the cost (blend Mo8A), while enhancing machinability and keeping hardness values within the same range (70 HRB). Second, adding enstatite (MgO·SiO2) permits the observation of the mechanisms occurring with the use of this additive. It is found that the stability of enstatite limits the diffusion of graphite during sintering, leading to the presence of free graphite in the pores, thus enhancing machinability. Furthermore, a lower amount of graphite in the matrix leads to a lower hardness, which is also beneficial to machinability. It is also found that the presence of copper enhances the diffusion of graphite, through the formation of a liquid phase during sintering. With the objective of improving machinability by reaching higher densities, blends were developed for densification through liquid phase sintering. High density samples are obtained (>7.5 g/cm3) for blends prepared with Fe-C-P constituents, namely with 0.5%P and 2.4%C. By systematically studying the effect of different parameters, the importance of the chemical composition (mainly the carbon content) and the importance of the sintering cycle (particularly the cooling rate) are demonstrated. Moreover, various heat treatments studied illustrate the different microstructures achievable for this system, showing various amounts of cementite, pearlite and free graphite. Although the machinability is limited for samples containing large amounts of cementite, it can be greatly improved with very slow cooling, leading to graphitization of the carbon in presence of phosphorus. Adequate control of the sintering cycle on samples made from FGS1625 powder leads to the obtention of high density (≥7.0 g/cm 3) microstructures containing various amounts of pearlite, ferrite and free graphite. Obtaining ferritic microstructures with free graphite designed for very high machinability (tool wear <1.0%) or fine pearlitic microstructures with excellent mechanical properties (transverse rupture strength >1600 MPa) is therefore possible. These results show that improvement of machinability through higher densities is limited by microstructure. Indeed, for the studied samples, microstructure is dominant in the determination of machinability, far more important than density, judging by the influence of cementite or of the volume fraction of free graphite on machinability for example. (Abstract shortened by UMI.)

Programming and Tuning a Quantum Annealing Device to Solve Real World Problems

NASA Astrophysics Data System (ADS)

Perdomo-Ortiz, Alejandro; O'Gorman, Bryan; Fluegemann, Joseph; Smelyanskiy, Vadim

2015-03-01

Solving real-world applications with quantum algorithms requires overcoming several challenges, ranging from translating the computational problem at hand to the quantum-machine language to tuning parameters of the quantum algorithm that have a significant impact on the performance of the device. In this talk, we discuss these challenges, strategies developed to enhance performance, and also a more efficient implementation of several applications. Although we will focus on applications of interest to NASA's Quantum Artificial Intelligence Laboratory, the methods and concepts presented here apply to a broader family of hard discrete optimization problems, including those that occur in many machine-learning algorithms.

Reliability Study of Solder Paste Alloy for the Improvement of Solder Joint at Surface Mount Fine-Pitch Components.

PubMed

Rahman, Mohd Nizam Ab; Zubir, Noor Suhana Mohd; Leuveano, Raden Achmad Chairdino; Ghani, Jaharah A; Mahmood, Wan Mohd Faizal Wan

2014-12-02

The significant increase in metal costs has forced the electronics industry to provide new materials and methods to reduce costs, while maintaining customers' high-quality expectations. This paper considers the problem of most electronic industries in reducing costly materials, by introducing a solder paste with alloy composition tin 98.3%, silver 0.3%, and copper 0.7%, used for the construction of the surface mount fine-pitch component on a Printing Wiring Board (PWB). The reliability of the solder joint between electronic components and PWB is evaluated through the dynamic characteristic test, thermal shock test, and Taguchi method after the printing process. After experimenting with the dynamic characteristic test and thermal shock test with 20 boards, the solder paste was still able to provide a high-quality solder joint. In particular, the Taguchi method is used to determine the optimal control parameters and noise factors of the Solder Printer (SP) machine, that affects solder volume and solder height. The control parameters include table separation distance, squeegee speed, squeegee pressure, and table speed of the SP machine. The result shows that the most significant parameter for the solder volume is squeegee pressure (2.0 mm), and the solder height is the table speed of the SP machine (2.5 mm/s).

Reliability Study of Solder Paste Alloy for the Improvement of Solder Joint at Surface Mount Fine-Pitch Components

PubMed Central

Rahman, Mohd Nizam Ab.; Zubir, Noor Suhana Mohd; Leuveano, Raden Achmad Chairdino; Ghani, Jaharah A.; Mahmood, Wan Mohd Faizal Wan

2014-01-01

The significant increase in metal costs has forced the electronics industry to provide new materials and methods to reduce costs, while maintaining customers’ high-quality expectations. This paper considers the problem of most electronic industries in reducing costly materials, by introducing a solder paste with alloy composition tin 98.3%, silver 0.3%, and copper 0.7%, used for the construction of the surface mount fine-pitch component on a Printing Wiring Board (PWB). The reliability of the solder joint between electronic components and PWB is evaluated through the dynamic characteristic test, thermal shock test, and Taguchi method after the printing process. After experimenting with the dynamic characteristic test and thermal shock test with 20 boards, the solder paste was still able to provide a high-quality solder joint. In particular, the Taguchi method is used to determine the optimal control parameters and noise factors of the Solder Printer (SP) machine, that affects solder volume and solder height. The control parameters include table separation distance, squeegee speed, squeegee pressure, and table speed of the SP machine. The result shows that the most significant parameter for the solder volume is squeegee pressure (2.0 mm), and the solder height is the table speed of the SP machine (2.5 mm/s). PMID:28788270

Optimisation Of Cutting Parameters Of Composite Material Laser Cutting Process By Taguchi Method

NASA Astrophysics Data System (ADS)

Lokesh, S.; Niresh, J.; Neelakrishnan, S.; Rahul, S. P. Deepak

2018-03-01

The aim of this work is to develop a laser cutting process model that can predict the relationship between the process input parameters and resultant surface roughness, kerf width characteristics. The research conduct is based on the Design of Experiment (DOE) analysis. Response Surface Methodology (RSM) is used in this work. It is one of the most practical and most effective techniques to develop a process model. Even though RSM has been used for the optimization of the laser process, this research investigates laser cutting of materials like Composite wood (veneer)to be best circumstances of laser cutting using RSM process. The input parameters evaluated are focal length, power supply and cutting speed, the output responses being kerf width, surface roughness, temperature. To efficiently optimize and customize the kerf width and surface roughness characteristics, a machine laser cutting process model using Taguchi L9 orthogonal methodology was proposed.

[Application of optimized parameters SVM based on photoacoustic spectroscopy method in fault diagnosis of power transformer].

PubMed

Zhang, Yu-xin; Cheng, Zhi-feng; Xu, Zheng-ping; Bai, Jing

2015-01-01

In order to solve the problems such as complex operation, consumption for the carrier gas and long test period in traditional power transformer fault diagnosis approach based on dissolved gas analysis (DGA), this paper proposes a new method which is detecting 5 types of characteristic gas content in transformer oil such as CH4, C2H2, C2H4, C2H6 and H2 based on photoacoustic Spectroscopy and C2H2/C2H4, CH4/H2, C2H4/C2H6 three-ratios data are calculated. The support vector machine model was constructed using cross validation method under five support vector machine functions and four kernel functions, heuristic algorithms were used in parameter optimization for penalty factor c and g, which to establish the best SVM model for the highest fault diagnosis accuracy and the fast computing speed. Particles swarm optimization and genetic algorithm two types of heuristic algorithms were comparative studied in this paper for accuracy and speed in optimization. The simulation result shows that SVM model composed of C-SVC, RBF kernel functions and genetic algorithm obtain 97. 5% accuracy in test sample set and 98. 333 3% accuracy in train sample set, and genetic algorithm was about two times faster than particles swarm optimization in computing speed. The methods described in this paper has many advantages such as simple operation, non-contact measurement, no consumption for the carrier gas, long test period, high stability and sensitivity, the result shows that the methods described in this paper can instead of the traditional transformer fault diagnosis by gas chromatography and meets the actual project needs in transformer fault diagnosis.

Integrated optimization of location assignment and sequencing in multi-shuttle automated storage and retrieval systems under modified 2n-command cycle pattern

NASA Astrophysics Data System (ADS)

Yang, Peng; Peng, Yongfei; Ye, Bin; Miao, Lixin

2017-09-01

This article explores the integrated optimization problem of location assignment and sequencing in multi-shuttle automated storage/retrieval systems under the modified 2n-command cycle pattern. The decision of storage and retrieval (S/R) location assignment and S/R request sequencing are jointly considered. An integer quadratic programming model is formulated to describe this integrated optimization problem. The optimal travel cycles for multi-shuttle S/R machines can be obtained to process S/R requests in the storage and retrieval request order lists by solving the model. The small-sized instances are optimally solved using CPLEX. For large-sized problems, two tabu search algorithms are proposed, in which the first come, first served and nearest neighbour are used to generate initial solutions. Various numerical experiments are conducted to examine the heuristics' performance and the sensitivity of algorithm parameters. Furthermore, the experimental results are analysed from the viewpoint of practical application, and a parameter list for applying the proposed heuristics is recommended under different real-life scenarios.

Hybrid approach of selecting hyperparameters of support vector machine for regression.

PubMed

Jeng, Jin-Tsong

2006-06-01

To select the hyperparameters of the support vector machine for regression (SVR), a hybrid approach is proposed to determine the kernel parameter of the Gaussian kernel function and the epsilon value of Vapnik's epsilon-insensitive loss function. The proposed hybrid approach includes a competitive agglomeration (CA) clustering algorithm and a repeated SVR (RSVR) approach. Since the CA clustering algorithm is used to find the nearly "optimal" number of clusters and the centers of clusters in the clustering process, the CA clustering algorithm is applied to select the Gaussian kernel parameter. Additionally, an RSVR approach that relies on the standard deviation of a training error is proposed to obtain an epsilon in the loss function. Finally, two functions, one real data set (i.e., a time series of quarterly unemployment rate for West Germany) and an identification of nonlinear plant are used to verify the usefulness of the hybrid approach.

Mathematical model of an air-filled alpha stirling refrigerator

NASA Astrophysics Data System (ADS)

McFarlane, Patrick; Semperlotti, Fabio; Sen, Mihir

2013-10-01

This work develops a mathematical model for an alpha Stirling refrigerator with air as the working fluid and will be useful in optimizing the mechanical design of these machines. Two pistons cyclically compress and expand air while moving sinusoidally in separate chambers connected by a regenerator, thus creating a temperature difference across the system. A complete non-linear mathematical model of the machine, including air thermodynamics, and heat transfer from the walls, as well as heat transfer and fluid resistance in the regenerator, is developed. Non-dimensional groups are derived, and the mathematical model is numerically solved. The heat transfer and work are found for both chambers, and the coefficient of performance of each chamber is calculated. Important design parameters are varied and their effect on refrigerator performance determined. This sensitivity analysis, which shows what the significant parameters are, is a useful tool for the design of practical Stirling refrigeration systems.

Real time PI-backstepping induction machine drive with efficiency optimization.

PubMed

Farhani, Fethi; Ben Regaya, Chiheb; Zaafouri, Abderrahmen; Chaari, Abdelkader

2017-09-01

This paper describes a robust and efficient speed control of a three phase induction machine (IM) subjected to load disturbances. First, a Multiple-Input Multiple-Output (MIMO) PI-Backstepping controller is proposed for a robust and highly accurate tracking of the mechanical speed and rotor flux. Asymptotic stability of the control scheme is proven by Lyapunov Stability Theory. Second, an active online optimization algorithm is used to optimize the efficiency of the drive system. The efficiency improvement approach consists of adjusting the rotor flux with respect to the load torque in order to minimize total losses in the IM. A dSPACE DS1104 R&D board is used to implement the proposed solution. The experimental results released on 3kW squirrel cage IM, show that the reference speed as well as the rotor flux are rapidly achieved with a fast transient response and without overshoot. A good load disturbances rejection response and IM parameters variation are fairly handled. The improvement of drive system efficiency reaches up to 180% at light load. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

Optimizing friction stir weld parameters of aluminum and copper using conventional milling machine

NASA Astrophysics Data System (ADS)

Manisegaran, Lohappriya V.; Ahmad, Nurainaa Ayuni; Nazri, Nurnadhirah; Noor, Amirul Syafiq Mohd; Ramachandran, Vignesh; Ismail, Muhammad Tarmizizulfika; Ahmad, Ku Zarina Ku; Daruis, Dian Darina Indah

2018-05-01

The joining of two of any particular materials through friction stir welding (FSW) are done by a rotating tool and the work piece material that generates heat which causes the region near the FSW tool to soften. This in return will mechanically intermix the work pieces. The first objective of this study is to join aluminum plates and copper plates by means of friction stir welding process using self-fabricated tools and conventional milling machine. This study also aims to investigate the optimum process parameters to produce the optimum mechanical properties of the welding joints for Aluminum plates and Copper plates. A suitable tool bit and a fixture is to be fabricated for the welding process. A conventional milling machine will be used to weld the aluminum and copper. The most important parameters to enable the process are speed and pressure of the tool (or tool design and alignment of the tool onto the work piece). The study showed that the best surface finish was produced from speed of 1150 rpm and tool bit tilted to 3°. For a 200mm × 100mm Aluminum 6061 with plate thickness of 2 mm at a speed of 1 mm/s, the time taken to complete the welding is only 200 seconds or equivalent to 3 minutes and 20 seconds. The Copper plates was successfully welded using FSW with tool rotation speed of 500 rpm, 700 rpm, 900 rpm, 1150 rpm and 1440 rpm and with welding traverse rate of 30 mm/min, 60 mm/min and 90 mm/min. As the conclusion, FSW using milling machine can be done on both Aluminum and Copper plates, however the weld parameters are different for the two types of plates.

Normal contour error measurement on-machine and compensation method for polishing complex surface by MRF

NASA Astrophysics Data System (ADS)

Chen, Hua; Chen, Jihong; Wang, Baorui; Zheng, Yongcheng

2016-10-01

The Magnetorheological finishing (MRF) process, based on the dwell time method with the constant normal spacing for flexible polishing, would bring out the normal contour error in the fine polishing complex surface such as aspheric surface. The normal contour error would change the ribbon's shape and removal characteristics of consistency for MRF. Based on continuously scanning the normal spacing between the workpiece and the finder by the laser range finder, the novel method was put forward to measure the normal contour errors while polishing complex surface on the machining track. The normal contour errors was measured dynamically, by which the workpiece's clamping precision, multi-axis machining NC program and the dynamic performance of the MRF machine were achieved for the verification and security check of the MRF process. The unit for measuring the normal contour errors of complex surface on-machine was designed. Based on the measurement unit's results as feedback to adjust the parameters of the feed forward control and the multi-axis machining, the optimized servo control method was presented to compensate the normal contour errors. The experiment for polishing 180mm × 180mm aspherical workpiece of fused silica by MRF was set up to validate the method. The results show that the normal contour error was controlled in less than 10um. And the PV value of the polished surface accuracy was improved from 0.95λ to 0.09λ under the conditions of the same process parameters. The technology in the paper has been being applied in the PKC600-Q1 MRF machine developed by the China Academe of Engineering Physics for engineering application since 2014. It is being used in the national huge optical engineering for processing the ultra-precision optical parts.

Understanding the dynamics of terrorism events with multiple-discipline datasets and machine learning approach

PubMed Central

Ding, Fangyu; Ge, Quansheng; Fu, Jingying; Hao, Mengmeng

2017-01-01

Terror events can cause profound consequences for the whole society. Finding out the regularity of terrorist attacks has important meaning for the global counter-terrorism strategy. In the present study, we demonstrate a novel method using relatively popular and robust machine learning methods to simulate the risk of terrorist attacks at a global scale based on multiple resources, long time series and globally distributed datasets. Historical data from 1970 to 2015 was adopted to train and evaluate machine learning models. The model performed fairly well in predicting the places where terror events might occur in 2015, with a success rate of 96.6%. Moreover, it is noteworthy that the model with optimized tuning parameter values successfully predicted 2,037 terrorism event locations where a terrorist attack had never happened before. PMID:28591138

Understanding the dynamics of terrorism events with multiple-discipline datasets and machine learning approach.

PubMed

Ding, Fangyu; Ge, Quansheng; Jiang, Dong; Fu, Jingying; Hao, Mengmeng

2017-01-01

Terror events can cause profound consequences for the whole society. Finding out the regularity of terrorist attacks has important meaning for the global counter-terrorism strategy. In the present study, we demonstrate a novel method using relatively popular and robust machine learning methods to simulate the risk of terrorist attacks at a global scale based on multiple resources, long time series and globally distributed datasets. Historical data from 1970 to 2015 was adopted to train and evaluate machine learning models. The model performed fairly well in predicting the places where terror events might occur in 2015, with a success rate of 96.6%. Moreover, it is noteworthy that the model with optimized tuning parameter values successfully predicted 2,037 terrorism event locations where a terrorist attack had never happened before.

Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders.

PubMed

Subasi, Abdulhamit

2013-06-01

Support vector machine (SVM) is an extensively used machine learning method with many biomedical signal classification applications. In this study, a novel PSO-SVM model has been proposed that hybridized the particle swarm optimization (PSO) and SVM to improve the EMG signal classification accuracy. This optimization mechanism involves kernel parameter setting in the SVM training procedure, which significantly influences the classification accuracy. The experiments were conducted on the basis of EMG signal to classify into normal, neurogenic or myopathic. In the proposed method the EMG signals were decomposed into the frequency sub-bands using discrete wavelet transform (DWT) and a set of statistical features were extracted from these sub-bands to represent the distribution of wavelet coefficients. The obtained results obviously validate the superiority of the SVM method compared to conventional machine learning methods, and suggest that further significant enhancements in terms of classification accuracy can be achieved by the proposed PSO-SVM classification system. The PSO-SVM yielded an overall accuracy of 97.41% on 1200 EMG signals selected from 27 subject records against 96.75%, 95.17% and 94.08% for the SVM, the k-NN and the RBF classifiers, respectively. PSO-SVM is developed as an efficient tool so that various SVMs can be used conveniently as the core of PSO-SVM for diagnosis of neuromuscular disorders. Copyright © 2013 Elsevier Ltd. All rights reserved.

Large-Scale Linear Optimization through Machine Learning: From Theory to Practical System Design and Implementation

DTIC Science & Technology

2016-08-10

AFRL-AFOSR-JP-TR-2016-0073 Large-scale Linear Optimization through Machine Learning: From Theory to Practical System Design and Implementation ...2016 4.  TITLE AND SUBTITLE Large-scale Linear Optimization through Machine Learning: From Theory to Practical System Design and Implementation 5a...performances on various machine learning tasks and it naturally lends itself to fast parallel implementations . Despite this, very little work has been

Development of a Joint Hydrogen and Syngas Combustion Mechanism Based on an Optimization Approach.

PubMed

Varga, Tamás; Olm, Carsten; Nagy, Tibor; Zsély, István Gy; Valkó, Éva; Pálvölgyi, Róbert; Curran, Henry J; Turányi, Tamás

2016-08-01

A comprehensive and hierarchical optimization of a joint hydrogen and syngas combustion mechanism has been carried out. The Kéromnès et al. ( Combust Flame , 2013, 160, 995-1011) mechanism for syngas combustion was updated with our recently optimized hydrogen combustion mechanism (Varga et al., Proc Combust Inst , 2015, 35, 589-596) and optimized using a comprehensive set of direct and indirect experimental data relevant to hydrogen and syngas combustion. The collection of experimental data consisted of ignition measurements in shock tubes and rapid compression machines, burning velocity measurements, and species profiles measured using shock tubes, flow reactors, and jet-stirred reactors. The experimental conditions covered wide ranges of temperatures (800-2500 K), pressures (0.5-50 bar), equivalence ratios ( ϕ = 0.3-5.0), and C/H ratios (0-3). In total, 48 Arrhenius parameters and 5 third-body collision efficiency parameters of 18 elementary reactions were optimized using these experimental data. A large number of directly measured rate coefficient values belonging to 15 of the reaction steps were also utilized. The optimization has resulted in a H 2 /CO combustion mechanism, which is applicable to a wide range of conditions. Moreover, new recommended rate parameters with their covariance matrix and temperature-dependent uncertainty ranges of the optimized rate coefficients are provided. The optimized mechanism was compared to 19 recent hydrogen and syngas combustion mechanisms and is shown to provide the best reproduction of the experimental data.

Development of a Joint Hydrogen and Syngas Combustion Mechanism Based on an Optimization Approach

PubMed Central

Varga, Tamás; Olm, Carsten; Nagy, Tibor; Zsély, István Gy.; Valkó, Éva; Pálvölgyi, Róbert; Curran, Henry. J.

2016-01-01

ABSTRACT A comprehensive and hierarchical optimization of a joint hydrogen and syngas combustion mechanism has been carried out. The Kéromnès et al. (Combust Flame, 2013, 160, 995–1011) mechanism for syngas combustion was updated with our recently optimized hydrogen combustion mechanism (Varga et al., Proc Combust Inst, 2015, 35, 589–596) and optimized using a comprehensive set of direct and indirect experimental data relevant to hydrogen and syngas combustion. The collection of experimental data consisted of ignition measurements in shock tubes and rapid compression machines, burning velocity measurements, and species profiles measured using shock tubes, flow reactors, and jet‐stirred reactors. The experimental conditions covered wide ranges of temperatures (800–2500 K), pressures (0.5–50 bar), equivalence ratios (ϕ = 0.3–5.0), and C/H ratios (0–3). In total, 48 Arrhenius parameters and 5 third‐body collision efficiency parameters of 18 elementary reactions were optimized using these experimental data. A large number of directly measured rate coefficient values belonging to 15 of the reaction steps were also utilized. The optimization has resulted in a H2/CO combustion mechanism, which is applicable to a wide range of conditions. Moreover, new recommended rate parameters with their covariance matrix and temperature‐dependent uncertainty ranges of the optimized rate coefficients are provided. The optimized mechanism was compared to 19 recent hydrogen and syngas combustion mechanisms and is shown to provide the best reproduction of the experimental data. PMID:27840549

Material Choice for spindle of machine tools

NASA Astrophysics Data System (ADS)

Gouasmi, S.; Merzoug, B.; Abba, G.; Kherredine, L.

2012-02-01

The requirements of contemporary industry and the flashing development of modern sciences impose restrictions on the majority of the elements of machines; the resulting financial constraints can be satisfied by a better output of the production equipment. As for those concerning the design, the resistance and the correct operation of the product, these require the development of increasingly precise parts, therefore the use of increasingly powerful tools [5]. The precision of machining and the output of the machine tools are generally determined by the precision of rotation of the spindle, indeed, more this one is large more the dimensions to obtain are in the zone of tolerance and the defects of shape are minimized. During the development of the machine tool, the spindle which by definition is a rotating shaft receiving and transmitting to the work piece or the cutting tool the rotational movement, must be designed according to certain optimal parameters to be able to ensure the precision required. This study will be devoted to the choice of the material of the spindle fulfilling the imposed requirements of precision.

An Efficient Data Partitioning to Improve Classification Performance While Keeping Parameters Interpretable

PubMed Central

Korjus, Kristjan; Hebart, Martin N.; Vicente, Raul

2016-01-01

Supervised machine learning methods typically require splitting data into multiple chunks for training, validating, and finally testing classifiers. For finding the best parameters of a classifier, training and validation are usually carried out with cross-validation. This is followed by application of the classifier with optimized parameters to a separate test set for estimating the classifier’s generalization performance. With limited data, this separation of test data creates a difficult trade-off between having more statistical power in estimating generalization performance versus choosing better parameters and fitting a better model. We propose a novel approach that we term “Cross-validation and cross-testing” improving this trade-off by re-using test data without biasing classifier performance. The novel approach is validated using simulated data and electrophysiological recordings in humans and rodents. The results demonstrate that the approach has a higher probability of discovering significant results than the standard approach of cross-validation and testing, while maintaining the nominal alpha level. In contrast to nested cross-validation, which is maximally efficient in re-using data, the proposed approach additionally maintains the interpretability of individual parameters. Taken together, we suggest an addition to currently used machine learning approaches which may be particularly useful in cases where model weights do not require interpretation, but parameters do. PMID:27564393

An Efficient Data Partitioning to Improve Classification Performance While Keeping Parameters Interpretable.

PubMed

Korjus, Kristjan; Hebart, Martin N; Vicente, Raul

2016-01-01

Supervised machine learning methods typically require splitting data into multiple chunks for training, validating, and finally testing classifiers. For finding the best parameters of a classifier, training and validation are usually carried out with cross-validation. This is followed by application of the classifier with optimized parameters to a separate test set for estimating the classifier's generalization performance. With limited data, this separation of test data creates a difficult trade-off between having more statistical power in estimating generalization performance versus choosing better parameters and fitting a better model. We propose a novel approach that we term "Cross-validation and cross-testing" improving this trade-off by re-using test data without biasing classifier performance. The novel approach is validated using simulated data and electrophysiological recordings in humans and rodents. The results demonstrate that the approach has a higher probability of discovering significant results than the standard approach of cross-validation and testing, while maintaining the nominal alpha level. In contrast to nested cross-validation, which is maximally efficient in re-using data, the proposed approach additionally maintains the interpretability of individual parameters. Taken together, we suggest an addition to currently used machine learning approaches which may be particularly useful in cases where model weights do not require interpretation, but parameters do.

Experimental investigation and optimization of welding process parameters for various steel grades using NN tool and Taguchi method

NASA Astrophysics Data System (ADS)

Soni, Sourabh Kumar; Thomas, Benedict

2018-04-01

The term "weldability" has been used to describe a wide variety of characteristics when a material is subjected to welding. In our analysis we perform experimental investigation to estimate the tensile strength of welded joint strength and then optimization of welding process parameters by using taguchi method and Artificial Neural Network (ANN) tool in MINITAB and MATLAB software respectively. The study reveals the influence on weldability of steel by varying composition of steel by mechanical characterization. At first we prepare the samples of different grades of steel (EN8, EN 19, EN 24). The samples were welded together by metal inert gas welding process and then tensile testing on Universal testing machine (UTM) was conducted for the same to evaluate the tensile strength of the welded steel specimens. Further comparative study was performed to find the effects of welding parameter on quality of weld strength by employing Taguchi method and Neural Network tool. Finally we concluded that taguchi method and Neural Network Tool is much efficient technique for optimization.

Estimation and Optimization of the Parameters Preserving the Lustre of the Fabrics

NASA Astrophysics Data System (ADS)

Prodanova, Krasimira

2009-11-01

The paper discusses the optimization of the continuance of the Damp-Heating Process of a steaming iron press machine, and the preserving of the lustre of the fabrics. In order to be obtained high qualitative damp-heating processing, it is necessary to monitor parameters such as temperature, damp, and pressure during the process. The purpose of the present paper is a mathematical model to be constructed that adequately describes the technological process using multivariate data analysis. It was established that the full factorial design of type 23 is not adequate. The research has proceeded with central rotatable design of experiment. The obtained model adequately describes the technological process of damp-heating treatment in the defined factor space. The present investigation is helpful to the technological improvement and modernization in sewing companies.

Study on Damage Evaluation and Machinability of UD-CFRP for the Orthogonal Cutting Operation Using Scanning Acoustic Microscopy and the Finite Element Method.

PubMed

Wang, Dongyao; He, Xiaodong; Xu, Zhonghai; Jiao, Weicheng; Yang, Fan; Jiang, Long; Li, Linlin; Liu, Wenbo; Wang, Rongguo

2017-02-20

Owing to high specific strength and designability, unidirectional carbon fiber reinforced polymer (UD-CFRP) has been utilized in numerous fields to replace conventional metal materials. Post machining processes are always required for UD-CFRP to achieve dimensional tolerance and assembly specifications. Due to inhomogeneity and anisotropy, UD-CFRP differs greatly from metal materials in machining and failure mechanism. To improve the efficiency and avoid machining-induced damage, this paper undertook to study the correlations between cutting parameters, fiber orientation angle, cutting forces, and cutting-induced damage for UD-CFRP laminate. Scanning acoustic microscopy (SAM) was employed and one-/two-dimensional damage factors were then created to quantitatively characterize the damage of the laminate workpieces. According to the 3D Hashin's criteria a numerical model was further proposed in terms of the finite element method (FEM). A good agreement between simulation and experimental results was validated for the prediction and structural optimization of the UD-CFRP.

Study on Damage Evaluation and Machinability of UD-CFRP for the Orthogonal Cutting Operation Using Scanning Acoustic Microscopy and the Finite Element Method

PubMed Central

Wang, Dongyao; He, Xiaodong; Xu, Zhonghai; Jiao, Weicheng; Yang, Fan; Jiang, Long; Li, Linlin; Liu, Wenbo; Wang, Rongguo

2017-01-01

Owing to high specific strength and designability, unidirectional carbon fiber reinforced polymer (UD-CFRP) has been utilized in numerous fields to replace conventional metal materials. Post machining processes are always required for UD-CFRP to achieve dimensional tolerance and assembly specifications. Due to inhomogeneity and anisotropy, UD-CFRP differs greatly from metal materials in machining and failure mechanism. To improve the efficiency and avoid machining-induced damage, this paper undertook to study the correlations between cutting parameters, fiber orientation angle, cutting forces, and cutting-induced damage for UD-CFRP laminate. Scanning acoustic microscopy (SAM) was employed and one-/two-dimensional damage factors were then created to quantitatively characterize the damage of the laminate workpieces. According to the 3D Hashin’s criteria a numerical model was further proposed in terms of the finite element method (FEM). A good agreement between simulation and experimental results was validated for the prediction and structural optimization of the UD-CFRP. PMID:28772565

Warpage optimization on a mobile phone case using response surface methodology (RSM)

NASA Astrophysics Data System (ADS)

Lee, X. N.; Fathullah, M.; Shayfull, Z.; Nasir, S. M.; Hazwan, M. H. M.; Shazzuan, S.

2017-09-01

Plastic injection moulding is a popular manufacturing method not only it is reliable, but also efficient and cost saving. It able to produce plastic part with detailed features and complex geometry. However, defects in injection moulding process degrades the quality and aesthetic of the injection moulded product. The most common defect occur in the process is warpage. Inappropriate process parameter setting of injection moulding machine is one of the reason that leads to the occurrence of warpage. The aims of this study were to improve the quality of injection moulded part by investigating the optimal parameters in minimizing warpage using Response Surface Methodology (RSM). Subsequent to this, the most significant parameter was identified and recommended parameters setting was compared with the optimized parameter setting using RSM. In this research, the mobile phone case was selected as case study. The mould temperature, melt temperature, packing pressure, packing time and cooling time were selected as variables whereas warpage in y-direction was selected as responses in this research. The simulation was carried out by using Autodesk Moldflow Insight 2012. In addition, the RSM was performed by using Design Expert 7.0. The warpage in y direction recommended by RSM were reduced by 70 %. RSM performed well in solving warpage issue.

Integrating machine learning to achieve an automatic parameter prediction for practical continuous-variable quantum key distribution

NASA Astrophysics Data System (ADS)

Liu, Weiqi; Huang, Peng; Peng, Jinye; Fan, Jianping; Zeng, Guihua

2018-02-01

For supporting practical quantum key distribution (QKD), it is critical to stabilize the physical parameters of signals, e.g., the intensity, phase, and polarization of the laser signals, so that such QKD systems can achieve better performance and practical security. In this paper, an approach is developed by integrating a support vector regression (SVR) model to optimize the performance and practical security of the QKD system. First, a SVR model is learned to precisely predict the time-along evolutions of the physical parameters of signals. Second, such predicted time-along evolutions are employed as feedback to control the QKD system for achieving the optimal performance and practical security. Finally, our proposed approach is exemplified by using the intensity evolution of laser light and a local oscillator pulse in the Gaussian modulated coherent state QKD system. Our experimental results have demonstrated three significant benefits of our SVR-based approach: (1) it can allow the QKD system to achieve optimal performance and practical security, (2) it does not require any additional resources and any real-time monitoring module to support automatic prediction of the time-along evolutions of the physical parameters of signals, and (3) it is applicable to any measurable physical parameter of signals in the practical QKD system.

Distribution of quantum Fisher information in asymmetric cloning machines

PubMed Central

Xiao, Xing; Yao, Yao; Zhou, Lei-Ming; Wang, Xiaoguang

2014-01-01

An unknown quantum state cannot be copied and broadcast freely due to the no-cloning theorem. Approximate cloning schemes have been proposed to achieve the optimal cloning characterized by the maximal fidelity between the original and its copies. Here, from the perspective of quantum Fisher information (QFI), we investigate the distribution of QFI in asymmetric cloning machines which produce two nonidentical copies. As one might expect, improving the QFI of one copy results in decreasing the QFI of the other copy. It is perhaps also unsurprising that asymmetric phase-covariant cloning outperforms universal cloning in distributing QFI since a priori information of the input state has been utilized. However, interesting results appear when we compare the distributabilities of fidelity (which quantifies the full information of quantum states), and QFI (which only captures the information of relevant parameters) in asymmetric cloning machines. Unlike the results of fidelity, where the distributability of symmetric cloning is always optimal for any d-dimensional cloning, we find that any asymmetric cloning outperforms symmetric cloning on the distribution of QFI for d ≤ 18, whereas some but not all asymmetric cloning strategies could be worse than symmetric ones when d > 18. PMID:25484234

Sequential Nonlinear Learning for Distributed Multiagent Systems via Extreme Learning Machines.

PubMed

Vanli, Nuri Denizcan; Sayin, Muhammed O; Delibalta, Ibrahim; Kozat, Suleyman Serdar

2017-03-01

We study online nonlinear learning over distributed multiagent systems, where each agent employs a single hidden layer feedforward neural network (SLFN) structure to sequentially minimize arbitrary loss functions. In particular, each agent trains its own SLFN using only the data that is revealed to itself. On the other hand, the aim of the multiagent system is to train the SLFN at each agent as well as the optimal centralized batch SLFN that has access to all the data, by exchanging information between neighboring agents. We address this problem by introducing a distributed subgradient-based extreme learning machine algorithm. The proposed algorithm provides guaranteed upper bounds on the performance of the SLFN at each agent and shows that each of these individual SLFNs asymptotically achieves the performance of the optimal centralized batch SLFN. Our performance guarantees explicitly distinguish the effects of data- and network-dependent parameters on the convergence rate of the proposed algorithm. The experimental results illustrate that the proposed algorithm achieves the oracle performance significantly faster than the state-of-the-art methods in the machine learning and signal processing literature. Hence, the proposed method is highly appealing for the applications involving big data.

A Temperature Compensation Method for Piezo-Resistive Pressure Sensor Utilizing Chaotic Ions Motion Algorithm Optimized Hybrid Kernel LSSVM.

PubMed

Li, Ji; Hu, Guoqing; Zhou, Yonghong; Zou, Chong; Peng, Wei; Alam Sm, Jahangir

2016-10-14

A piezo-resistive pressure sensor is made of silicon, the nature of which is considerably influenced by ambient temperature. The effect of temperature should be eliminated during the working period in expectation of linear output. To deal with this issue, an approach consists of a hybrid kernel Least Squares Support Vector Machine (LSSVM) optimized by a chaotic ions motion algorithm presented. To achieve the learning and generalization for excellent performance, a hybrid kernel function, constructed by a local kernel as Radial Basis Function (RBF) kernel, and a global kernel as polynomial kernel is incorporated into the Least Squares Support Vector Machine. The chaotic ions motion algorithm is introduced to find the best hyper-parameters of the Least Squares Support Vector Machine. The temperature data from a calibration experiment is conducted to validate the proposed method. With attention on algorithm robustness and engineering applications, the compensation result shows the proposed scheme outperforms other compared methods on several performance measures as maximum absolute relative error, minimum absolute relative error mean and variance of the averaged value on fifty runs. Furthermore, the proposed temperature compensation approach lays a foundation for more extensive research.

A Study of Electrochemical Machining of Ti-6Al-4V in NaNO3 solution

NASA Astrophysics Data System (ADS)

Li, Hansong; Gao, Chuanping; Wang, Guoqian; Qu, Ningsong; Zhu, Di

2016-10-01

The titanium alloy Ti-6Al-4V is used in many industries including aviation, automobile manufacturing, and medical equipment, because of its low density, extraordinary corrosion resistance and high specific strength. Electrochemical machining (ECM) is a non-traditional machining method that allows applications to all kinds of metallic materials in regardless of their mechanical properties. It is widely applied to the machining of Ti-6Al-4V components, which usually takes place in a multicomponent electrolyte solution. In this study, a 10% NaNO3 solution was used to make multiple holes in Ti-6Al-4V sheets by through-mask electrochemical machining (TMECM). The polarization curve and current efficiency curve of this alloy were measured to understand the electrical properties of Ti-6Al-4V in a 10% NaNO3 solution. The measurements show that in a 10% NaNO3 solution, when the current density was above 6.56 A·cm-2, the current efficiency exceeded 100%. According to polarization curve and current efficiency curve, an orthogonal TMECM experiment was conducted on Ti-6Al-4V. The experimental results suggest that with appropriate process parameters, high-quality holes can be obtained in a 10% NaNO3 solution. Using the optimized process parameters, an array of micro-holes with an aperture of 2.52 mm to 2.57 mm and maximum roundness of 9 μm were produced using TMECM.

Uncertainty analysis of an inflow forecasting model: extension of the UNEEC machine learning-based method

NASA Astrophysics Data System (ADS)

Pianosi, Francesca; Lal Shrestha, Durga; Solomatine, Dimitri

2010-05-01

This research presents an extension of UNEEC (Uncertainty Estimation based on Local Errors and Clustering, Shrestha and Solomatine, 2006, 2008 & Solomatine and Shrestha, 2009) method in the direction of explicit inclusion of parameter uncertainty. UNEEC method assumes that there is an optimal model and the residuals of the model can be used to assess the uncertainty of the model prediction. It is assumed that all sources of uncertainty including input, parameter and model structure uncertainty are explicitly manifested in the model residuals. In this research, theses assumptions are relaxed, and the UNEEC method is extended to consider parameter uncertainty as well (abbreviated as UNEEC-P). In UNEEC-P, first we use Monte Carlo (MC) sampling in parameter space to generate N model realizations (each of which is a time series), estimate the prediction quantiles based on the empirical distribution functions of the model residuals considering all the residual realizations, and only then apply the standard UNEEC method that encapsulates the uncertainty of a hydrologic model (expressed by quantiles of the error distribution) in a machine learning model (e.g., ANN). UNEEC-P is applied first to a linear regression model of synthetic data, and then to a real case study of forecasting inflow to lake Lugano in northern Italy. The inflow forecasting model is a stochastic heteroscedastic model (Pianosi and Soncini-Sessa, 2009). The preliminary results show that the UNEEC-P method produces wider uncertainty bounds, which is consistent with the fact that the method considers also parameter uncertainty of the optimal model. In the future UNEEC method will be further extended to consider input and structure uncertainty which will provide more realistic estimation of model predictions.

Developing Parametric Models for the Assembly of Machine Fixtures for Virtual Multiaxial CNC Machining Centers

NASA Astrophysics Data System (ADS)

Balaykin, A. V.; Bezsonov, K. A.; Nekhoroshev, M. V.; Shulepov, A. P.

2018-01-01

This paper dwells upon a variance parameterization method. Variance or dimensional parameterization is based on sketching, with various parametric links superimposed on the sketch objects and user-imposed constraints in the form of an equation system that determines the parametric dependencies. This method is fully integrated in a top-down design methodology to enable the creation of multi-variant and flexible fixture assembly models, as all the modeling operations are hierarchically linked in the built tree. In this research the authors consider a parameterization method of machine tooling used for manufacturing parts using multiaxial CNC machining centers in the real manufacturing process. The developed method allows to significantly reduce tooling design time when making changes of a part’s geometric parameters. The method can also reduce time for designing and engineering preproduction, in particular, for development of control programs for CNC equipment and control and measuring machines, automate the release of design and engineering documentation. Variance parameterization helps to optimize construction of parts as well as machine tooling using integrated CAE systems. In the framework of this study, the authors demonstrate a comprehensive approach to parametric modeling of machine tooling in the CAD package used in the real manufacturing process of aircraft engines.

Fabrication of locally micro-structured fiber Bragg gratings by fs-laser machining

NASA Astrophysics Data System (ADS)

Dutz, Franz J.; Stephan, Valentin; Marchi, Gabriele; Koch, Alexander W.; Roths, Johannes; Huber, Heinz P.

2018-06-01

Here, we describe a method for producing locally micro-structured fiber Bragg gratings (LMFGB) by fs-laser machining. This technique enables the precise and reproducible ablation of cladding material to create circumferential grooves inside the claddings of optical fibers. From initial ablation experiments we acquired optimized process parameters. The fabricated grooves were located in the middle of uniform type I fiber Bragg gratings. LMFBGs with four different groove widths of 48, 85, 135 and 205 μ { {m}} were produced. The grooves exhibited constant depths of about 30 μ {m} and steep sidewall angles. With the combination of micro-structures and fiber Bragg gratings, fiber optic sensor elements with enhanced functionalities can be achieved.

Virtual screening of inorganic materials synthesis parameters with deep learning

NASA Astrophysics Data System (ADS)

Kim, Edward; Huang, Kevin; Jegelka, Stefanie; Olivetti, Elsa

2017-12-01

Virtual materials screening approaches have proliferated in the past decade, driven by rapid advances in first-principles computational techniques, and machine-learning algorithms. By comparison, computationally driven materials synthesis screening is still in its infancy, and is mired by the challenges of data sparsity and data scarcity: Synthesis routes exist in a sparse, high-dimensional parameter space that is difficult to optimize over directly, and, for some materials of interest, only scarce volumes of literature-reported syntheses are available. In this article, we present a framework for suggesting quantitative synthesis parameters and potential driving factors for synthesis outcomes. We use a variational autoencoder to compress sparse synthesis representations into a lower dimensional space, which is found to improve the performance of machine-learning tasks. To realize this screening framework even in cases where there are few literature data, we devise a novel data augmentation methodology that incorporates literature synthesis data from related materials systems. We apply this variational autoencoder framework to generate potential SrTiO3 synthesis parameter sets, propose driving factors for brookite TiO2 formation, and identify correlations between alkali-ion intercalation and MnO2 polymorph selection.

Analysis on the multi-dimensional spectrum of the thrust force for the linear motor feed drive system in machine tools

NASA Astrophysics Data System (ADS)

Yang, Xiaojun; Lu, Dun; Ma, Chengfang; Zhang, Jun; Zhao, Wanhua

2017-01-01

The motor thrust force has lots of harmonic components due to the nonlinearity of drive circuit and motor itself in the linear motor feed drive system. What is more, in the motion process, these thrust force harmonics may vary with the position, velocity, acceleration and load, which affects the displacement fluctuation of the feed drive system. Therefore, in this paper, on the basis of the thrust force spectrum obtained by the Maxwell equation and the electromagnetic energy method, the multi-dimensional variation of each thrust harmonic is analyzed under different motion parameters. Then the model of the servo system is established oriented to the dynamic precision. The influence of the variation of the thrust force spectrum on the displacement fluctuation is discussed. At last the experiments are carried out to verify the theoretical analysis above. It can be found that the thrust harmonics show multi-dimensional spectrum characteristics under different motion parameters and loads, which should be considered to choose the motion parameters and optimize the servo control parameters in the high-speed and high-precision machine tools equipped with the linear motor feed drive system.

Fruit fly optimization based least square support vector regression for blind image restoration

NASA Astrophysics Data System (ADS)

Zhang, Jiao; Wang, Rui; Li, Junshan; Yang, Yawei

2014-11-01

The goal of image restoration is to reconstruct the original scene from a degraded observation. It is a critical and challenging task in image processing. Classical restorations require explicit knowledge of the point spread function and a description of the noise as priors. However, it is not practical for many real image processing. The recovery processing needs to be a blind image restoration scenario. Since blind deconvolution is an ill-posed problem, many blind restoration methods need to make additional assumptions to construct restrictions. Due to the differences of PSF and noise energy, blurring images can be quite different. It is difficult to achieve a good balance between proper assumption and high restoration quality in blind deconvolution. Recently, machine learning techniques have been applied to blind image restoration. The least square support vector regression (LSSVR) has been proven to offer strong potential in estimating and forecasting issues. Therefore, this paper proposes a LSSVR-based image restoration method. However, selecting the optimal parameters for support vector machine is essential to the training result. As a novel meta-heuristic algorithm, the fruit fly optimization algorithm (FOA) can be used to handle optimization problems, and has the advantages of fast convergence to the global optimal solution. In the proposed method, the training samples are created from a neighborhood in the degraded image to the central pixel in the original image. The mapping between the degraded image and the original image is learned by training LSSVR. The two parameters of LSSVR are optimized though FOA. The fitness function of FOA is calculated by the restoration error function. With the acquired mapping, the degraded image can be recovered. Experimental results show the proposed method can obtain satisfactory restoration effect. Compared with BP neural network regression, SVR method and Lucy-Richardson algorithm, it speeds up the restoration rate and performs better. Both objective and subjective restoration performances are studied in the comparison experiments.

Joint optimization of maintenance, buffers and machines in manufacturing lines

NASA Astrophysics Data System (ADS)

Nahas, Nabil; Nourelfath, Mustapha

2018-01-01

This article considers a series manufacturing line composed of several machines separated by intermediate buffers of finite capacity. The goal is to find the optimal number of preventive maintenance actions performed on each machine, the optimal selection of machines and the optimal buffer allocation plan that minimize the total system cost, while providing the desired system throughput level. The mean times between failures of all machines are assumed to increase when applying periodic preventive maintenance. To estimate the production line throughput, a decomposition method is used. The decision variables in the formulated optimal design problem are buffer levels, types of machines and times between preventive maintenance actions. Three heuristic approaches are developed to solve the formulated combinatorial optimization problem. The first heuristic consists of a genetic algorithm, the second is based on the nonlinear threshold accepting metaheuristic and the third is an ant colony system. The proposed heuristics are compared and their efficiency is shown through several numerical examples. It is found that the nonlinear threshold accepting algorithm outperforms the genetic algorithm and ant colony system, while the genetic algorithm provides better results than the ant colony system for longer manufacturing lines.

Determining A Purely Symbolic Transfer Function from Symbol Streams: Theory and Algorithms

DOE Office of Scientific and Technical Information (OSTI.GOV)

Griffin, Christopher H

Transfer function modeling is a \\emph{standard technique} in classical Linear Time Invariant and Statistical Process Control. The work of Box and Jenkins was seminal in developing methods for identifying parameters associated with classicalmore » $(r,s,k)$$ transfer functions. Discrete event systems are often \\emph{used} for modeling hybrid control structures and high-level decision problems. \\emph{Examples include} discrete time, discrete strategy repeated games. For these games, a \\emph{discrete transfer function in the form of} an accurate hidden Markov model of input-output relations \\emph{could be used to derive optimal response strategies.} In this paper, we develop an algorithm \\emph{for} creating probabilistic \\textit{Mealy machines} that act as transfer function models for discrete event dynamic systems (DEDS). Our models are defined by three parameters, $$(l_1, l_2, k)$ just as the Box-Jenkins transfer function models. Here $$l_1$$ is the maximal input history lengths to consider, $$l_2$$ is the maximal output history lengths to consider and $k$ is the response lag. Using related results, We show that our Mealy machine transfer functions are optimal in the sense that they maximize the mutual information between the current known state of the DEDS and the next observed input/output pair.« less

Running accuracy analysis of a 3-RRR parallel kinematic machine considering the deformations of the links

NASA Astrophysics Data System (ADS)

Wang, Liping; Jiang, Yao; Li, Tiemin

2014-09-01

Parallel kinematic machines have drawn considerable attention and have been widely used in some special fields. However, high precision is still one of the challenges when they are used for advanced machine tools. One of the main reasons is that the kinematic chains of parallel kinematic machines are composed of elongated links that can easily suffer deformations, especially at high speeds and under heavy loads. A 3-RRR parallel kinematic machine is taken as a study object for investigating its accuracy with the consideration of the deformations of its links during the motion process. Based on the dynamic model constructed by the Newton-Euler method, all the inertia loads and constraint forces of the links are computed and their deformations are derived. Then the kinematic errors of the machine are derived with the consideration of the deformations of the links. Through further derivation, the accuracy of the machine is given in a simple explicit expression, which will be helpful to increase the calculating speed. The accuracy of this machine when following a selected circle path is simulated. The influences of magnitude of the maximum acceleration and external loads on the running accuracy of the machine are investigated. The results show that the external loads will deteriorate the accuracy of the machine tremendously when their direction coincides with the direction of the worst stiffness of the machine. The proposed method provides a solution for predicting the running accuracy of the parallel kinematic machines and can also be used in their design optimization as well as selection of suitable running parameters.

Modifications of Ti-6Al-4V surfaces by direct-write laser machining of linear grooves

NASA Astrophysics Data System (ADS)

Ulerich, Joseph P.; Ionescu, Lara C.; Chen, Jianbo; Soboyejo, Winston O.; Arnold, Craig B.

2007-02-01

As patients who receive orthopedic implants live longer and opt for surgery at a younger age, the need to extend the in vivo lifetimes of these implants has grown. One approach is to pattern implant surfaces with linear grooves, which elicit a cellular response known as contact guidance. Lasers provide a unique method of generating these surface patterns because they are capable of modifying physical and chemical properties over multiple length scales. In this paper we explore the relationship between surface morphology and laser parameters such as fluence, pulse overlap (translation distance), number of passes, and machining environment. We find that using simple procedures involving multiple passes it is possible to manipulate groove properties such as depth, shape, sub-micron roughness, and chemical composition of the Ti-6Al-4V oxide layer. Finally, we demonstrate this procedure by machining several sets of grooves with the same primary groove parameters but varied secondary characteristics. The significance of the secondary groove characteristics is demonstrated by preliminary cell studies indicating that the grooves exhibit basic features of contact guidance and that the cell proliferation in these grooves are significantly altered despite their similar primary characteristics. With further study it will be possible to use specific laser parameters during groove formation to create optimal physical and chemical properties for improved osseointegration.

As above, so below? Towards understanding inverse models in BCI

NASA Astrophysics Data System (ADS)

Lindgren, Jussi T.

2018-02-01

Objective. In brain-computer interfaces (BCI), measurements of the user’s brain activity are classified into commands for the computer. With EEG-based BCIs, the origins of the classified phenomena are often considered to be spatially localized in the cortical volume and mixed in the EEG. We investigate if more accurate BCIs can be obtained by reconstructing the source activities in the volume. Approach. We contrast the physiology-driven source reconstruction with data-driven representations obtained by statistical machine learning. We explain these approaches in a common linear dictionary framework and review the different ways to obtain the dictionary parameters. We consider the effect of source reconstruction on some major difficulties in BCI classification, namely information loss, feature selection and nonstationarity of the EEG. Main results. Our analysis suggests that the approaches differ mainly in their parameter estimation. Physiological source reconstruction may thus be expected to improve BCI accuracy if machine learning is not used or where it produces less optimal parameters. We argue that the considered difficulties of surface EEG classification can remain in the reconstructed volume and that data-driven techniques are still necessary. Finally, we provide some suggestions for comparing approaches. Significance. The present work illustrates the relationships between source reconstruction and machine learning-based approaches for EEG data representation. The provided analysis and discussion should help in understanding, applying, comparing and improving such techniques in the future.

FSW of Aluminum Tailor Welded Blanks across Machine Platforms

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hovanski, Yuri; Upadhyay, Piyush; Carlson, Blair

2015-02-16

Development and characterization of friction stir welded aluminum tailor welded blanks was successfully carried out on three separate machine platforms. Each was a commercially available, gantry style, multi-axis machine designed specifically for friction stir welding. Weld parameters were developed to support high volume production of dissimilar thickness aluminum tailor welded blanks at speeds of 3 m/min and greater. Parameters originally developed on an ultra-high stiffness servo driven machine where first transferred to a high stiffness servo-hydraulic friction stir welding machine, and subsequently transferred to a purpose built machine designed to accommodate thin sheet aluminum welding. The inherent beam stiffness, bearingmore » compliance, and control system for each machine were distinctly unique, which posed specific challenges in transferring welding parameters across machine platforms. This work documents the challenges imposed by successfully transferring weld parameters from machine to machine, produced from different manufacturers and with unique control systems and interfaces.« less

Optimizing ChIP-seq peak detectors using visual labels and supervised machine learning

PubMed Central

Goerner-Potvin, Patricia; Morin, Andreanne; Shao, Xiaojian; Pastinen, Tomi

2017-01-01

Motivation: Many peak detection algorithms have been proposed for ChIP-seq data analysis, but it is not obvious which algorithm and what parameters are optimal for any given dataset. In contrast, regions with and without obvious peaks can be easily labeled by visual inspection of aligned read counts in a genome browser. We propose a supervised machine learning approach for ChIP-seq data analysis, using labels that encode qualitative judgments about which genomic regions contain or do not contain peaks. The main idea is to manually label a small subset of the genome, and then learn a model that makes consistent peak predictions on the rest of the genome. Results: We created 7 new histone mark datasets with 12 826 visually determined labels, and analyzed 3 existing transcription factor datasets. We observed that default peak detection parameters yield high false positive rates, which can be reduced by learning parameters using a relatively small training set of labeled data from the same experiment type. We also observed that labels from different people are highly consistent. Overall, these data indicate that our supervised labeling method is useful for quantitatively training and testing peak detection algorithms. Availability and Implementation: Labeled histone mark data http://cbio.ensmp.fr/~thocking/chip-seq-chunk-db/, R package to compute the label error of predicted peaks https://github.com/tdhock/PeakError Contacts: toby.hocking@mail.mcgill.ca or guil.bourque@mcgill.ca Supplementary information: Supplementary data are available at Bioinformatics online. PMID:27797775

Optimizing ChIP-seq peak detectors using visual labels and supervised machine learning.

PubMed

Hocking, Toby Dylan; Goerner-Potvin, Patricia; Morin, Andreanne; Shao, Xiaojian; Pastinen, Tomi; Bourque, Guillaume

2017-02-15

Many peak detection algorithms have been proposed for ChIP-seq data analysis, but it is not obvious which algorithm and what parameters are optimal for any given dataset. In contrast, regions with and without obvious peaks can be easily labeled by visual inspection of aligned read counts in a genome browser. We propose a supervised machine learning approach for ChIP-seq data analysis, using labels that encode qualitative judgments about which genomic regions contain or do not contain peaks. The main idea is to manually label a small subset of the genome, and then learn a model that makes consistent peak predictions on the rest of the genome. We created 7 new histone mark datasets with 12 826 visually determined labels, and analyzed 3 existing transcription factor datasets. We observed that default peak detection parameters yield high false positive rates, which can be reduced by learning parameters using a relatively small training set of labeled data from the same experiment type. We also observed that labels from different people are highly consistent. Overall, these data indicate that our supervised labeling method is useful for quantitatively training and testing peak detection algorithms. Labeled histone mark data http://cbio.ensmp.fr/~thocking/chip-seq-chunk-db/ , R package to compute the label error of predicted peaks https://github.com/tdhock/PeakError. toby.hocking@mail.mcgill.ca or guil.bourque@mcgill.ca. Supplementary data are available at Bioinformatics online. © The Author 2016. Published by Oxford University Press.

Daily River Flow Forecasting with Hybrid Support Vector Machine – Particle Swarm Optimization

NASA Astrophysics Data System (ADS)

Zaini, N.; Malek, M. A.; Yusoff, M.; Mardi, N. H.; Norhisham, S.

2018-04-01

The application of artificial intelligence techniques for river flow forecasting can further improve the management of water resources and flood prevention. This study concerns the development of support vector machine (SVM) based model and its hybridization with particle swarm optimization (PSO) to forecast short term daily river flow at Upper Bertam Catchment located in Cameron Highland, Malaysia. Ten years duration of historical rainfall, antecedent river flow data and various meteorology parameters data from 2003 to 2012 are used in this study. Four SVM based models are proposed which are SVM1, SVM2, SVM-PSO1 and SVM-PSO2 to forecast 1 to 7 day ahead of river flow. SVM1 and SVM-PSO1 are the models with historical rainfall and antecedent river flow as its input, while SVM2 and SVM-PSO2 are the models with historical rainfall, antecedent river flow data and additional meteorological parameters as input. The performances of the proposed model are measured in term of RMSE and R2 . It is found that, SVM2 outperformed SVM1 and SVM-PSO2 outperformed SVM-PSO1 which meant the additional meteorology parameters used as input to the proposed models significantly affect the model performances. Hybrid models SVM-PSO1 and SVM-PSO2 yield higher performances as compared to SVM1 and SVM2. It is found that hybrid models are more effective in forecasting river flow at 1 to 7 day ahead at the study area.

On robust parameter estimation in brain-computer interfacing

NASA Astrophysics Data System (ADS)

Samek, Wojciech; Nakajima, Shinichi; Kawanabe, Motoaki; Müller, Klaus-Robert

2017-12-01

Objective. The reliable estimation of parameters such as mean or covariance matrix from noisy and high-dimensional observations is a prerequisite for successful application of signal processing and machine learning algorithms in brain-computer interfacing (BCI). This challenging task becomes significantly more difficult if the data set contains outliers, e.g. due to subject movements, eye blinks or loose electrodes, as they may heavily bias the estimation and the subsequent statistical analysis. Although various robust estimators have been developed to tackle the outlier problem, they ignore important structural information in the data and thus may not be optimal. Typical structural elements in BCI data are the trials consisting of a few hundred EEG samples and indicating the start and end of a task. Approach. This work discusses the parameter estimation problem in BCI and introduces a novel hierarchical view on robustness which naturally comprises different types of outlierness occurring in structured data. Furthermore, the class of minimum divergence estimators is reviewed and a robust mean and covariance estimator for structured data is derived and evaluated with simulations and on a benchmark data set. Main results. The results show that state-of-the-art BCI algorithms benefit from robustly estimated parameters. Significance. Since parameter estimation is an integral part of various machine learning algorithms, the presented techniques are applicable to many problems beyond BCI.

Optimal shutdown management

NASA Astrophysics Data System (ADS)

Bottasso, C. L.; Croce, A.; Riboldi, C. E. D.

2014-06-01

The paper presents a novel approach for the synthesis of the open-loop pitch profile during emergency shutdowns. The problem is of interest in the design of wind turbines, as such maneuvers often generate design driving loads on some of the machine components. The pitch profile synthesis is formulated as a constrained optimal control problem, solved numerically using a direct single shooting approach. A cost function expressing a compromise between load reduction and rotor overspeed is minimized with respect to the unknown blade pitch profile. Constraints may include a load reduction not-to-exceed the next dominating loads, a not-to-be-exceeded maximum rotor speed, and a maximum achievable blade pitch rate. Cost function and constraints are computed over a possibly large number of operating conditions, defined so as to cover as well as possible the operating situations encountered in the lifetime of the machine. All such conditions are simulated by using a high-fidelity aeroservoelastic model of the wind turbine, ensuring the accuracy of the evaluation of all relevant parameters. The paper demonstrates the capabilities of the novel proposed formulation, by optimizing the pitch profile of a multi-MW wind turbine. Results show that the procedure can reliably identify optimal pitch profiles that reduce design-driving loads, in a fully automated way.

GAME: GAlaxy Machine learning for Emission lines

NASA Astrophysics Data System (ADS)

Ucci, G.; Ferrara, A.; Pallottini, A.; Gallerani, S.

2018-06-01

We present an updated, optimized version of GAME (GAlaxy Machine learning for Emission lines), a code designed to infer key interstellar medium physical properties from emission line intensities of ultraviolet /optical/far-infrared galaxy spectra. The improvements concern (a) an enlarged spectral library including Pop III stars, (b) the inclusion of spectral noise in the training procedure, and (c) an accurate evaluation of uncertainties. We extensively validate the optimized code and compare its performance against empirical methods and other available emission line codes (PYQZ and HII-CHI-MISTRY) on a sample of 62 SDSS stacked galaxy spectra and 75 observed HII regions. Very good agreement is found for metallicity. However, ionization parameters derived by GAME tend to be higher. We show that this is due to the use of too limited libraries in the other codes. The main advantages of GAME are the simultaneous use of all the measured spectral lines and the extremely short computational times. We finally discuss the code potential and limitations.

CEPC-SPPC accelerator status towards CDR

NASA Astrophysics Data System (ADS)

Gao, J.

2017-12-01

In this paper we will give an introduction to the Circular Electron Positron Collider (CEPC). The scientific background, physics goal, the collider design requirements and the conceptual design principle of the CEPC are described. On the CEPC accelerator, the optimization of parameter designs for the CEPC with different energies, machine lengths, single ring and crab-waist collision partial double ring, advanced partial double ring and fully partial double ring options, etc. have been discussed systematically, and compared. The CEPC accelerator baseline and alternative designs have been proposed based on the luminosity potential in relation with the design goals. The CEPC sub-systems, such as the collider main ring, booster, electron positron injector, etc. have also been introduced. The detector and the MAchine-Detector Interface (MDI) design have been briefly mentioned. Finally, the optimization design of the Super Proton-Proton Collider (SppC), its energy and luminosity potentials, in the same tunnel of the CEPC are also discussed. The CEPC-SppC Progress Report (2015-2016) has been published.

An IPSO-SVM algorithm for security state prediction of mine production logistics system

NASA Astrophysics Data System (ADS)

Zhang, Yanliang; Lei, Junhui; Ma, Qiuli; Chen, Xin; Bi, Runfang

2017-06-01

A theoretical basis for the regulation of corporate security warning and resources was provided in order to reveal the laws behind the security state in mine production logistics. Considering complex mine production logistics system and the variable is difficult to acquire, a superior security status predicting model of mine production logistics system based on the improved particle swarm optimization and support vector machine (IPSO-SVM) is proposed in this paper. Firstly, through the linear adjustments of inertia weight and learning weights, the convergence speed and search accuracy are enhanced with the aim to deal with situations associated with the changeable complexity and the data acquisition difficulty. The improved particle swarm optimization (IPSO) is then introduced to resolve the problem of parameter settings in traditional support vector machines (SVM). At the same time, security status index system is built to determine the classification standards of safety status. The feasibility and effectiveness of this method is finally verified using the experimental results.

Optimal classification for the diagnosis of duchenne muscular dystrophy images using support vector machines.

PubMed

Zhang, Ming-Huan; Ma, Jun-Shan; Shen, Ying; Chen, Ying

2016-09-01

This study aimed to investigate the optimal support vector machines (SVM)-based classifier of duchenne muscular dystrophy (DMD) magnetic resonance imaging (MRI) images. T1-weighted (T1W) and T2-weighted (T2W) images of the 15 boys with DMD and 15 normal controls were obtained. Textural features of the images were extracted and wavelet decomposed, and then, principal features were selected. Scale transform was then performed for MRI images. Afterward, SVM-based classifiers of MRI images were analyzed based on the radical basis function and decomposition levels. The cost (C) parameter and kernel parameter [Formula: see text] were used for classification. Then, the optimal SVM-based classifier, expressed as [Formula: see text]), was identified by performance evaluation (sensitivity, specificity and accuracy). Eight of 12 textural features were selected as principal features (eigenvalues [Formula: see text]). The 16 SVM-based classifiers were obtained using combination of (C, [Formula: see text]), and those with lower C and [Formula: see text] values showed higher performances, especially classifier of [Formula: see text]). The SVM-based classifiers of T1W images showed higher performance than T1W images at the same decomposition level. The T1W images in classifier of [Formula: see text]) at level 2 decomposition showed the highest performance of all, and its overall correct sensitivity, specificity, and accuracy reached 96.9, 97.3, and 97.1 %, respectively. The T1W images in SVM-based classifier [Formula: see text] at level 2 decomposition showed the highest performance of all, demonstrating that it was the optimal classification for the diagnosis of DMD.

Product modular design incorporating preventive maintenance issues

NASA Astrophysics Data System (ADS)

Gao, Yicong; Feng, Yixiong; Tan, Jianrong

2016-03-01

Traditional modular design methods lead to product maintenance problems, because the module form of a system is created according to either the function requirements or the manufacturing considerations. For solving these problems, a new modular design method is proposed with the considerations of not only the traditional function related attributes, but also the maintenance related ones. First, modularity parameters and modularity scenarios for product modularity are defined. Then the reliability and economic assessment models of product modularity strategies are formulated with the introduction of the effective working age of modules. A mathematical model used to evaluate the difference among the modules of the product so that the optimal module of the product can be established. After that, a multi-objective optimization problem based on metrics for preventive maintenance interval different degrees and preventive maintenance economics is formulated for modular optimization. Multi-objective GA is utilized to rapidly approximate the Pareto set of optimal modularity strategy trade-offs between preventive maintenance cost and preventive maintenance interval difference degree. Finally, a coordinate CNC boring machine is adopted to depict the process of product modularity. In addition, two factorial design experiments based on the modularity parameters are constructed and analyzed. These experiments investigate the impacts of these parameters on the optimal modularity strategies and the structure of module. The research proposes a new modular design method, which may help to improve the maintainability of product in modular design.

Irredundant Sequential Machines Via Optimal Logic Synthesis

DTIC Science & Technology

1989-10-01

1989 Irredundant Sequential Machines Via Optimal Logic Synthesis NSrinivas Devadas , Hi-Keung Tony Ma, A. Richard Newton, and Alberto Sangiovanni- S...Agency under contract N00014-87-K-0825, and a grant from AT & T Bell Laboratories. Author Information Devadas : Department of Electrical Engineering...Sequential Machines Via Optimal Logic Synthesis Srinivas Devadas * Hi-Keung Tony ha. A. Richard Newton and Alberto Sangiovanni-Viucentelli Department of

A Sensor Dynamic Measurement Error Prediction Model Based on NAPSO-SVM.

PubMed

Jiang, Minlan; Jiang, Lan; Jiang, Dingde; Li, Fei; Song, Houbing

2018-01-15

Dynamic measurement error correction is an effective way to improve sensor precision. Dynamic measurement error prediction is an important part of error correction, and support vector machine (SVM) is often used for predicting the dynamic measurement errors of sensors. Traditionally, the SVM parameters were always set manually, which cannot ensure the model's performance. In this paper, a SVM method based on an improved particle swarm optimization (NAPSO) is proposed to predict the dynamic measurement errors of sensors. Natural selection and simulated annealing are added in the PSO to raise the ability to avoid local optima. To verify the performance of NAPSO-SVM, three types of algorithms are selected to optimize the SVM's parameters: the particle swarm optimization algorithm (PSO), the improved PSO optimization algorithm (NAPSO), and the glowworm swarm optimization (GSO). The dynamic measurement error data of two sensors are applied as the test data. The root mean squared error and mean absolute percentage error are employed to evaluate the prediction models' performances. The experimental results show that among the three tested algorithms the NAPSO-SVM method has a better prediction precision and a less prediction errors, and it is an effective method for predicting the dynamic measurement errors of sensors.

Joint Machine Learning and Game Theory for Rate Control in High Efficiency Video Coding.

PubMed

Gao, Wei; Kwong, Sam; Jia, Yuheng

2017-08-25

In this paper, a joint machine learning and game theory modeling (MLGT) framework is proposed for inter frame coding tree unit (CTU) level bit allocation and rate control (RC) optimization in High Efficiency Video Coding (HEVC). First, a support vector machine (SVM) based multi-classification scheme is proposed to improve the prediction accuracy of CTU-level Rate-Distortion (R-D) model. The legacy "chicken-and-egg" dilemma in video coding is proposed to be overcome by the learning-based R-D model. Second, a mixed R-D model based cooperative bargaining game theory is proposed for bit allocation optimization, where the convexity of the mixed R-D model based utility function is proved, and Nash bargaining solution (NBS) is achieved by the proposed iterative solution search method. The minimum utility is adjusted by the reference coding distortion and frame-level Quantization parameter (QP) change. Lastly, intra frame QP and inter frame adaptive bit ratios are adjusted to make inter frames have more bit resources to maintain smooth quality and bit consumption in the bargaining game optimization. Experimental results demonstrate that the proposed MLGT based RC method can achieve much better R-D performances, quality smoothness, bit rate accuracy, buffer control results and subjective visual quality than the other state-of-the-art one-pass RC methods, and the achieved R-D performances are very close to the performance limits from the FixedQP method.

Design of static synchronous series compensator based damping controller employing invasive weed optimization algorithm.

PubMed

Ahmed, Ashik; Al-Amin, Rasheduzzaman; Amin, Ruhul

2014-01-01

This paper proposes designing of Static Synchronous Series Compensator (SSSC) based damping controller to enhance the stability of a Single Machine Infinite Bus (SMIB) system by means of Invasive Weed Optimization (IWO) technique. Conventional PI controller is used as the SSSC damping controller which takes rotor speed deviation as the input. The damping controller parameters are tuned based on time integral of absolute error based cost function using IWO. Performance of IWO based controller is compared to that of Particle Swarm Optimization (PSO) based controller. Time domain based simulation results are presented and performance of the controllers under different loading conditions and fault scenarios is studied in order to illustrate the effectiveness of the IWO based design approach.

Divergent estimation error in portfolio optimization and in linear regression

NASA Astrophysics Data System (ADS)

Kondor, I.; Varga-Haszonits, I.

2008-08-01

The problem of estimation error in portfolio optimization is discussed, in the limit where the portfolio size N and the sample size T go to infinity such that their ratio is fixed. The estimation error strongly depends on the ratio N/T and diverges for a critical value of this parameter. This divergence is the manifestation of an algorithmic phase transition, it is accompanied by a number of critical phenomena, and displays universality. As the structure of a large number of multidimensional regression and modelling problems is very similar to portfolio optimization, the scope of the above observations extends far beyond finance, and covers a large number of problems in operations research, machine learning, bioinformatics, medical science, economics, and technology.

Intensification of the Reverse Cationic Flotation of Hematite Ores with Optimization of Process and Hydrodynamic Parameters of Flotation Cell

NASA Astrophysics Data System (ADS)

Poperechnikova, O. Yu; Filippov, L. O.; Shumskaya, E. N.; Filippova, I. V.

2017-07-01

The demand of high grade iron ore concentrates is a major issue due to the depletion of rich iron-bearing ores and high competitiveness in the iron ore market. Iron ore production is forced out to upgrade flowsheets to decrease the silica content in the pelettes. Different types of ore have different mineral composition and texture-structural features which require different mineral processing methods and technologies. The paper presents a comparative study of the cationic and anionic flotation routes to process a fine-grain oxidized iron ore. The modified carboxymethyl cellulose was found as the most efficient depressant in reverse cationic flotation. The results of flotation optimization of hematite ores using matrix of second-order center rotatable uniform design allowed to define the collector concentration, impeller rotation speed and air flowrate as the main flotation parameters impacting on the iron ore concentrate quality and iron recovery in a laboratory flotation machine. These parameters have been selected as independent during the experiments.

Evolutionary algorithm optimization of biological learning parameters in a biomimetic neuroprosthesis

PubMed Central

Dura-Bernal, S.; Neymotin, S. A.; Kerr, C. C.; Sivagnanam, S.; Majumdar, A.; Francis, J. T.; Lytton, W. W.

2017-01-01

Biomimetic simulation permits neuroscientists to better understand the complex neuronal dynamics of the brain. Embedding a biomimetic simulation in a closed-loop neuroprosthesis, which can read and write signals from the brain, will permit applications for amelioration of motor, psychiatric, and memory-related brain disorders. Biomimetic neuroprostheses require real-time adaptation to changes in the external environment, thus constituting an example of a dynamic data-driven application system. As model fidelity increases, so does the number of parameters and the complexity of finding appropriate parameter configurations. Instead of adapting synaptic weights via machine learning, we employed major biological learning methods: spike-timing dependent plasticity and reinforcement learning. We optimized the learning metaparameters using evolutionary algorithms, which were implemented in parallel and which used an island model approach to obtain sufficient speed. We employed these methods to train a cortical spiking model to utilize macaque brain activity, indicating a selected target, to drive a virtual musculoskeletal arm with realistic anatomical and biomechanical properties to reach to that target. The optimized system was able to reproduce macaque data from a comparable experimental motor task. These techniques can be used to efficiently tune the parameters of multiscale systems, linking realistic neuronal dynamics to behavior, and thus providing a useful tool for neuroscience and neuroprosthetics. PMID:29200477

Study of process parameter on mist lubrication of Titanium (Grade 5) alloy

NASA Astrophysics Data System (ADS)

Maity, Kalipada; Pradhan, Swastik

2017-02-01

This paper deals with the machinability of Ti-6Al-4V alloy with mist cooling lubrication using carbide inserts. The influence of process parameter on the cutting forces, evolution of tool wear, surface finish of the workpiece, material removal rate and chip reduction coefficient have been investigated. Weighted principal component analysis coupled with grey relational analysis optimization is applied to identify the optimum setting of the process parameter. Optimal condition of the process parameter was cutting speed at 160 m/min, feed at 0.16 mm/rev and depth of cut at 1.6 mm. Effects of cutting speed and depth of cut on the type of chips formation were observed. Most of the chips forms were long tubular and long helical type. Image analyses of the segmented chip were examined to study the shape and size of the saw tooth profile of serrated chips. It was found that by increasing cutting speed from 95 m/min to 160 m/min, the free surface lamella of the chips increased and the visibility of the saw tooth segment became clearer.

Multi Objective Optimization of Multi Wall Carbon Nanotube Based Nanogrinding Wheel Using Grey Relational and Regression Analysis

NASA Astrophysics Data System (ADS)

Sethuramalingam, Prabhu; Vinayagam, Babu Kupusamy

2016-07-01

Carbon nanotube mixed grinding wheel is used in the grinding process to analyze the surface characteristics of AISI D2 tool steel material. Till now no work has been carried out using carbon nanotube based grinding wheel. Carbon nanotube based grinding wheel has excellent thermal conductivity and good mechanical properties which are used to improve the surface finish of the workpiece. In the present study, the multi response optimization of process parameters like surface roughness and metal removal rate of grinding process of single wall carbon nanotube (CNT) in mixed cutting fluids is undertaken using orthogonal array with grey relational analysis. Experiments are performed with designated grinding conditions obtained using the L9 orthogonal array. Based on the results of the grey relational analysis, a set of optimum grinding parameters is obtained. Using the analysis of variance approach the significant machining parameters are found. Empirical model for the prediction of output parameters has been developed using regression analysis and the results are compared empirically, for conditions of with and without CNT grinding wheel in grinding process.

Expanded explorations into the optimization of an energy function for protein design

PubMed Central

Huang, Yao-ming; Bystroff, Christopher

2014-01-01

Nature possesses a secret formula for the energy as a function of the structure of a protein. In protein design, approximations are made to both the structural representation of the molecule and to the form of the energy equation, such that the existence of a general energy function for proteins is by no means guaranteed. Here we present new insights towards the application of machine learning to the problem of finding a general energy function for protein design. Machine learning requires the definition of an objective function, which carries with it the implied definition of success in protein design. We explored four functions, consisting of two functional forms, each with two criteria for success. Optimization was carried out by a Monte Carlo search through the space of all variable parameters. Cross-validation of the optimized energy function against a test set gave significantly different results depending on the choice of objective function, pointing to relative correctness of the built-in assumptions. Novel energy cross-terms correct for the observed non-additivity of energy terms and an imbalance in the distribution of predicted amino acids. This paper expands on the work presented at ACM-BCB, Orlando FL , October 2012. PMID:24384706

Additive manufacturing of reflective optics: evaluating finishing methods

NASA Astrophysics Data System (ADS)

Leuteritz, G.; Lachmayer, R.

2018-02-01

Individually shaped light distributions become more and more important in lighting technologies and thus the importance of additively manufactured reflectors increases significantly. The vast field of applications ranges from automotive lighting to medical imaging and bolsters the statement. However, the surfaces of additively manufactured reflectors suffer from insufficient optical properties even when manufactured using optimized process parameters for the Selective Laser Melting (SLM) process. Therefore post-process treatments of reflectors are necessary in order to further enhance their optical quality. This work concentrates on the effectiveness of post-process procedures for reflective optics. Based on already optimized aluminum reflectors, which are manufactured with a SLM machine, the parts are differently machined after the SLM process. Selected finishing methods like laser polishing, sputtering or sand blasting are applied and their effects quantified and compared. The post-process procedures are investigated on their impact on surface roughness and reflectance as well as geometrical precision. For each finishing method a demonstrator will be created and compared to a fully milled sample and among themselves. Ultimately, guidelines are developed in order to figure out the optimal treatment of additively manufactured reflectors regarding their optical and geometrical properties. Simulations of the light distributions will be validated with the developed demonstrators.

Efficient machining of ultra precise steel moulds with freeform surfaces

NASA Astrophysics Data System (ADS)

Bulla, B.; Robertson, D. J.; Dambon, O.; Klocke, F.

2013-09-01

Ultra precision diamond turning of hardened steel to produce optical quality surfaces can be realized by applying an ultrasonic assisted process. With this technology optical moulds used typically for injection moulding can be machined directly from steel without the requirement to overcoat the mould with a diamond machinable material such as Nickel Phosphor. This has both the advantage of increasing the mould tool lifetime and also reducing manufacture costs by dispensing with the relatively expensive plating process. This publication will present results we have obtained for generating free form moulds in hardened steel by means of ultrasonic assisted diamond turning with a vibration frequency of 80 kHz. To provide a baseline with which to characterize the system performance we perform plane cutting experiments on different steel alloys with different compositions. The baseline machining results provides us information on the surface roughness and on tool wear caused during machining and we relate these to material composition. Moving on to freeform surfaces, we will present a theoretical background to define the machine program parameters for generating free forms by applying slow slide servo machining techniques. A solution for optimal part generation is introduced which forms the basis for the freeform machining experiments. The entire process chain, from the raw material through to ultra precision machining is presented, with emphasis on maintaining surface alignment when moving a component from CNC pre-machining to final machining using ultrasonic assisted diamond turning. The free form moulds are qualified on the basis of the surface roughness measurements and a form error map comparing the machined surface with the originally defined surface. These experiments demonstrate the feasibility of efficient free form machining applying ultrasonic assisted diamond turning of hardened steel.

Analytical Model-Based Design Optimization of a Transverse Flux Machine

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hasan, Iftekhar; Husain, Tausif; Sozer, Yilmaz

This paper proposes an analytical machine design tool using magnetic equivalent circuit (MEC)-based particle swarm optimization (PSO) for a double-sided, flux-concentrating transverse flux machine (TFM). The magnetic equivalent circuit method is applied to analytically establish the relationship between the design objective and the input variables of prospective TFM designs. This is computationally less intensive and more time efficient than finite element solvers. A PSO algorithm is then used to design a machine with the highest torque density within the specified power range along with some geometric design constraints. The stator pole length, magnet length, and rotor thickness are the variablesmore » that define the optimization search space. Finite element analysis (FEA) was carried out to verify the performance of the MEC-PSO optimized machine. The proposed analytical design tool helps save computation time by at least 50% when compared to commercial FEA-based optimization programs, with results found to be in agreement with less than 5% error.« less

Hierarchical winner-take-all particle swarm optimization social network for neural model fitting.

PubMed

Coventry, Brandon S; Parthasarathy, Aravindakshan; Sommer, Alexandra L; Bartlett, Edward L

2017-02-01

Particle swarm optimization (PSO) has gained widespread use as a general mathematical programming paradigm and seen use in a wide variety of optimization and machine learning problems. In this work, we introduce a new variant on the PSO social network and apply this method to the inverse problem of input parameter selection from recorded auditory neuron tuning curves. The topology of a PSO social network is a major contributor to optimization success. Here we propose a new social network which draws influence from winner-take-all coding found in visual cortical neurons. We show that the winner-take-all network performs exceptionally well on optimization problems with greater than 5 dimensions and runs at a lower iteration count as compared to other PSO topologies. Finally we show that this variant of PSO is able to recreate auditory frequency tuning curves and modulation transfer functions, making it a potentially useful tool for computational neuroscience models.

Technique of optimization of minimum temperature driving forces in the heaters of regeneration system of a steam turbine unit

NASA Astrophysics Data System (ADS)

Shamarokov, A. S.; Zorin, V. M.; Dai, Fam Kuang

2016-03-01

At the current stage of development of nuclear power engineering, high demands on nuclear power plants (NPP), including on their economy, are made. In these conditions, improving the quality of NPP means, in particular, the need to reasonably choose the values of numerous managed parameters of technological (heat) scheme. Furthermore, the chosen values should correspond to the economic conditions of NPP operation, which are postponed usually a considerable time interval from the point of time of parameters' choice. The article presents the technique of optimization of controlled parameters of the heat circuit of a steam turbine plant for the future. Its particularity is to obtain the results depending on a complex parameter combining the external economic and operating parameters that are relatively stable under the changing economic environment. The article presents the results of optimization according to this technique of the minimum temperature driving forces in the surface heaters of the heat regeneration system of the steam turbine plant of a K-1200-6.8/50 type. For optimization, the collector-screen heaters of high and low pressure developed at the OAO All-Russia Research and Design Institute of Nuclear Power Machine Building, which, in the authors' opinion, have the certain advantages over other types of heaters, were chosen. The optimality criterion in the task was the change in annual reduced costs for NPP compared to the version accepted as the baseline one. The influence on the decision of the task of independent variables that are not included in the complex parameter was analyzed. An optimization task was decided using the alternating-variable descent method. The obtained values of minimum temperature driving forces can guide the design of new nuclear plants with a heat circuit, similar to that accepted in the considered task.

Comparing SVM and ANN based Machine Learning Methods for Species Identification of Food Contaminating Beetles.

PubMed

Bisgin, Halil; Bera, Tanmay; Ding, Hongjian; Semey, Howard G; Wu, Leihong; Liu, Zhichao; Barnes, Amy E; Langley, Darryl A; Pava-Ripoll, Monica; Vyas, Himansu J; Tong, Weida; Xu, Joshua

2018-04-25

Insect pests, such as pantry beetles, are often associated with food contaminations and public health risks. Machine learning has the potential to provide a more accurate and efficient solution in detecting their presence in food products, which is currently done manually. In our previous research, we demonstrated such feasibility where Artificial Neural Network (ANN) based pattern recognition techniques could be implemented for species identification in the context of food safety. In this study, we present a Support Vector Machine (SVM) model which improved the average accuracy up to 85%. Contrary to this, the ANN method yielded ~80% accuracy after extensive parameter optimization. Both methods showed excellent genus level identification, but SVM showed slightly better accuracy  for most species. Highly accurate species level identification remains a challenge, especially in distinguishing between species from the same genus which may require improvements in both imaging and machine learning techniques. In summary, our work does illustrate a new SVM based technique and provides a good comparison with the ANN model in our context. We believe such insights will pave better way forward for the application of machine learning towards species identification and food safety.

A new optimization tool path planning for 3-axis end milling of free-form surfaces based on efficient machining intervals

NASA Astrophysics Data System (ADS)

Vu, Duy-Duc; Monies, Frédéric; Rubio, Walter

2018-05-01

A large number of studies, based on 3-axis end milling of free-form surfaces, seek to optimize tool path planning. Approaches try to optimize the machining time by reducing the total tool path length while respecting the criterion of the maximum scallop height. Theoretically, the tool path trajectories that remove the most material follow the directions in which the machined width is the largest. The free-form surface is often considered as a single machining area. Therefore, the optimization on the entire surface is limited. Indeed, it is difficult to define tool trajectories with optimal feed directions which generate largest machined widths. Another limiting point of previous approaches for effectively reduce machining time is the inadequate choice of the tool. Researchers use generally a spherical tool on the entire surface. However, the gains proposed by these different methods developed with these tools lead to relatively small time savings. Therefore, this study proposes a new method, using toroidal milling tools, for generating toolpaths in different regions on the machining surface. The surface is divided into several regions based on machining intervals. These intervals ensure that the effective radius of the tool, at each cutter-contact points on the surface, is always greater than the radius of the tool in an optimized feed direction. A parallel plane strategy is then used on the sub-surfaces with an optimal specific feed direction for each sub-surface. This method allows one to mill the entire surface with efficiency greater than with the use of a spherical tool. The proposed method is calculated and modeled using Maple software to find optimal regions and feed directions in each region. This new method is tested on a free-form surface. A comparison is made with a spherical cutter to show the significant gains obtained with a toroidal milling cutter. Comparisons with CAM software and experimental validations are also done. The results show the efficiency of the method.

Integrating Natural Language Processing and Machine Learning Algorithms to Categorize Oncologic Response in Radiology Reports.

PubMed

Chen, Po-Hao; Zafar, Hanna; Galperin-Aizenberg, Maya; Cook, Tessa

2018-04-01

A significant volume of medical data remains unstructured. Natural language processing (NLP) and machine learning (ML) techniques have shown to successfully extract insights from radiology reports. However, the codependent effects of NLP and ML in this context have not been well-studied. Between April 1, 2015 and November 1, 2016, 9418 cross-sectional abdomen/pelvis CT and MR examinations containing our internal structured reporting element for cancer were separated into four categories: Progression, Stable Disease, Improvement, or No Cancer. We combined each of three NLP techniques with five ML algorithms to predict the assigned label using the unstructured report text and compared the performance of each combination. The three NLP algorithms included term frequency-inverse document frequency (TF-IDF), term frequency weighting (TF), and 16-bit feature hashing. The ML algorithms included logistic regression (LR), random decision forest (RDF), one-vs-all support vector machine (SVM), one-vs-all Bayes point machine (BPM), and fully connected neural network (NN). The best-performing NLP model consisted of tokenized unigrams and bigrams with TF-IDF. Increasing N-gram length yielded little to no added benefit for most ML algorithms. With all parameters optimized, SVM had the best performance on the test dataset, with 90.6 average accuracy and F score of 0.813. The interplay between ML and NLP algorithms and their effect on interpretation accuracy is complex. The best accuracy is achieved when both algorithms are optimized concurrently.

Design of Clinical Support Systems Using Integrated Genetic Algorithm and Support Vector Machine

NASA Astrophysics Data System (ADS)

Chen, Yung-Fu; Huang, Yung-Fa; Jiang, Xiaoyi; Hsu, Yuan-Nian; Lin, Hsuan-Hung

Clinical decision support system (CDSS) provides knowledge and specific information for clinicians to enhance diagnostic efficiency and improving healthcare quality. An appropriate CDSS can highly elevate patient safety, improve healthcare quality, and increase cost-effectiveness. Support vector machine (SVM) is believed to be superior to traditional statistical and neural network classifiers. However, it is critical to determine suitable combination of SVM parameters regarding classification performance. Genetic algorithm (GA) can find optimal solution within an acceptable time, and is faster than greedy algorithm with exhaustive searching strategy. By taking the advantage of GA in quickly selecting the salient features and adjusting SVM parameters, a method using integrated GA and SVM (IGS), which is different from the traditional method with GA used for feature selection and SVM for classification, was used to design CDSSs for prediction of successful ventilation weaning, diagnosis of patients with severe obstructive sleep apnea, and discrimination of different cell types form Pap smear. The results show that IGS is better than methods using SVM alone or linear discriminator.

Tuning support vector machines for minimax and Neyman-Pearson classification.

PubMed

Davenport, Mark A; Baraniuk, Richard G; Scott, Clayton D

2010-10-01

This paper studies the training of support vector machine (SVM) classifiers with respect to the minimax and Neyman-Pearson criteria. In principle, these criteria can be optimized in a straightforward way using a cost-sensitive SVM. In practice, however, because these criteria require especially accurate error estimation, standard techniques for tuning SVM parameters, such as cross-validation, can lead to poor classifier performance. To address this issue, we first prove that the usual cost-sensitive SVM, here called the 2C-SVM, is equivalent to another formulation called the 2nu-SVM. We then exploit a characterization of the 2nu-SVM parameter space to develop a simple yet powerful approach to error estimation based on smoothing. In an extensive experimental study, we demonstrate that smoothing significantly improves the accuracy of cross-validation error estimates, leading to dramatic performance gains. Furthermore, we propose coordinate descent strategies that offer significant gains in computational efficiency, with little to no loss in performance.

Multiple-Point Temperature Gradient Algorithm for Ring Laser Gyroscope Bias Compensation

PubMed Central

Li, Geng; Zhang, Pengfei; Wei, Guo; Xie, Yuanping; Yu, Xudong; Long, Xingwu

2015-01-01

To further improve ring laser gyroscope (RLG) bias stability, a multiple-point temperature gradient algorithm is proposed for RLG bias compensation in this paper. Based on the multiple-point temperature measurement system, a complete thermo-image of the RLG block is developed. Combined with the multiple-point temperature gradients between different points of the RLG block, the particle swarm optimization algorithm is used to tune the support vector machine (SVM) parameters, and an optimized design for selecting the thermometer locations is also discussed. The experimental results validate the superiority of the introduced method and enhance the precision and generalizability in the RLG bias compensation model. PMID:26633401

A Machine Learning and Optimization Toolkit for the Swarm

DTIC Science & Technology

2014-11-17

Machine   Learning  and  Op0miza0on   Toolkit  for  the  Swarm   Ilge  Akkaya,  Shuhei  Emoto...3. DATES COVERED 00-00-2014 to 00-00-2014 4. TITLE AND SUBTITLE A Machine Learning and Optimization Toolkit for the Swarm 5a. CONTRACT NUMBER... machine   learning   methodologies  by  providing  the  right  interfaces  between   machine   learning  tools  and

Recent developments in turning hardened steels - A review

NASA Astrophysics Data System (ADS)

Sivaraman, V.; Prakash, S.

2017-05-01

Hard materials ranging from HRC 45 - 68 such as hardened AISI H13, AISI 4340, AISI 52100, D2 STL, D3 STEEL Steel etc., need super hard tool materials to machine. Turning of these hard materials is termed as hard turning. Hard turning makes possible direct machining of the hard materials and also eliminates the lubricant requirement and thus favoring dry machining. Hard turning is a finish turning process and hence conventional grinding is not required. Development of the new advanced super hard tool materials such as ceramic inserts, Cubic Boron Nitride, Polycrystalline Cubic Boron Nitride etc. enabled the turning of these materials. PVD and CVD methods of coating have made easier the production of single and multi layered coated tool inserts. Coatings of TiN, TiAlN, TiC, Al2O3, AlCrN over cemented carbide inserts has lead to the machining of difficult to machine materials. Advancement in the process of hard machining paved way for better surface finish, long tool life, reduced tool wear, cutting force and cutting temperatures. Micro and Nano coated carbide inserts, nanocomposite coated PCBN inserts, micro and nano CBN coated carbide inserts and similar developments have made machining of hardened steels much easier and economical. In this paper, broad literature review on turning of hardened steels including optimizing process parameters, cooling requirements, different tool materials etc., are done.

Shot-by-shot Spectrum Model for Rod-pinch, Pulsed Radiography Machines

DOE Office of Scientific and Technical Information (OSTI.GOV)

Wood, William Monford

A simplified model of bremsstrahlung production is developed for determining the x-ray spectrum output of a rod-pinch radiography machine, on a shot-by-shot basis, using the measured voltage, V(t), and current, I(t). The motivation for this model is the need for an agile means of providing shot-by-shot spectrum prediction, from a laptop or desktop computer, for quantitative radiographic analysis. Simplifying assumptions are discussed, and the model is applied to the Cygnus rod-pinch machine. Output is compared to wedge transmission data for a series of radiographs from shots with identical target objects. Resulting model enables variation of parameters in real time, thusmore » allowing for rapid optimization of the model across many shots. “Goodness of fit” is compared with output from LSP Particle-In-Cell code, as well as the Monte Carlo Neutron Propagation with Xrays (“MCNPX”) model codes, and is shown to provide an excellent predictive representation of the spectral output of the Cygnus machine. In conclusion, improvements to the model, specifically for application to other geometries, are discussed.« less

Shot-by-shot Spectrum Model for Rod-pinch, Pulsed Radiography Machines

DOE PAGES

Wood, William Monford

2018-02-07

A simplified model of bremsstrahlung production is developed for determining the x-ray spectrum output of a rod-pinch radiography machine, on a shot-by-shot basis, using the measured voltage, V(t), and current, I(t). The motivation for this model is the need for an agile means of providing shot-by-shot spectrum prediction, from a laptop or desktop computer, for quantitative radiographic analysis. Simplifying assumptions are discussed, and the model is applied to the Cygnus rod-pinch machine. Output is compared to wedge transmission data for a series of radiographs from shots with identical target objects. Resulting model enables variation of parameters in real time, thusmore » allowing for rapid optimization of the model across many shots. “Goodness of fit” is compared with output from LSP Particle-In-Cell code, as well as the Monte Carlo Neutron Propagation with Xrays (“MCNPX”) model codes, and is shown to provide an excellent predictive representation of the spectral output of the Cygnus machine. In conclusion, improvements to the model, specifically for application to other geometries, are discussed.« less

Crystal Orientation Effect on the Subsurface Deformation of Monocrystalline Germanium in Nanometric Cutting.

PubMed

Lai, Min; Zhang, Xiaodong; Fang, Fengzhou

2017-12-01

Molecular dynamics simulations of nanometric cutting on monocrystalline germanium are conducted to investigate the subsurface deformation during and after nanometric cutting. The continuous random network model of amorphous germanium is established by molecular dynamics simulation, and its characteristic parameters are extracted to compare with those of the machined deformed layer. The coordination number distribution and radial distribution function (RDF) show that the machined surface presents the similar amorphous state. The anisotropic subsurface deformation is studied by nanometric cutting on the (010), (101), and (111) crystal planes of germanium, respectively. The deformed structures are prone to extend along the 110 slip system, which leads to the difference in the shape and thickness of the deformed layer on various directions and crystal planes. On machined surface, the greater thickness of subsurface deformed layer induces the greater surface recovery height. In order to get the critical thickness limit of deformed layer on machined surface of germanium, the optimized cutting direction on each crystal plane is suggested according to the relevance of the nanometric cutting to the nanoindentation.

Shot-by-shot spectrum model for rod-pinch, pulsed radiography machines

NASA Astrophysics Data System (ADS)

Wood, Wm M.

2018-02-01

A simplified model of bremsstrahlung production is developed for determining the x-ray spectrum output of a rod-pinch radiography machine, on a shot-by-shot basis, using the measured voltage, V(t), and current, I(t). The motivation for this model is the need for an agile means of providing shot-by-shot spectrum prediction, from a laptop or desktop computer, for quantitative radiographic analysis. Simplifying assumptions are discussed, and the model is applied to the Cygnus rod-pinch machine. Output is compared to wedge transmission data for a series of radiographs from shots with identical target objects. Resulting model enables variation of parameters in real time, thus allowing for rapid optimization of the model across many shots. "Goodness of fit" is compared with output from LSP Particle-In-Cell code, as well as the Monte Carlo Neutron Propagation with Xrays ("MCNPX") model codes, and is shown to provide an excellent predictive representation of the spectral output of the Cygnus machine. Improvements to the model, specifically for application to other geometries, are discussed.

Machining fixture layout optimization using particle swarm optimization algorithm

NASA Astrophysics Data System (ADS)

Dou, Jianping; Wang, Xingsong; Wang, Lei

2011-05-01

Optimization of fixture layout (locator and clamp locations) is critical to reduce geometric error of the workpiece during machining process. In this paper, the application of particle swarm optimization (PSO) algorithm is presented to minimize the workpiece deformation in the machining region. A PSO based approach is developed to optimize fixture layout through integrating ANSYS parametric design language (APDL) of finite element analysis to compute the objective function for a given fixture layout. Particle library approach is used to decrease the total computation time. The computational experiment of 2D case shows that the numbers of function evaluations are decreased about 96%. Case study illustrates the effectiveness and efficiency of the PSO based optimization approach.

Simultaneous Scheduling of Jobs, AGVs and Tools Considering Tool Transfer Times in Multi Machine FMS By SOS Algorithm

NASA Astrophysics Data System (ADS)

Sivarami Reddy, N.; Ramamurthy, D. V., Dr.; Prahlada Rao, K., Dr.

2017-08-01

This article addresses simultaneous scheduling of machines, AGVs and tools where machines are allowed to share the tools considering transfer times of jobs and tools between machines, to generate best optimal sequences that minimize makespan in a multi-machine Flexible Manufacturing System (FMS). Performance of FMS is expected to improve by effective utilization of its resources, by proper integration and synchronization of their scheduling. Symbiotic Organisms Search (SOS) algorithm is a potent tool which is a better alternative for solving optimization problems like scheduling and proven itself. The proposed SOS algorithm is tested on 22 job sets with makespan as objective for scheduling of machines and tools where machines are allowed to share tools without considering transfer times of jobs and tools and the results are compared with the results of existing methods. The results show that the SOS has outperformed. The same SOS algorithm is used for simultaneous scheduling of machines, AGVs and tools where machines are allowed to share tools considering transfer times of jobs and tools to determine the best optimal sequences that minimize makespan.

Influence de la pression de mise en forme sur le detourage de stratifies carbone/epoxy

NASA Astrophysics Data System (ADS)

Coulon, Pierre

The need to reduce the weight of structures has led to an increasing use of composite materials in the aerospace industry. To meet the required tolerances and quality, the manufacturing processes must adapt to these new materials. The machining is one of these processes that need to be optimized to control the final part quality. This experimental study aims at understanding the relationship between manufacturing parameters of quasi-isotropic carbon fibre laminates and their machinability. After a preliminary study, it was concluded that curing pressure in autoclave was the most influential manufacturing parameter. The pressure is linked, experimentally, to the void content and then to the mechanical properties and finally to the cutting forces. The research methodology is based on a classic multifactorial design of experience in which the input factors are the curing pressure, feed rate and cutting speed. This study confirms the correlation existing between the curing pressure and void content as well as the relationship between the curing pressure and mechanical properties. The new element of this study is the correlation between the curing pressure and cutting forces during trimming. This last point is interesting because it leads to the development of a predictive model for cutting forces. Although the results of this study are hardly generalizable to other materials, the prediction of cutting forces is possible. Quality after machining is also studied through two criteria: the roughness measurement and evaluation of delamination. Roughness is measured using a roughness depth measuring equipment optimized to make best use of this technique. The study confirms the patterns already observed without being able to improve the characterization of cutting quality. Keywords: composites, trimming, curing pressure, cutting forces, void content, ILSS, delamination, roughness.

Evaluation of CFETR as a Fusion Nuclear Science Facility using multiple system codes

NASA Astrophysics Data System (ADS)

Chan, V. S.; Costley, A. E.; Wan, B. N.; Garofalo, A. M.; Leuer, J. A.

2015-02-01

This paper presents the results of a multi-system codes benchmarking study of the recently published China Fusion Engineering Test Reactor (CFETR) pre-conceptual design (Wan et al 2014 IEEE Trans. Plasma Sci. 42 495). Two system codes, General Atomics System Code (GASC) and Tokamak Energy System Code (TESC), using different methodologies to arrive at CFETR performance parameters under the same CFETR constraints show that the correlation between the physics performance and the fusion performance is consistent, and the computed parameters are in good agreement. Optimization of the first wall surface for tritium breeding and the minimization of the machine size are highly compatible. Variations of the plasma currents and profiles lead to changes in the required normalized physics performance, however, they do not significantly affect the optimized size of the machine. GASC and TESC have also been used to explore a lower aspect ratio, larger volume plasma taking advantage of the engineering flexibility in the CFETR design. Assuming the ITER steady-state scenario physics, the larger plasma together with a moderately higher BT and Ip can result in a high gain Qfus ˜ 12, Pfus ˜ 1 GW machine approaching DEMO-like performance. It is concluded that the CFETR baseline mode can meet the minimum goal of the Fusion Nuclear Science Facility (FNSF) mission and advanced physics will enable it to address comprehensively the outstanding critical technology gaps on the path to a demonstration reactor (DEMO). Before proceeding with CFETR construction steady-state operation has to be demonstrated, further development is needed to solve the divertor heat load issue, and blankets have to be designed with tritium breeding ratio (TBR) >1 as a target.

Methods, systems and apparatus for optimization of third harmonic current injection in a multi-phase machine

DOEpatents

Gallegos-Lopez, Gabriel

2012-10-02

Methods, system and apparatus are provided for increasing voltage utilization in a five-phase vector controlled machine drive system that employs third harmonic current injection to increase torque and power output by a five-phase machine. To do so, a fundamental current angle of a fundamental current vector is optimized for each particular torque-speed of operating point of the five-phase machine.

Solving a Higgs optimization problem with quantum annealing for machine learning.

PubMed

Mott, Alex; Job, Joshua; Vlimant, Jean-Roch; Lidar, Daniel; Spiropulu, Maria

2017-10-18

The discovery of Higgs-boson decays in a background of standard-model processes was assisted by machine learning methods. The classifiers used to separate signals such as these from background are trained using highly unerring but not completely perfect simulations of the physical processes involved, often resulting in incorrect labelling of background processes or signals (label noise) and systematic errors. Here we use quantum and classical annealing (probabilistic techniques for approximating the global maximum or minimum of a given function) to solve a Higgs-signal-versus-background machine learning optimization problem, mapped to a problem of finding the ground state of a corresponding Ising spin model. We build a set of weak classifiers based on the kinematic observables of the Higgs decay photons, which we then use to construct a strong classifier. This strong classifier is highly resilient against overtraining and against errors in the correlations of the physical observables in the training data. We show that the resulting quantum and classical annealing-based classifier systems perform comparably to the state-of-the-art machine learning methods that are currently used in particle physics. However, in contrast to these methods, the annealing-based classifiers are simple functions of directly interpretable experimental parameters with clear physical meaning. The annealer-trained classifiers use the excited states in the vicinity of the ground state and demonstrate some advantage over traditional machine learning methods for small training datasets. Given the relative simplicity of the algorithm and its robustness to error, this technique may find application in other areas of experimental particle physics, such as real-time decision making in event-selection problems and classification in neutrino physics.

Solving a Higgs optimization problem with quantum annealing for machine learning

NASA Astrophysics Data System (ADS)

Mott, Alex; Job, Joshua; Vlimant, Jean-Roch; Lidar, Daniel; Spiropulu, Maria

2017-10-01

The discovery of Higgs-boson decays in a background of standard-model processes was assisted by machine learning methods. The classifiers used to separate signals such as these from background are trained using highly unerring but not completely perfect simulations of the physical processes involved, often resulting in incorrect labelling of background processes or signals (label noise) and systematic errors. Here we use quantum and classical annealing (probabilistic techniques for approximating the global maximum or minimum of a given function) to solve a Higgs-signal-versus-background machine learning optimization problem, mapped to a problem of finding the ground state of a corresponding Ising spin model. We build a set of weak classifiers based on the kinematic observables of the Higgs decay photons, which we then use to construct a strong classifier. This strong classifier is highly resilient against overtraining and against errors in the correlations of the physical observables in the training data. We show that the resulting quantum and classical annealing-based classifier systems perform comparably to the state-of-the-art machine learning methods that are currently used in particle physics. However, in contrast to these methods, the annealing-based classifiers are simple functions of directly interpretable experimental parameters with clear physical meaning. The annealer-trained classifiers use the excited states in the vicinity of the ground state and demonstrate some advantage over traditional machine learning methods for small training datasets. Given the relative simplicity of the algorithm and its robustness to error, this technique may find application in other areas of experimental particle physics, such as real-time decision making in event-selection problems and classification in neutrino physics.

An improved CS-LSSVM algorithm-based fault pattern recognition of ship power equipments.

PubMed

Yang, Yifei; Tan, Minjia; Dai, Yuewei

2017-01-01

A ship power equipments' fault monitoring signal usually provides few samples and the data's feature is non-linear in practical situation. This paper adopts the method of the least squares support vector machine (LSSVM) to deal with the problem of fault pattern identification in the case of small sample data. Meanwhile, in order to avoid involving a local extremum and poor convergence precision which are induced by optimizing the kernel function parameter and penalty factor of LSSVM, an improved Cuckoo Search (CS) algorithm is proposed for the purpose of parameter optimization. Based on the dynamic adaptive strategy, the newly proposed algorithm improves the recognition probability and the searching step length, which can effectively solve the problems of slow searching speed and low calculation accuracy of the CS algorithm. A benchmark example demonstrates that the CS-LSSVM algorithm can accurately and effectively identify the fault pattern types of ship power equipments.

Implementing a quantum cloning machine in separate cavities via the optical coherent pulse as a quantum communication bus

NASA Astrophysics Data System (ADS)

Zhu, Meng-Zheng; Ye, Liu

2015-04-01

An efficient scheme is proposed to implement a quantum cloning machine in separate cavities based on a hybrid interaction between electron-spin systems placed in the cavities and an optical coherent pulse. The coefficient of the output state for the present cloning machine is just the direct product of two trigonometric functions, which ensures that different types of quantum cloning machine can be achieved readily in the same framework by appropriately adjusting the rotated angles. The present scheme can implement optimal one-to-two symmetric (asymmetric) universal quantum cloning, optimal symmetric (asymmetric) phase-covariant cloning, optimal symmetric (asymmetric) real-state cloning, optimal one-to-three symmetric economical real-state cloning, and optimal symmetric cloning of qubits given by an arbitrary axisymmetric distribution. In addition, photon loss of the qubus beams during the transmission and decoherence effects caused by such a photon loss are investigated.

Optimization process planning using hybrid genetic algorithm and intelligent search for job shop machining.

PubMed

Salehi, Mojtaba; Bahreininejad, Ardeshir

2011-08-01

Optimization of process planning is considered as the key technology for computer-aided process planning which is a rather complex and difficult procedure. A good process plan of a part is built up based on two elements: (1) the optimized sequence of the operations of the part; and (2) the optimized selection of the machine, cutting tool and Tool Access Direction (TAD) for each operation. In the present work, the process planning is divided into preliminary planning, and secondary/detailed planning. In the preliminary stage, based on the analysis of order and clustering constraints as a compulsive constraint aggregation in operation sequencing and using an intelligent searching strategy, the feasible sequences are generated. Then, in the detailed planning stage, using the genetic algorithm which prunes the initial feasible sequences, the optimized operation sequence and the optimized selection of the machine, cutting tool and TAD for each operation based on optimization constraints as an additive constraint aggregation are obtained. The main contribution of this work is the optimization of sequence of the operations of the part, and optimization of machine selection, cutting tool and TAD for each operation using the intelligent search and genetic algorithm simultaneously.

Optimization process planning using hybrid genetic algorithm and intelligent search for job shop machining

PubMed Central

Salehi, Mojtaba

2010-01-01

Optimization of process planning is considered as the key technology for computer-aided process planning which is a rather complex and difficult procedure. A good process plan of a part is built up based on two elements: (1) the optimized sequence of the operations of the part; and (2) the optimized selection of the machine, cutting tool and Tool Access Direction (TAD) for each operation. In the present work, the process planning is divided into preliminary planning, and secondary/detailed planning. In the preliminary stage, based on the analysis of order and clustering constraints as a compulsive constraint aggregation in operation sequencing and using an intelligent searching strategy, the feasible sequences are generated. Then, in the detailed planning stage, using the genetic algorithm which prunes the initial feasible sequences, the optimized operation sequence and the optimized selection of the machine, cutting tool and TAD for each operation based on optimization constraints as an additive constraint aggregation are obtained. The main contribution of this work is the optimization of sequence of the operations of the part, and optimization of machine selection, cutting tool and TAD for each operation using the intelligent search and genetic algorithm simultaneously. PMID:21845020

Classical Optimal Control for Energy Minimization Based On Diffeomorphic Modulation under Observable-Response-Preserving Homotopy.

PubMed

Soley, Micheline B; Markmann, Andreas; Batista, Victor S

2018-06-12

We introduce the so-called "Classical Optimal Control Optimization" (COCO) method for global energy minimization based on the implementation of the diffeomorphic modulation under observable-response-preserving homotopy (DMORPH) gradient algorithm. A probe particle with time-dependent mass m( t;β) and dipole μ( r, t;β) is evolved classically on the potential energy surface V( r) coupled to an electric field E( t;β), as described by the time-dependent density of states represented on a grid, or otherwise as a linear combination of Gaussians generated by the k-means clustering algorithm. Control parameters β defining m( t;β), μ( r, t;β), and E( t;β) are optimized by following the gradients of the energy with respect to β, adapting them to steer the particle toward the global minimum energy configuration. We find that the resulting COCO algorithm is capable of resolving near-degenerate states separated by large energy barriers and successfully locates the global minima of golf potentials on flat and rugged surfaces, previously explored for testing quantum annealing methodologies and the quantum optimal control optimization (QuOCO) method. Preliminary results show successful energy minimization of multidimensional Lennard-Jones clusters. Beyond the analysis of energy minimization in the specific model systems investigated, we anticipate COCO should be valuable for solving minimization problems in general, including optimization of parameters in applications to machine learning and molecular structure determination.

76 FR 5832 - International Business Machines (IBM), Software Group Business Unit, Optim Data Studio Tools QA...

Federal Register 2010, 2011, 2012, 2013, 2014

2011-02-02

... DEPARTMENT OF LABOR Employment and Training Administration [TA-W-74,554] International Business Machines (IBM), Software Group Business Unit, Optim Data Studio Tools QA, San Jose, CA; Notice of... determination of the TAA petition filed on behalf of workers at International Business Machines (IBM), Software...

Temperature field simulation on Ti6Al4V and Inconel718 heated by continuous infrared laser

NASA Astrophysics Data System (ADS)

Wang, Yanshen; Zhang, Zheng; Feng, Weiwei; Wang, Bo; Gai, Yuxian

2014-08-01

Laser assisted machining technology can heat and soften metals, which can be used for improving the machinability of superalloys such as Ti6Al4V and Inconel718. Researches on temperature field simulation of Ti6Al4V and Inconel718 are conducted in this paper. A thermal differential equation is established based on Fourier's law and energy conservation law. Then, a model using ABAQUS for simulating heat transfer process is brought out, which is then experimentally validated. Using the simulation model, detailed investigations on temperature field simulation are carried out in Ti6Al4V and Inconel718. According to simulation, surface temperature of the two superalloys eventually reaches their peak values, and the peak temperature of Ti6Al4V is much higher than that of Inconel718. To further investigate temperature heated by laser, laser parameters such as power, scanning velocity, laser spot radius and inclination angle are set to be variables separately for simulation. Simulation results show that laser power and laser spot radius are predominant factors in heating process compared with the influence of scanning velocity and inclination angle. Simulations in this paper provide valuable references for parameter optimization in the following laser heating experiments, which plays an important role in laser assisted machining.

Experiments for practical education in process parameter optimization for selective laser sintering to increase workpiece quality

NASA Astrophysics Data System (ADS)

Reutterer, Bernd; Traxler, Lukas; Bayer, Natascha; Drauschke, Andreas

2016-04-01

Selective Laser Sintering (SLS) is considered as one of the most important additive manufacturing processes due to component stability and its broad range of usable materials. However the influence of the different process parameters on mechanical workpiece properties is still poorly studied, leading to the fact that further optimization is necessary to increase workpiece quality. In order to investigate the impact of various process parameters, laboratory experiments are implemented to improve the understanding of the SLS limitations and advantages on an educational level. Experiments are based on two different workstations, used to teach students the fundamentals of SLS. First of all a 50 W CO2 laser workstation is used to investigate the interaction of the laser beam with the used material in accordance with varied process parameters to analyze a single-layered test piece. Second of all the FORMIGA P110 laser sintering system from EOS is used to print different 3D test pieces in dependence on various process parameters. Finally quality attributes are tested including warpage, dimension accuracy or tensile strength. For dimension measurements and evaluation of the surface structure a telecentric lens in combination with a camera is used. A tensile test machine allows testing of the tensile strength and the interpreting of stress-strain curves. The developed laboratory experiments are suitable to teach students the influence of processing parameters. In this context they will be able to optimize the input parameters depending on the component which has to be manufactured and to increase the overall quality of the final workpiece.

Tool path strategy and cutting process monitoring in intelligent machining

NASA Astrophysics Data System (ADS)

Chen, Ming; Wang, Chengdong; An, Qinglong; Ming, Weiwei

2018-06-01

Intelligent machining is a current focus in advanced manufacturing technology, and is characterized by high accuracy and efficiency. A central technology of intelligent machining—the cutting process online monitoring and optimization—is urgently needed for mass production. In this research, the cutting process online monitoring and optimization in jet engine impeller machining, cranio-maxillofacial surgery, and hydraulic servo valve deburring are introduced as examples of intelligent machining. Results show that intelligent tool path optimization and cutting process online monitoring are efficient techniques for improving the efficiency, quality, and reliability of machining.

Modeling and Compensation of Random Drift of MEMS Gyroscopes Based on Least Squares Support Vector Machine Optimized by Chaotic Particle Swarm Optimization.

PubMed

Xing, Haifeng; Hou, Bo; Lin, Zhihui; Guo, Meifeng

2017-10-13

MEMS (Micro Electro Mechanical System) gyroscopes have been widely applied to various fields, but MEMS gyroscope random drift has nonlinear and non-stationary characteristics. It has attracted much attention to model and compensate the random drift because it can improve the precision of inertial devices. This paper has proposed to use wavelet filtering to reduce noise in the original data of MEMS gyroscopes, then reconstruct the random drift data with PSR (phase space reconstruction), and establish the model for the reconstructed data by LSSVM (least squares support vector machine), of which the parameters were optimized using CPSO (chaotic particle swarm optimization). Comparing the effect of modeling the MEMS gyroscope random drift with BP-ANN (back propagation artificial neural network) and the proposed method, the results showed that the latter had a better prediction accuracy. Using the compensation of three groups of MEMS gyroscope random drift data, the standard deviation of three groups of experimental data dropped from 0.00354°/s, 0.00412°/s, and 0.00328°/s to 0.00065°/s, 0.00072°/s and 0.00061°/s, respectively, which demonstrated that the proposed method can reduce the influence of MEMS gyroscope random drift and verified the effectiveness of this method for modeling MEMS gyroscope random drift.

Magic in the machine: a computational magician's assistant.

PubMed

Williams, Howard; McOwan, Peter W

2014-01-01

A human magician blends science, psychology, and performance to create a magical effect. In this paper we explore what can be achieved when that human intelligence is replaced or assisted by machine intelligence. Magical effects are all in some form based on hidden mathematical, scientific, or psychological principles; often the parameters controlling these underpinning techniques are hard for a magician to blend to maximize the magical effect required. The complexity is often caused by interacting and often conflicting physical and psychological constraints that need to be optimally balanced. Normally this tuning is done by trial and error, combined with human intuitions. Here we focus on applying Artificial Intelligence methods to the creation and optimization of magic tricks exploiting mathematical principles. We use experimentally derived data about particular perceptual and cognitive features, combined with a model of the underlying mathematical process to provide a psychologically valid metric to allow optimization of magical impact. In the paper we introduce our optimization methodology and describe how it can be flexibly applied to a range of different types of mathematics based tricks. We also provide two case studies as exemplars of the methodology at work: a magical jigsaw, and a mind reading card trick effect. We evaluate each trick created through testing in laboratory and public performances, and further demonstrate the real world efficacy of our approach for professional performers through sales of the tricks in a reputable magic shop in London.

Applications of wavelet-based compression to multidimensional Earth science data

NASA Technical Reports Server (NTRS)

Bradley, Jonathan N.; Brislawn, Christopher M.

1993-01-01

A data compression algorithm involving vector quantization (VQ) and the discrete wavelet transform (DWT) is applied to two different types of multidimensional digital earth-science data. The algorithms (WVQ) is optimized for each particular application through an optimization procedure that assigns VQ parameters to the wavelet transform subbands subject to constraints on compression ratio and encoding complexity. Preliminary results of compressing global ocean model data generated on a Thinking Machines CM-200 supercomputer are presented. The WVQ scheme is used in both a predictive and nonpredictive mode. Parameters generated by the optimization algorithm are reported, as are signal-to-noise (SNR) measurements of actual quantized data. The problem of extrapolating hydrodynamic variables across the continental landmasses in order to compute the DWT on a rectangular grid is discussed. Results are also presented for compressing Landsat TM 7-band data using the WVQ scheme. The formulation of the optimization problem is presented along with SNR measurements of actual quantized data. Postprocessing applications are considered in which the seven spectral bands are clustered into 256 clusters using a k-means algorithm and analyzed using the Los Alamos multispectral data analysis program, SPECTRUM, both before and after being compressed using the WVQ program.

Assisted closed-loop optimization of SSVEP-BCI efficiency

PubMed Central

Fernandez-Vargas, Jacobo; Pfaff, Hanns U.; Rodríguez, Francisco B.; Varona, Pablo

2012-01-01

We designed a novel assisted closed-loop optimization protocol to improve the efficiency of brain-computer interfaces (BCI) based on steady state visually evoked potentials (SSVEP). In traditional paradigms, the control over the BCI-performance completely depends on the subjects' ability to learn from the given feedback cues. By contrast, in the proposed protocol both the subject and the machine share information and control over the BCI goal. Generally, the innovative assistance consists in the delivery of online information together with the online adaptation of BCI stimuli properties. In our case, this adaptive optimization process is realized by (1) a closed-loop search for the best set of SSVEP flicker frequencies and (2) feedback of actual SSVEP magnitudes to both the subject and the machine. These closed-loop interactions between subject and machine are evaluated in real-time by continuous measurement of their efficiencies, which are used as online criteria to adapt the BCI control parameters. The proposed protocol aims to compensate for variability in possibly unknown subjects' state and trait dimensions. In a study with N = 18 subjects, we found significant evidence that our protocol outperformed classic SSVEP-BCI control paradigms. Evidence is presented that it takes indeed into account interindividual variabilities: e.g., under the new protocol, baseline resting state EEG measures predict subjects' BCI performances. This paper illustrates the promising potential of assisted closed-loop protocols in BCI systems. Probably their applicability might be expanded to innovative uses, e.g., as possible new diagnostic/therapeutic tools for clinical contexts and as new paradigms for basic research. PMID:23443214

Assisted closed-loop optimization of SSVEP-BCI efficiency.

PubMed

Fernandez-Vargas, Jacobo; Pfaff, Hanns U; Rodríguez, Francisco B; Varona, Pablo

2013-01-01

We designed a novel assisted closed-loop optimization protocol to improve the efficiency of brain-computer interfaces (BCI) based on steady state visually evoked potentials (SSVEP). In traditional paradigms, the control over the BCI-performance completely depends on the subjects' ability to learn from the given feedback cues. By contrast, in the proposed protocol both the subject and the machine share information and control over the BCI goal. Generally, the innovative assistance consists in the delivery of online information together with the online adaptation of BCI stimuli properties. In our case, this adaptive optimization process is realized by (1) a closed-loop search for the best set of SSVEP flicker frequencies and (2) feedback of actual SSVEP magnitudes to both the subject and the machine. These closed-loop interactions between subject and machine are evaluated in real-time by continuous measurement of their efficiencies, which are used as online criteria to adapt the BCI control parameters. The proposed protocol aims to compensate for variability in possibly unknown subjects' state and trait dimensions. In a study with N = 18 subjects, we found significant evidence that our protocol outperformed classic SSVEP-BCI control paradigms. Evidence is presented that it takes indeed into account interindividual variabilities: e.g., under the new protocol, baseline resting state EEG measures predict subjects' BCI performances. This paper illustrates the promising potential of assisted closed-loop protocols in BCI systems. Probably their applicability might be expanded to innovative uses, e.g., as possible new diagnostic/therapeutic tools for clinical contexts and as new paradigms for basic research.

Development of a novel optimization tool for electron linacs inspired by artificial intelligence techniques in video games

NASA Astrophysics Data System (ADS)

Meier, E.; Biedron, S. G.; LeBlanc, G.; Morgan, M. J.

2011-03-01

This paper reports the results of an advanced algorithm for the optimization of electron beam parameters in Free Electron Laser (FEL) Linacs. In the novel approach presented in this paper, the system uses state of the art developments in video games to mimic an operator's decisions to perform an optimization task when no prior knowledge, other than constraints on the actuators is available. The system was tested for the simultaneous optimization of the energy spread and the transmission of the Australian Synchrotron Linac. The proposed system successfully increased the transmission of the machine from 90% to 97% and decreased the energy spread of the beam from 1.04% to 0.91%. Results of a control experiment performed at the new FERMI@Elettra FEL is also reported, suggesting the adaptability of the scheme for beam-based control.

A Sensor Dynamic Measurement Error Prediction Model Based on NAPSO-SVM

PubMed Central

Jiang, Minlan; Jiang, Lan; Jiang, Dingde; Li, Fei

2018-01-01

Dynamic measurement error correction is an effective way to improve sensor precision. Dynamic measurement error prediction is an important part of error correction, and support vector machine (SVM) is often used for predicting the dynamic measurement errors of sensors. Traditionally, the SVM parameters were always set manually, which cannot ensure the model’s performance. In this paper, a SVM method based on an improved particle swarm optimization (NAPSO) is proposed to predict the dynamic measurement errors of sensors. Natural selection and simulated annealing are added in the PSO to raise the ability to avoid local optima. To verify the performance of NAPSO-SVM, three types of algorithms are selected to optimize the SVM’s parameters: the particle swarm optimization algorithm (PSO), the improved PSO optimization algorithm (NAPSO), and the glowworm swarm optimization (GSO). The dynamic measurement error data of two sensors are applied as the test data. The root mean squared error and mean absolute percentage error are employed to evaluate the prediction models’ performances. The experimental results show that among the three tested algorithms the NAPSO-SVM method has a better prediction precision and a less prediction errors, and it is an effective method for predicting the dynamic measurement errors of sensors. PMID:29342942

Laser beam micro-milling of nickel alloy: dimensional variations and RSM optimization of laser parameters

NASA Astrophysics Data System (ADS)

Ahmed, Naveed; Alahmari, Abdulrahman M.; Darwish, Saied; Naveed, Madiha

2016-12-01

Micro-channels are considered as the integral part of several engineering devices such as micro-channel heat exchangers, micro-coolers, micro-pulsating heat pipes and micro-channels used in gas turbine blades for aerospace applications. In such applications, a fluid flow is required to pass through certain micro-passages such as micro-grooves and micro-channels. The fluid flow characteristics (flow rate, turbulence, pressure drop and fluid dynamics) are mainly established based on the size and accuracy of micro-passages. Variations (oversizing and undersizing) in micro-passage's geometry directly affect the fluid flow characteristics. In this study, the micro-channels of several sizes are fabricated in well-known aerospace nickel alloy (Inconel 718) through laser beam micro-milling. The variations in geometrical characteristics of different-sized micro-channels are studied under the influences of different parameters of Nd:YAG laser. In order to have a minimum variation in the machined geometries of each size of micro-channel, the multi-objective optimization of laser parameters has been carried out utilizing the response surface methodology approach. The objective was set to achieve the targeted top widths and depths of micro-channels with minimum degree of taperness associated with the micro-channel's sidewalls. The optimized sets of laser parameters proposed for each size of micro-channel can be used to fabricate the micro-channels in Inconel 718 with minimum amount of geometrical variations.

A hybrid PSO-SVM-based method for predicting the friction coefficient between aircraft tire and coating

NASA Astrophysics Data System (ADS)

Zhan, Liwei; Li, Chengwei

2017-02-01

A hybrid PSO-SVM-based model is proposed to predict the friction coefficient between aircraft tire and coating. The presented hybrid model combines a support vector machine (SVM) with particle swarm optimization (PSO) technique. SVM has been adopted to solve regression problems successfully. Its regression accuracy is greatly related to optimizing parameters such as the regularization constant C , the parameter gamma γ corresponding to RBF kernel and the epsilon parameter \\varepsilon in the SVM training procedure. However, the friction coefficient which is predicted based on SVM has yet to be explored between aircraft tire and coating. The experiment reveals that drop height and tire rotational speed are the factors affecting friction coefficient. Bearing in mind, the friction coefficient can been predicted using the hybrid PSO-SVM-based model by the measured friction coefficient between aircraft tire and coating. To compare regression accuracy, a grid search (GS) method and a genetic algorithm (GA) are used to optimize the relevant parameters (C , γ and \\varepsilon ), respectively. The regression accuracy could be reflected by the coefficient of determination ({{R}2} ). The result shows that the hybrid PSO-RBF-SVM-based model has better accuracy compared with the GS-RBF-SVM- and GA-RBF-SVM-based models. The agreement of this model (PSO-RBF-SVM) with experiment data confirms its good performance.

Modeling of Geometric Error in Linear Guide Way to Improved the vertical three-axis CNC Milling machine’s accuracy

NASA Astrophysics Data System (ADS)

Kwintarini, Widiyanti; Wibowo, Agung; Arthaya, Bagus M.; Yuwana Martawirya, Yatna

2018-03-01

The purpose of this study was to improve the accuracy of three-axis CNC Milling Vertical engines with a general approach by using mathematical modeling methods of machine tool geometric errors. The inaccuracy of CNC machines can be caused by geometric errors that are an important factor during the manufacturing process and during the assembly phase, and are factors for being able to build machines with high-accuracy. To improve the accuracy of the three-axis vertical milling machine, by knowing geometric errors and identifying the error position parameters in the machine tool by arranging the mathematical modeling. The geometric error in the machine tool consists of twenty-one error parameters consisting of nine linear error parameters, nine angle error parameters and three perpendicular error parameters. The mathematical modeling approach of geometric error with the calculated alignment error and angle error in the supporting components of the machine motion is linear guide way and linear motion. The purpose of using this mathematical modeling approach is the identification of geometric errors that can be helpful as reference during the design, assembly and maintenance stages to improve the accuracy of CNC machines. Mathematically modeling geometric errors in CNC machine tools can illustrate the relationship between alignment error, position and angle on a linear guide way of three-axis vertical milling machines.

Performance analysis of cutting graphite-epoxy composite using a 90,000psi abrasive waterjet

NASA Astrophysics Data System (ADS)

Choppali, Aiswarya

Graphite-epoxy composites are being widely used in many aerospace and structural applications because of their properties: which include lighter weight, higher strength to weight ratio and a greater flexibility in design. However, the inherent anisotropy of these composites makes it difficult to machine them using conventional methods. To overcome the major issues that develop with conventional machining such as fiber pull out, delamination, heat generation and high tooling costs, an effort is herein made to study abrasive waterjet machining of composites. An abrasive waterjet is used to cut 1" thick graphite epoxy composites based on baseline data obtained from the cutting of ¼" thick material. The objective of this project is to study the surface roughness of the cut surface with a focus on demonstrating the benefits of using higher pressures for cutting composites. The effects of major cutting parameters: jet pressure, traverse speed, abrasive feed rate and cutting head size are studied at different levels. Statistical analysis of the experimental data provides an understanding of the effect of the process parameters on surface roughness. Additionally, the effect of these parameters on the taper angle of the cut is studied. The data is analyzed to obtain a set of process parameters that optimize the cutting of 1" thick graphite-epoxy composite. The statistical analysis is used to validate the experimental data. Costs involved in the cutting process are investigated in term of abrasive consumed to better understand and illustrate the practical benefits of using higher pressures. It is demonstrated that, as pressure increased, ultra-high pressure waterjets produced a better surface quality at a faster traverse rate with lower costs.

Comparative Performance Analysis of Coarse Solvers for Algebraic Multigrid on Multicore and Manycore Architectures

DOE Office of Scientific and Technical Information (OSTI.GOV)

Druinsky, Alex; Ghysels, Pieter; Li, Xiaoye S.

In this paper, we study the performance of a two-level algebraic-multigrid algorithm, with a focus on the impact of the coarse-grid solver on performance. We consider two algorithms for solving the coarse-space systems: the preconditioned conjugate gradient method and a new robust HSS-embedded low-rank sparse-factorization algorithm. Our test data comes from the SPE Comparative Solution Project for oil-reservoir simulations. We contrast the performance of our code on one 12-core socket of a Cray XC30 machine with performance on a 60-core Intel Xeon Phi coprocessor. To obtain top performance, we optimized the code to take full advantage of fine-grained parallelism andmore » made it thread-friendly for high thread count. We also developed a bounds-and-bottlenecks performance model of the solver which we used to guide us through the optimization effort, and also carried out performance tuning in the solver’s large parameter space. Finally, as a result, significant speedups were obtained on both machines.« less

Short-Term Distribution System State Forecast Based on Optimal Synchrophasor Sensor Placement and Extreme Learning Machine

DOE Office of Scientific and Technical Information (OSTI.GOV)

Jiang, Huaiguang; Zhang, Yingchen

This paper proposes an approach for distribution system state forecasting, which aims to provide an accurate and high speed state forecasting with an optimal synchrophasor sensor placement (OSSP) based state estimator and an extreme learning machine (ELM) based forecaster. Specifically, considering the sensor installation cost and measurement error, an OSSP algorithm is proposed to reduce the number of synchrophasor sensor and keep the whole distribution system numerically and topologically observable. Then, the weighted least square (WLS) based system state estimator is used to produce the training data for the proposed forecaster. Traditionally, the artificial neural network (ANN) and support vectormore » regression (SVR) are widely used in forecasting due to their nonlinear modeling capabilities. However, the ANN contains heavy computation load and the best parameters for SVR are difficult to obtain. In this paper, the ELM, which overcomes these drawbacks, is used to forecast the future system states with the historical system states. The proposed approach is effective and accurate based on the testing results.« less

Learning to represent spatial transformations with factored higher-order Boltzmann machines.

PubMed

Memisevic, Roland; Hinton, Geoffrey E

2010-06-01

To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicative interactions that use the intensity of a pixel in the first image as a multiplicative gain on a learned, symmetric weight between a pixel in the second image and a hidden unit. This creates cubically many parameters, which form a three-dimensional interaction tensor. We describe a low-rank approximation to this interaction tensor that uses a sum of factors, each of which is a three-way outer product. This approximation allows efficient learning of transformations between larger image patches. Since each factor can be viewed as an image filter, the model as a whole learns optimal filter pairs for efficiently representing transformations. We demonstrate the learning of optimal filter pairs from various synthetic and real image sequences. We also show how learning about image transformations allows the model to perform a simple visual analogy task, and we show how a completely unsupervised network trained on transformations perceives multiple motions of transparent dot patterns in the same way as humans.

Optimization of a novel large field of view distortion phantom for MR-only treatment planning.

PubMed

Price, Ryan G; Knight, Robert A; Hwang, Ken-Pin; Bayram, Ersin; Nejad-Davarani, Siamak P; Glide-Hurst, Carri K

2017-07-01

MR-only treatment planning requires images of high geometric fidelity, particularly for large fields of view (FOV). However, the availability of large FOV distortion phantoms with analysis software is currently limited. This work sought to optimize a modular distortion phantom to accommodate multiple bore configurations and implement distortion characterization in a widely implementable solution. To determine candidate materials, 1.0 T MR and CT images were acquired of twelve urethane foam samples of various densities and strengths. Samples were precision-machined to accommodate 6 mm diameter paintballs used as landmarks. Final material candidates were selected by balancing strength, machinability, weight, and cost. Bore sizes and minimum aperture width resulting from couch position were tabulated from the literature (14 systems, 5 vendors). Bore geometry and couch position were simulated using MATLAB to generate machine-specific models to optimize the phantom build. Previously developed software for distortion characterization was modified for several magnet geometries (1.0 T, 1.5 T, 3.0 T), compared against previously published 1.0 T results, and integrated into the 3D Slicer application platform. All foam samples provided sufficient MR image contrast with paintball landmarks. Urethane foam (compressive strength ∼1000 psi, density ~20 lb/ft 3 ) was selected for its accurate machinability and weight characteristics. For smaller bores, a phantom version with the following parameters was used: 15 foam plates, 55 × 55 × 37.5 cm 3 (L×W×H), 5,082 landmarks, and weight ~30 kg. To accommodate > 70 cm wide bores, an extended build used 20 plates spanning 55 × 55 × 50 cm 3 with 7,497 landmarks and weight ~44 kg. Distortion characterization software was implemented as an external module into 3D Slicer's plugin framework and results agreed with the literature. The design and implementation of a modular, extendable distortion phantom was optimized for several bore configurations. The phantom and analysis software will be available for multi-institutional collaborations and cross-validation trials to support MR-only planning. © 2017 The Authors. Journal of Applied Clinical Medical Physics published by Wiley Periodicals, Inc. on behalf of American Association of Physicists in Medicine.

Dual stator winding variable speed asynchronous generator: optimal design and experiments

NASA Astrophysics Data System (ADS)

Tutelea, L. N.; Deaconu, S. I.; Popa, G. N.

2015-06-01

In the present paper is carried out a theoretical and experimental study of dual stator winding squirrel cage asynchronous generator (DSWA) behavior in the presence of saturation regime (non-sinusoidal) due to the variable speed operation. The main aims are the determination of the relations of calculating the equivalent parameters of the machine windings to optimal design using a Matlab code. Issue is limited to three phase range of double stator winding cage-induction generator of small sized powers, the most currently used in the small adjustable speed wind or hydro power plants. The tests were carried out using three-phase asynchronous generator having rated power of 6 [kVA].

A Novel Weighted Kernel PCA-Based Method for Optimization and Uncertainty Quantification

NASA Astrophysics Data System (ADS)

Thimmisetty, C.; Talbot, C.; Chen, X.; Tong, C. H.

2016-12-01

It has been demonstrated that machine learning methods can be successfully applied to uncertainty quantification for geophysical systems through the use of the adjoint method coupled with kernel PCA-based optimization. In addition, it has been shown through weighted linear PCA how optimization with respect to both observation weights and feature space control variables can accelerate convergence of such methods. Linear machine learning methods, however, are inherently limited in their ability to represent features of non-Gaussian stochastic random fields, as they are based on only the first two statistical moments of the original data. Nonlinear spatial relationships and multipoint statistics leading to the tortuosity characteristic of channelized media, for example, are captured only to a limited extent by linear PCA. With the aim of coupling the kernel-based and weighted methods discussed, we present a novel mathematical formulation of kernel PCA, Weighted Kernel Principal Component Analysis (WKPCA), that both captures nonlinear relationships and incorporates the attribution of significance levels to different realizations of the stochastic random field of interest. We also demonstrate how new instantiations retaining defining characteristics of the random field can be generated using Bayesian methods. In particular, we present a novel WKPCA-based optimization method that minimizes a given objective function with respect to both feature space random variables and observation weights through which optimal snapshot significance levels and optimal features are learned. We showcase how WKPCA can be applied to nonlinear optimal control problems involving channelized media, and in particular demonstrate an application of the method to learning the spatial distribution of material parameter values in the context of linear elasticity, and discuss further extensions of the method to stochastic inversion.

Hypothermic machine perfusion in kidney transplantation.

PubMed

De Deken, Julie; Kocabayoglu, Peri; Moers, Cyril

2016-06-01

This article summarizes novel developments in hypothermic machine perfusion (HMP) as an organ preservation modality for kidneys recovered from deceased donors. HMP has undergone a renaissance in recent years. This renewed interest has arisen parallel to a shift in paradigms; not only optimal preservation of an often marginal quality graft is required, but also improved graft function and tools to predict the latter are expected from HMP. The focus of attention in this field is currently drawn to the protection of endothelial integrity by means of additives to the perfusion solution, improvement of the HMP solution, choice of temperature, duration of perfusion, and machine settings. HMP may offer the opportunity to assess aspects of graft viability before transplantation, which can potentially aid preselection of grafts based on characteristics such as perfusate biomarkers, as well as measurement of machine perfusion dynamics parameters. HMP has proven to be beneficial as a kidney preservation method for all types of renal grafts, most notably those retrieved from extended criteria donors. Large numbers of variables during HMP, such as duration, machine settings and additives to the perfusion solution are currently being investigated to improve renal function and graft survival. In addition, the search for biomarkers has become a focus of attention to predict graft function posttransplant.

Evaluation of image features and classification methods for Barrett's cancer detection using VLE imaging

NASA Astrophysics Data System (ADS)

Klomp, Sander; van der Sommen, Fons; Swager, Anne-Fré; Zinger, Svitlana; Schoon, Erik J.; Curvers, Wouter L.; Bergman, Jacques J.; de With, Peter H. N.

2017-03-01

Volumetric Laser Endomicroscopy (VLE) is a promising technique for the detection of early neoplasia in Barrett's Esophagus (BE). VLE generates hundreds of high resolution, grayscale, cross-sectional images of the esophagus. However, at present, classifying these images is a time consuming and cumbersome effort performed by an expert using a clinical prediction model. This paper explores the feasibility of using computer vision techniques to accurately predict the presence of dysplastic tissue in VLE BE images. Our contribution is threefold. First, a benchmarking is performed for widely applied machine learning techniques and feature extraction methods. Second, three new features based on the clinical detection model are proposed, having superior classification accuracy and speed, compared to earlier work. Third, we evaluate automated parameter tuning by applying simple grid search and feature selection methods. The results are evaluated on a clinically validated dataset of 30 dysplastic and 30 non-dysplastic VLE images. Optimal classification accuracy is obtained by applying a support vector machine and using our modified Haralick features and optimal image cropping, obtaining an area under the receiver operating characteristic of 0.95 compared to the clinical prediction model at 0.81. Optimal execution time is achieved using a proposed mean and median feature, which is extracted at least factor 2.5 faster than alternative features with comparable performance.

Subgrid-scale scalar flux modelling based on optimal estimation theory and machine-learning procedures

NASA Astrophysics Data System (ADS)

Vollant, A.; Balarac, G.; Corre, C.

2017-09-01

New procedures are explored for the development of models in the context of large eddy simulation (LES) of a passive scalar. They rely on the combination of the optimal estimator theory with machine-learning algorithms. The concept of optimal estimator allows to identify the most accurate set of parameters to be used when deriving a model. The model itself can then be defined by training an artificial neural network (ANN) on a database derived from the filtering of direct numerical simulation (DNS) results. This procedure leads to a subgrid scale model displaying good structural performance, which allows to perform LESs very close to the filtered DNS results. However, this first procedure does not control the functional performance so that the model can fail when the flow configuration differs from the training database. Another procedure is then proposed, where the model functional form is imposed and the ANN used only to define the model coefficients. The training step is a bi-objective optimisation in order to control both structural and functional performances. The model derived from this second procedure proves to be more robust. It also provides stable LESs for a turbulent plane jet flow configuration very far from the training database but over-estimates the mixing process in that case.

Warpage analysis in injection moulding process

NASA Astrophysics Data System (ADS)

Hidayah, M. H. N.; Shayfull, Z.; Nasir, S. M.; Fathullah, M.; Hazwan, M. H. M.

2017-09-01

This study was concentrated on the effects of process parameters in plastic injection moulding process towards warpage problem by using Autodesk Moldflow Insight (AMI) software for the simulation. In this study, plastic dispenser of dental floss has been analysed with thermoplastic material of Polypropylene (PP) used as the moulded material and details properties of 80 Tonne Nessei NEX 1000 injection moulding machine also has been used in this study. The variable parameters of the process are packing pressure, packing time, melt temperature and cooling time. Minimization of warpage obtained from the optimization and analysis data from the Design Expert software. Integration of Response Surface Methodology (RSM), Center Composite Design (CCD) with polynomial models that has been obtained from Design of Experiment (DOE) is the method used in this study. The results show that packing pressure is the main factor that will contribute to the formation of warpage in x-axis and y-axis. While in z-axis, the main factor is melt temperature and packing time is the less significant among the four parameters in x, y and z-axes. From optimal processing parameter, the value of warpage in x, y and z-axis have been optimised by 21.60%, 26.45% and 24.53%, respectively.

Carbon dioxide emission prediction using support vector machine

NASA Astrophysics Data System (ADS)

Saleh, Chairul; Rachman Dzakiyullah, Nur; Bayu Nugroho, Jonathan

2016-02-01

In this paper, the SVM model was proposed for predict expenditure of carbon (CO2) emission. The energy consumption such as electrical energy and burning coal is input variable that affect directly increasing of CO2 emissions were conducted to built the model. Our objective is to monitor the CO2 emission based on the electrical energy and burning coal used from the production process. The data electrical energy and burning coal used were obtained from Alcohol Industry in order to training and testing the models. It divided by cross-validation technique into 90% of training data and 10% of testing data. To find the optimal parameters of SVM model was used the trial and error approach on the experiment by adjusting C parameters and Epsilon. The result shows that the SVM model has an optimal parameter on C parameters 0.1 and 0 Epsilon. To measure the error of the model by using Root Mean Square Error (RMSE) with error value as 0.004. The smallest error of the model represents more accurately prediction. As a practice, this paper was contributing for an executive manager in making the effective decision for the business operation were monitoring expenditure of CO2 emission.

The Impact Of Surface Shape Of Chip-Breaker On Machined Surface

NASA Astrophysics Data System (ADS)

Šajgalík, Michal; Czán, Andrej; Martinček, Juraj; Varga, Daniel; Hemžský, Pavel; Pitela, David

2015-12-01

Machined surface is one of the most used indicators of workpiece quality. But machined surface is influenced by several factors such as cutting parameters, cutting material, shape of cutting tool or cutting insert, micro-structure of machined material and other known as technological parameters. By improving of these parameters, we can improve machined surface. In the machining, there is important to identify the characteristics of main product of these processes - workpiece, but also the byproduct - the chip. Size and shape of chip has impact on lifetime of cutting tools and its inappropriate form can influence the machine functionality and lifetime, too. This article deals with elimination of long chip created when machining of shaft in automotive industry and with impact of shape of chip-breaker on shape of chip in various cutting conditions based on production requirements.

Prediction and control of the service-related properties of parts at the technological preparation stage and during the manufacture process

NASA Astrophysics Data System (ADS)

Bez'iazychnyi, V. F.

The paper is concerned with the problem of optimizing the machining of aircraft engine parts in order to satisfy certain requirements for tool wear, machining precision and surface layer characteristics, and hardening depth. A generalized multiple-objective function and its computer implementation are developed which make it possible to optimize the machining process without the use of experimental data. Alternative methods of controlling the machining process are discussed.

Study on residual stresses in ultrasonic torsional vibration assisted micro-milling

NASA Astrophysics Data System (ADS)

Lu, Zesheng; Hu, Haijun; Sun, Yazhou; Sun, Qing

2010-10-01

It is well known that machining induced residual stresses can seriously affect the dimensional accuracy, corrosion and wear resistance, etc., and further influence the longevity and reliability of Micro-Optical Components (MOC). In Ultrasonic Torsional Vibration Assisted Micro-milling (UTVAM), cutting parameters, vibration parameters, mill cutter parameters, the status of wear length of tool flank are the main factors which affect residual stresses. A 2D model of UTVAM was established with FE analysis software ABAQUS. Johnson-Cook's flow stress model and shear failure principle are used as the workpiece material model and failure principle, while friction between tool and workpiece uses modified Coulomb's law whose sliding friction area is combined with sticking friction. By means of FEA, the influence rules of cutting parameters, vibration parameters, mill cutter parameters, the status of wear length of tool flank on residual stresses are obtained, which provides a basis for choosing optimal process parameters and improving the longevity and reliability of MOC.

Performance evaluation of Titanium nitride coated tool in turning of mild steel

NASA Astrophysics Data System (ADS)

Srinivas, B.; Pramod Kumar, G.; Cheepu, Muralimohan; Jagadeesh, N.; kumar, K. Ravi; Haribabu, S.

2018-03-01

The growth in demand for bio-gradable materials is opened as a venue for using vegetable oils, coconut oils etc., as alternate to the conventional coolants for machining operations. At present in manufacturing industries the demand for surface quality is increasing rapidly along with dimensional accuracy and geometric tolerances. The present study is influence of cutting parameters on the surface roughness during the turning of mild steel with TiN coated carbide tool using groundnut oil and soluble oil as coolants. The results showed vegetable gave closer surface finish compares with soluble oil. Cutting parameters has been optimized with Taguchi technique. In this paper, the main objective is to optimize the cutting parameters and reduce surface roughness analogous to increase the tool life by apply the coating on the carbide inserts. The cost of the coating is more, but economically efficient than changing the tools frequently. The plots were generated and analysed to find the relationship between them which are confirmed by performing a comparison study between the predicted results and theoretical results.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Kato, Go

We consider the situation where s replicas of a qubit with an unknown state and its orthogonal k replicas are given as an input, and we try to make c clones of the qubit with the unknown state. As a function of s, k, and c, we obtain the optimal fidelity between the qubit with an unknown state and the clone by explicitly giving a completely positive trace-preserving (CPTP) map that represents a cloning machine. We discuss dependency of the fidelity on the values of the parameters s, k, and c.

Optimization of Dimensional accuracy in plasma arc cutting process employing parametric modelling approach

NASA Astrophysics Data System (ADS)

Naik, Deepak kumar; Maity, K. P.

2018-03-01

Plasma arc cutting (PAC) is a high temperature thermal cutting process employed for the cutting of extensively high strength material which are difficult to cut through any other manufacturing process. This process involves high energized plasma arc to cut any conducting material with better dimensional accuracy in lesser time. This research work presents the effect of process parameter on to the dimensional accuracy of PAC process. The input process parameters were selected as arc voltage, standoff distance and cutting speed. A rectangular plate of 304L stainless steel of 10 mm thickness was taken for the experiment as a workpiece. Stainless steel is very extensively used material in manufacturing industries. Linear dimension were measured following Taguchi’s L16 orthogonal array design approach. Three levels were selected to conduct the experiment for each of the process parameter. In all experiments, clockwise cut direction was followed. The result obtained thorough measurement is further analyzed. Analysis of variance (ANOVA) and Analysis of means (ANOM) were performed to evaluate the effect of each process parameter. ANOVA analysis reveals the effect of input process parameter upon leaner dimension in X axis. The results of the work shows that the optimal setting of process parameter values for the leaner dimension on the X axis. The result of the investigations clearly show that the specific range of input process parameter achieved the improved machinability.

Online energy management strategy of fuel cell hybrid electric vehicles based on data fusion approach

NASA Astrophysics Data System (ADS)

Zhou, Daming; Al-Durra, Ahmed; Gao, Fei; Ravey, Alexandre; Matraji, Imad; Godoy Simões, Marcelo

2017-10-01

Energy management strategy plays a key role for Fuel Cell Hybrid Electric Vehicles (FCHEVs), it directly affects the efficiency and performance of energy storages in FCHEVs. For example, by using a suitable energy distribution controller, the fuel cell system can be maintained in a high efficiency region and thus saving hydrogen consumption. In this paper, an energy management strategy for online driving cycles is proposed based on a combination of the parameters from three offline optimized fuzzy logic controllers using data fusion approach. The fuzzy logic controllers are respectively optimized for three typical driving scenarios: highway, suburban and city in offline. To classify patterns of online driving cycles, a Probabilistic Support Vector Machine (PSVM) is used to provide probabilistic classification results. Based on the classification results of the online driving cycle, the parameters of each offline optimized fuzzy logic controllers are then fused using Dempster-Shafer (DS) evidence theory, in order to calculate the final parameters for the online fuzzy logic controller. Three experimental validations using Hardware-In-the-Loop (HIL) platform with different-sized FCHEVs have been performed. Experimental comparison results show that, the proposed PSVM-DS based online controller can achieve a relatively stable operation and a higher efficiency of fuel cell system in real driving cycles.

High efficiency machining technology and equipment for edge chamfer of KDP crystals

NASA Astrophysics Data System (ADS)

Chen, Dongsheng; Wang, Baorui; Chen, Jihong

2016-10-01

Potassium dihydrogen phosphate (KDP) is a type of nonlinear optical crystal material. To Inhibit the transverse stimulated Raman scattering of laser beam and then enhance the optical performance of the optics, the edges of the large-sized KDP crystal needs to be removed to form chamfered faces with high surface quality (RMS<5 nm). However, as the depth of cut (DOC) of fly cutting is usually several, its machining efficiency is too low to be accepted for chamfering of the KDP crystal as the amount of materials to be removed is in the order of millimeter. This paper proposes a novel hybrid machining method, which combines precision grinding with fly cutting, for crackless and high efficiency chamfer of KDP crystal. A specialized machine tool, which adopts aerostatic bearing linear slide and aerostatic bearing spindle, was developed for chamfer of the KDP crystal. The aerostatic bearing linear slide consists of an aerostatic bearing guide with linearity of 0.1 μm/100mm and a linear motor to achieve linear feeding with high precision and high dynamic performance. The vertical spindle consists of an aerostatic bearing spindle with the rotation accuracy (axial) of 0.05 microns and Fork type flexible connection precision driving mechanism. The machining experiment on flying and grinding was carried out, the optimize machining parameters was gained by a series of experiment. Surface roughness of 2.4 nm has been obtained. The machining efficiency can be improved by six times using the combined method to produce the same machined surface quality.

RANS computations for identification of 1-D cavitation model parameters: application to full load cavitation vortex rope

NASA Astrophysics Data System (ADS)

Alligné, S.; Decaix, J.; Müller, A.; Nicolet, C.; Avellan, F.; Münch, C.

2017-04-01

Due to the massive penetration of alternative renewable energies, hydropower is a key energy conversion technology for stabilizing the electrical power network by using hydraulic machines at off design operating conditions. At full load, the axisymmetric cavitation vortex rope developing in Francis turbines acts as an internal source of energy, leading to an instability commonly referred to as self-excited surge. 1-D models are developed to predict this phenomenon and to define the range of safe operating points for a hydropower plant. These models require a calibration of several parameters. The present work aims at identifying these parameters by using CFD results as objective functions for an optimization process. A 2-D Venturi and 3-D Francis turbine are considered.

Design of a multiple kernel learning algorithm for LS-SVM by convex programming.

PubMed

Jian, Ling; Xia, Zhonghang; Liang, Xijun; Gao, Chuanhou

2011-06-01

As a kernel based method, the performance of least squares support vector machine (LS-SVM) depends on the selection of the kernel as well as the regularization parameter (Duan, Keerthi, & Poo, 2003). Cross-validation is efficient in selecting a single kernel and the regularization parameter; however, it suffers from heavy computational cost and is not flexible to deal with multiple kernels. In this paper, we address the issue of multiple kernel learning for LS-SVM by formulating it as semidefinite programming (SDP). Furthermore, we show that the regularization parameter can be optimized in a unified framework with the kernel, which leads to an automatic process for model selection. Extensive experimental validations are performed and analyzed. Copyright © 2011 Elsevier Ltd. All rights reserved.

Improving Classification of Cancer and Mining Biomarkers from Gene Expression Profiles Using Hybrid Optimization Algorithms and Fuzzy Support Vector Machine

PubMed Central

Moteghaed, Niloofar Yousefi; Maghooli, Keivan; Garshasbi, Masoud

2018-01-01

Background: Gene expression data are characteristically high dimensional with a small sample size in contrast to the feature size and variability inherent in biological processes that contribute to difficulties in analysis. Selection of highly discriminative features decreases the computational cost and complexity of the classifier and improves its reliability for prediction of a new class of samples. Methods: The present study used hybrid particle swarm optimization and genetic algorithms for gene selection and a fuzzy support vector machine (SVM) as the classifier. Fuzzy logic is used to infer the importance of each sample in the training phase and decrease the outlier sensitivity of the system to increase the ability to generalize the classifier. A decision-tree algorithm was applied to the most frequent genes to develop a set of rules for each type of cancer. This improved the abilities of the algorithm by finding the best parameters for the classifier during the training phase without the need for trial-and-error by the user. The proposed approach was tested on four benchmark gene expression profiles. Results: Good results have been demonstrated for the proposed algorithm. The classification accuracy for leukemia data is 100%, for colon cancer is 96.67% and for breast cancer is 98%. The results show that the best kernel used in training the SVM classifier is the radial basis function. Conclusions: The experimental results show that the proposed algorithm can decrease the dimensionality of the dataset, determine the most informative gene subset, and improve classification accuracy using the optimal parameters of the classifier with no user interface. PMID:29535919

Hierarchical Winner-Take-All Particle Swarm Optimization Social Network for Neural Model Fitting

PubMed Central

Coventry, Brandon S.; Parthasarathy, Aravindakshan; Sommer, Alexandra L.; Bartlett, Edward L.

2016-01-01

Particle swarm optimization (PSO) has gained widespread use as a general mathematical programming paradigm and seen use in a wide variety of optimization and machine learning problems. In this work, we introduce a new variant on the PSO social network and apply this method to the inverse problem of input parameter selection from recorded auditory neuron tuning curves. The topology of a PSO social network is a major contributor to optimization success. Here we propose a new social network which draws influence from winner-take-all coding found in visual cortical neurons. We show that the winner-take-all network performs exceptionally well on optimization problems with greater than 5 dimensions and runs at a lower iteration count as compared to other PSO topologies. Finally we show that this variant of PSO is able to recreate auditory frequency tuning curves and modulation transfer functions, making it a potentially useful tool for computational neuroscience models. PMID:27726048

Reverse engineering of machine-tool settings with modified roll for spiral bevel pinions

NASA Astrophysics Data System (ADS)

Liu, Guanglei; Chang, Kai; Liu, Zeliang

2013-05-01

Although a great deal of research has been dedicated to the synthesis of spiral bevel gears, little related to reverse engineering can be found. An approach is proposed to reverse the machine-tool settings of the pinion of a spiral bevel gear drive on the basis of the blank and tooth surface data obtained by a coordinate measuring machine(CMM). Real tooth contact analysis(RTCA) is performed to preliminary ascertain the contact pattern, the motion curve, as well as the position of the mean contact point. And then the tangent to the contact path and the motion curve are interpolated in the sense of the least square method to extract the initial values of the bias angle and the higher order coefficients(HOC) in modified roll motion. A trial tooth surface is generated by machine-tool settings derived from the local synthesis relating to the initial meshing performances and modified roll motion. An optimization objective is formed which equals the tooth surface deviation between the real tooth surface and the trial tooth surface. The design variables are the parameters describing the meshing performances at the mean contact point in addition to the HOC. When the objective is optimized within an arbitrarily given convergence tolerance, the machine-tool settings together with the HOC are obtained. The proposed approach is verified by a spiral bevel pinion used in the accessory gear box of an aviation engine. The trial tooth surfaces approach to the real tooth surface on the whole in the example. The results show that the convergent tooth surface deviation for the concave side on the average is less than 0.5 μm, and is less than 1.3 μm for the convex side. The biggest tooth surface deviation is 6.7 μm which is located at the corner of the grid on the convex side. Those nodes with relative bigger tooth surface deviations are all located at the boundary of the grid. An approach is proposed to figure out the machine-tool settings of a spiral bevel pinion by way of reverse engineering without having known the theoretical tooth surfaces and the corresponding machine-tool settings.

INDUSTRIE 4.0 - Automation in weft knitting technology

NASA Astrophysics Data System (ADS)

Simonis, K.; Gloy, Y.-S.; Gries, T.

2016-07-01

Industry 4.0 applies to the knitting industry. Regarding the knitting process retrofitting activities are executed mostly manually by an operator on the basis on the operator's experience. In doing so, the knitted fabric is not necessarily produced in the most efficient way regarding process speed and fabric quality aspects. The knitting division at ITA is concentrating on project activities regarding automation and Industry 4.0. ITA is working on analysing the correspondences of the knitting process parameters and their influence on the fabric quality. By using e.g. the augmented reality technology, the operator will be supported when setting up the knitting machine in case of product or pattern change - or in case of an intervention when production errors occur. Furthermore, the RFID-Technology offers great possibilities to ensure information flow between sub-processes of the fragmented textile process chain. ITA is using RFID-chips to save yarn production information and connect the information to the fabric producing machine control. In addition, ITA is currently working on integrating image processing systems into the large circular knitting machine in order to ensure online-quality measurement of the knitted fabrics. This will lead to a self-optimizing and selflearning knitting machine.

A comparison of numerical and machine-learning modeling of soil water content with limited input data

NASA Astrophysics Data System (ADS)

Karandish, Fatemeh; Šimůnek, Jiří

2016-12-01

Soil water content (SWC) is a key factor in optimizing the usage of water resources in agriculture since it provides information to make an accurate estimation of crop water demand. Methods for predicting SWC that have simple data requirements are needed to achieve an optimal irrigation schedule, especially for various water-saving irrigation strategies that are required to resolve both food and water security issues under conditions of water shortages. Thus, a two-year field investigation was carried out to provide a dataset to compare the effectiveness of HYDRUS-2D, a physically-based numerical model, with various machine-learning models, including Multiple Linear Regressions (MLR), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), and Support Vector Machines (SVM), for simulating time series of SWC data under water stress conditions. SWC was monitored using TDRs during the maize growing seasons of 2010 and 2011. Eight combinations of six, simple, independent parameters, including pan evaporation and average air temperature as atmospheric parameters, cumulative growth degree days (cGDD) and crop coefficient (Kc) as crop factors, and water deficit (WD) and irrigation depth (In) as crop stress factors, were adopted for the estimation of SWCs in the machine-learning models. Having Root Mean Square Errors (RMSE) in the range of 0.54-2.07 mm, HYDRUS-2D ranked first for the SWC estimation, while the ANFIS and SVM models with input datasets of cGDD, Kc, WD and In ranked next with RMSEs ranging from 1.27 to 1.9 mm and mean bias errors of -0.07 to 0.27 mm, respectively. However, the MLR models did not perform well for SWC forecasting, mainly due to non-linear changes of SWCs under the irrigation process. The results demonstrated that despite requiring only simple input data, the ANFIS and SVM models could be favorably used for SWC predictions under water stress conditions, especially when there is a lack of data. However, process-based numerical models are undoubtedly a better choice for predicting SWCs with lower uncertainties when required data are available, and thus for designing water saving strategies for agriculture and for other environmental applications requiring estimates of SWCs.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hasan, Iftekhar; Husain, Tausif; Sozer, Yilmaz

This paper proposes an analytical machine design tool using magnetic equivalent circuit (MEC)-based particle swarm optimization (PSO) for a double-sided, flux-concentrating transverse flux machine (TFM). The magnetic equivalent circuit method is applied to analytically establish the relationship between the design objective and the input variables of prospective TFM designs. This is computationally less intensive and more time efficient than finite element solvers. A PSO algorithm is then used to design a machine with the highest torque density within the specified power range along with some geometric design constraints. The stator pole length, magnet length, and rotor thickness are the variablesmore » that define the optimization search space. Finite element analysis (FEA) was carried out to verify the performance of the MEC-PSO optimized machine. The proposed analytical design tool helps save computation time by at least 50% when compared to commercial FEA-based optimization programs, with results found to be in agreement with less than 5% error.« less

Intelligent Systems for Stabilizing Mode-Locked Lasers and Frequency Combs: Machine Learning and Equation-Free Control Paradigms for Self-Tuning Optics

NASA Astrophysics Data System (ADS)

Kutz, J. Nathan; Brunton, Steven L.

2015-12-01

We demonstrate that a software architecture using innovations in machine learning and adaptive control provides an ideal integration platform for self-tuning optics. For mode-locked lasers, commercially available optical telecom components can be integrated with servocontrollers to enact a training and execution software module capable of self-tuning the laser cavity even in the presence of mechanical and/or environmental perturbations, thus potentially stabilizing a frequency comb. The algorithm training stage uses an exhaustive search of parameter space to discover best regions of performance for one or more objective functions of interest. The execution stage first uses a sparse sensing procedure to recognize the parameter space before quickly moving to the near optimal solution and maintaining it using the extremum seeking control protocol. The method is robust and equationfree, thus requiring no detailed or quantitatively accurate model of the physics. It can also be executed on a broad range of problems provided only that suitable objective functions can be found and experimentally measured.

A hybrid algorithm optimization approach for machine loading problem in flexible manufacturing system

NASA Astrophysics Data System (ADS)

Kumar, Vijay M.; Murthy, ANN; Chandrashekara, K.

2012-05-01

The production planning problem of flexible manufacturing system (FMS) concerns with decisions that have to be made before an FMS begins to produce parts according to a given production plan during an upcoming planning horizon. The main aspect of production planning deals with machine loading problem in which selection of a subset of jobs to be manufactured and assignment of their operations to the relevant machines are made. Such problems are not only combinatorial optimization problems, but also happen to be non-deterministic polynomial-time-hard, making it difficult to obtain satisfactory solutions using traditional optimization techniques. In this paper, an attempt has been made to address the machine loading problem with objectives of minimization of system unbalance and maximization of throughput simultaneously while satisfying the system constraints related to available machining time and tool slot designing and using a meta-hybrid heuristic technique based on genetic algorithm and particle swarm optimization. The results reported in this paper demonstrate the model efficiency and examine the performance of the system with respect to measures such as throughput and system utilization.

Experimental and numerical study on optimization of the single point incremental forming of AINSI 304L stainless steel sheet

NASA Astrophysics Data System (ADS)

Saidi, B.; Giraud-Moreau, L.; Cherouat, A.; Nasri, R.

2017-09-01

AINSI 304L stainless steel sheets are commonly formed into a variety of shapes for applications in the industrial, architectural, transportation and automobile fields, it’s also used for manufacturing of denture base. In the field of dentistry, there is a need for personalized devises that are custom made for the patient. The single point incremental forming process is highly promising in this area for manufacturing of denture base. The single point incremental forming process (ISF) is an emerging process based on the use of a spherical tool, which is moved along CNC controlled tool path. One of the major advantages of this process is the ability to program several punch trajectories on the same machine in order to obtain different shapes. Several applications of this process exist in the medical field for the manufacturing of personalized titanium prosthesis (cranial plate, knee prosthesis...) due to the need of product customization to each patient. The objective of this paper is to study the incremental forming of AISI 304L stainless steel sheets for future applications in the dentistry field. During the incremental forming process, considerable forces can occur. The control of the forming force is particularly important to ensure the safe use of the CNC milling machine and preserve the tooling and machinery. In this paper, the effect of four different process parameters on the maximum force is studied. The proposed approach consists in using an experimental design based on experimental results. An analysis of variance was conducted with ANOVA to find the input parameters allowing to minimize the maximum forming force. A numerical simulation of the incremental forming process is performed with the optimal input process parameters. Numerical results are compared with the experimental ones.

Scheduling Jobs with Variable Job Processing Times on Unrelated Parallel Machines

PubMed Central

Zhang, Guang-Qian; Wang, Jian-Jun; Liu, Ya-Jing

2014-01-01

m unrelated parallel machines scheduling problems with variable job processing times are considered, where the processing time of a job is a function of its position in a sequence, its starting time, and its resource allocation. The objective is to determine the optimal resource allocation and the optimal schedule to minimize a total cost function that dependents on the total completion (waiting) time, the total machine load, the total absolute differences in completion (waiting) times on all machines, and total resource cost. If the number of machines is a given constant number, we propose a polynomial time algorithm to solve the problem. PMID:24982933

Mathematical calibration procedure of a capacitive sensor-based indexed metrology platform

NASA Astrophysics Data System (ADS)

Brau-Avila, A.; Santolaria, J.; Acero, R.; Valenzuela-Galvan, M.; Herrera-Jimenez, V. M.; Aguilar, J. J.

2017-03-01

The demand for faster and more reliable measuring tasks for the control and quality assurance of modern production systems has created new challenges for the field of coordinate metrology. Thus, the search for new solutions in coordinate metrology systems and the need for the development of existing ones still persists. One example of such a system is the portable coordinate measuring machine (PCMM), the use of which in industry has considerably increased in recent years, mostly due to its flexibility for accomplishing in-line measuring tasks as well as its reduced cost and operational advantages compared to traditional coordinate measuring machines. Nevertheless, PCMMs have a significant drawback derived from the techniques applied in the verification and optimization procedures of their kinematic parameters. These techniques are based on the capture of data with the measuring instrument from a calibrated gauge object, fixed successively in various positions so that most of the instrument measuring volume is covered, which results in time-consuming, tedious and expensive verification and optimization procedures. In this work the mathematical calibration procedure of a capacitive sensor-based indexed metrology platform (IMP) is presented. This calibration procedure is based on the readings and geometric features of six capacitive sensors and their targets with nanometer resolution. The final goal of the IMP calibration procedure is to optimize the geometric features of the capacitive sensors and their targets in order to use the optimized data in the verification procedures of PCMMs.

Magic in the machine: a computational magician's assistant

PubMed Central

Williams, Howard; McOwan, Peter W.

2014-01-01

A human magician blends science, psychology, and performance to create a magical effect. In this paper we explore what can be achieved when that human intelligence is replaced or assisted by machine intelligence. Magical effects are all in some form based on hidden mathematical, scientific, or psychological principles; often the parameters controlling these underpinning techniques are hard for a magician to blend to maximize the magical effect required. The complexity is often caused by interacting and often conflicting physical and psychological constraints that need to be optimally balanced. Normally this tuning is done by trial and error, combined with human intuitions. Here we focus on applying Artificial Intelligence methods to the creation and optimization of magic tricks exploiting mathematical principles. We use experimentally derived data about particular perceptual and cognitive features, combined with a model of the underlying mathematical process to provide a psychologically valid metric to allow optimization of magical impact. In the paper we introduce our optimization methodology and describe how it can be flexibly applied to a range of different types of mathematics based tricks. We also provide two case studies as exemplars of the methodology at work: a magical jigsaw, and a mind reading card trick effect. We evaluate each trick created through testing in laboratory and public performances, and further demonstrate the real world efficacy of our approach for professional performers through sales of the tricks in a reputable magic shop in London. PMID:25452736

Investigations on high speed machining of EN-353 steel alloy under different machining environments

NASA Astrophysics Data System (ADS)

Venkata Vishnu, A.; Jamaleswara Kumar, P.

2018-03-01

The addition of Nano Particles into conventional cutting fluids enhances its cooling capabilities; in the present paper an attempt is made by adding nano sized particles into conventional cutting fluids. Taguchi Robust Design Methodology is employed in order to study the performance characteristics of different turning parameters i.e. cutting speed, feed rate, depth of cut and type of tool under different machining environments i.e. dry machining, machining with lubricant - SAE 40 and machining with mixture of nano sized particles of Boric acid and base fluid SAE 40. A series of turning operations were performed using L27 (3)13 orthogonal array, considering high cutting speeds and the other machining parameters to measure hardness. The results are compared among the different machining environments, and it is concluded that there is considerable improvement in the machining performance using lubricant SAE 40 and mixture of SAE 40 + boric acid compared with dry machining. The ANOVA suggests that the selected parameters and the interactions are significant and cutting speed has most significant effect on hardness.

Machine Learning, deep learning and optimization in computer vision

NASA Astrophysics Data System (ADS)

Canu, Stéphane

2017-03-01

As quoted in the Large Scale Computer Vision Systems NIPS workshop, computer vision is a mature field with a long tradition of research, but recent advances in machine learning, deep learning, representation learning and optimization have provided models with new capabilities to better understand visual content. The presentation will go through these new developments in machine learning covering basic motivations, ideas, models and optimization in deep learning for computer vision, identifying challenges and opportunities. It will focus on issues related with large scale learning that is: high dimensional features, large variety of visual classes, and large number of examples.

Continuous performance measurement in flight systems. [sequential control model

NASA Technical Reports Server (NTRS)

Connelly, E. M.; Sloan, N. A.; Zeskind, R. M.

1975-01-01

The desired response of many man machine control systems can be formulated as a solution to an optimal control synthesis problem where the cost index is given and the resulting optimal trajectories correspond to the desired trajectories of the man machine system. Optimal control synthesis provides the reference criteria and the significance of error information required for performance measurement. The synthesis procedure described provides a continuous performance measure (CPM) which is independent of the mechanism generating the control action. Therefore, the technique provides a meaningful method for online evaluation of man's control capability in terms of total man machine performance.

Controlling Continuous-Variable Quantum Key Distribution with Entanglement in the Middle Using Tunable Linear Optics Cloning Machines

NASA Astrophysics Data System (ADS)

Wu, Xiao Dong; Chen, Feng; Wu, Xiang Hua; Guo, Ying

2017-02-01

Continuous-variable quantum key distribution (CVQKD) can provide detection efficiency, as compared to discrete-variable quantum key distribution (DVQKD). In this paper, we demonstrate a controllable CVQKD with the entangled source in the middle, contrast to the traditional point-to-point CVQKD where the entanglement source is usually created by one honest party and the Gaussian noise added on the reference partner of the reconciliation is uncontrollable. In order to harmonize the additive noise that originates in the middle to resist the effect of malicious eavesdropper, we propose a controllable CVQKD protocol by performing a tunable linear optics cloning machine (LOCM) at one participant's side, say Alice. Simulation results show that we can achieve the optimal secret key rates by selecting the parameters of the tuned LOCM in the derived regions.

A sustainable solid state recycling of pure aluminum by means of friction stir extrusion process (FSE)

NASA Astrophysics Data System (ADS)

Mehtedi, Mohamad El; Forcellese, Archimede; Simoncini, Michela; Spigarelli, Stefano

2018-05-01

In this research, the feasibility of solid-state recycling of pure aluminum AA1099 machining chips using FSE process is investigated. In the early stage, a FE simulation was conducted in order to optimize the die design and the process parameters in terms of plunge rotational speed and extrusion rate. The AA1099 aluminum chips were produced by turning of an as-received bar without lubrication. The chips were compacted on a MTS machine up to 150KN of load. The extruded samples were analyzed by optical and electron microscope in order to see the material flow and to characterize the microstructure. Finally, micro-hardness Vickers profiles were carried out, in both longitudinal and transversal direction of the obtained profiles, in order to investigate the homogeneity of the mechanical properties of the extrudate.

Study of Material Densification of In718 in the Higher Throughput Parameter Regime

NASA Technical Reports Server (NTRS)

Cordner, Samuel

2016-01-01

Selective Laser Melting (SLM) is a powder bed fusion additive manufacturing process used increasingly in the aerospace industry to reduce the cost, weight, and fabrication time for complex propulsion components. Previous optimization studies for SLM using the Concept Laser M1 and M2 machines at NASA Marshall Space Flight Center have centered on machine default parameters. The objective of this project is to characterize how heat treatment affects density and porosity from a microscopic point of view. This is performs using higher throughput parameters (a previously unexplored region of the manufacturing operating envelope for this application) on material consolidation. Density blocks were analyzed to explore the relationship between build parameters (laser power, scan speed, and hatch spacing) and material consolidation (assessed in terms of density and porosity). The study also considers the impact of post-processing, specifically hot isostatic pressing and heat treatment, as well as deposition pattern on material consolidation in the higher energy parameter regime. Metallurgical evaluation of specimens will also be presented. This work will contribute to creating a knowledge base (understanding material behavior in all ranges of the AM equipment operating envelope) that is critical to transitioning AM from the custom low rate production sphere it currently occupies to the world of mass high rate production, where parts are fabricated at a rapid rate with confidence that they will meet or exceed all stringent functional requirements for spaceflight hardware. These studies will also provide important data on the sensitivity of material consolidation to process parameters that will inform the design and development of future flight articles using SLM.

LED light design method for high contrast and uniform illumination imaging in machine vision.

PubMed

Wu, Xiaojun; Gao, Guangming

2018-03-01

In machine vision, illumination is very critical to determine the complexity of the inspection algorithms. Proper lights can obtain clear and sharp images with the highest contrast and low noise between the interested object and the background, which is conducive to the target being located, measured, or inspected. Contrary to the empirically based trial-and-error convention to select the off-the-shelf LED light in machine vision, an optimization algorithm for LED light design is proposed in this paper. It is composed of the contrast optimization modeling and the uniform illumination technology for non-normal incidence (UINI). The contrast optimization model is built based on the surface reflection characteristics, e.g., the roughness, the reflective index, and light direction, etc., to maximize the contrast between the features of interest and the background. The UINI can keep the uniformity of the optimized lighting by the contrast optimization model. The simulation and experimental results demonstrate that the optimization algorithm is effective and suitable to produce images with the highest contrast and uniformity, which is very inspirational to the design of LED illumination systems in machine vision.

Simulating carbon and water fluxes at Arctic and boreal ecosystems in Alaska by optimizing the modified BIOME-BGC with eddy covariance data

NASA Astrophysics Data System (ADS)

Ueyama, M.; Kondo, M.; Ichii, K.; Iwata, H.; Euskirchen, E. S.; Zona, D.; Rocha, A. V.; Harazono, Y.; Nakai, T.; Oechel, W. C.

2013-12-01

To better predict carbon and water cycles in Arctic ecosystems, we modified a process-based ecosystem model, BIOME-BGC, by introducing new processes: change in active layer depth on permafrost and phenology of tundra vegetation. The modified BIOME-BGC was optimized using an optimization method. The model was constrained using gross primary productivity (GPP) and net ecosystem exchange (NEE) at 23 eddy covariance sites in Alaska, and vegetation/soil carbon from a literature survey. The model was used to simulate regional carbon and water fluxes of Alaska from 1900 to 2011. Simulated regional fluxes were validated with upscaled GPP, ecosystem respiration (RE), and NEE based on two methods: (1) a machine learning technique and (2) a top-down model. Our initial simulation suggests that the original BIOME-BGC with default ecophysiological parameters substantially underestimated GPP and RE for tundra and overestimated those fluxes for boreal forests. We will discuss how optimization using the eddy covariance data impacts the historical simulation by comparing the new version of the model with simulated results from the original BIOME-BGC with default ecophysiological parameters. This suggests that the incorporation of the active layer depth and plant phenology processes is important to include when simulating carbon and water fluxes in Arctic ecosystems.

An Interactive Astronaut-Robot System with Gesture Control

PubMed Central

Liu, Jinguo; Luo, Yifan; Ju, Zhaojie

2016-01-01

Human-robot interaction (HRI) plays an important role in future planetary exploration mission, where astronauts with extravehicular activities (EVA) have to communicate with robot assistants by speech-type or gesture-type user interfaces embedded in their space suits. This paper presents an interactive astronaut-robot system integrating a data-glove with a space suit for the astronaut to use hand gestures to control a snake-like robot. Support vector machine (SVM) is employed to recognize hand gestures and particle swarm optimization (PSO) algorithm is used to optimize the parameters of SVM to further improve its recognition accuracy. Various hand gestures from American Sign Language (ASL) have been selected and used to test and validate the performance of the proposed system. PMID:27190503

Identification of spilled oils by NIR spectroscopy technology based on KPCA and LSSVM

NASA Astrophysics Data System (ADS)

Tan, Ailing; Bi, Weihong

2011-08-01

Oil spills on the sea surface are seen relatively often with the development of the petroleum exploitation and transportation of the sea. Oil spills are great threat to the marine environment and the ecosystem, thus the oil pollution in the ocean becomes an urgent topic in the environmental protection. To develop the oil spill accident treatment program and track the source of the spilled oils, a novel qualitative identification method combined Kernel Principal Component Analysis (KPCA) and Least Square Support Vector Machine (LSSVM) was proposed. The proposed method adapt Fourier transform NIR spectrophotometer to collect the NIR spectral data of simulated gasoline, diesel fuel and kerosene oil spills samples and do some pretreatments to the original spectrum. We use the KPCA algorithm which is an extension of Principal Component Analysis (PCA) using techniques of kernel methods to extract nonlinear features of the preprocessed spectrum. Support Vector Machines (SVM) is a powerful methodology for solving spectral classification tasks in chemometrics. LSSVM are reformulations to the standard SVMs which lead to solving a system of linear equations. So a LSSVM multiclass classification model was designed which using Error Correcting Output Code (ECOC) method borrowing the idea of error correcting codes used for correcting bit errors in transmission channels. The most common and reliable approach to parameter selection is to decide on parameter ranges, and to then do a grid search over the parameter space to find the optimal model parameters. To test the proposed method, 375 spilled oil samples of unknown type were selected to study. The optimal model has the best identification capabilities with the accuracy of 97.8%. Experimental results show that the proposed KPCA plus LSSVM qualitative analysis method of near infrared spectroscopy has good recognition result, which could work as a new method for rapid identification of spilled oils.

Taguchi Optimization of Cutting Parameters in Turning AISI 1020 MS with M2 HSS Tool

NASA Astrophysics Data System (ADS)

Sonowal, Dharindom; Sarma, Dhrupad; Bakul Barua, Parimal; Nath, Thuleswar

2017-08-01

In this paper the effect of three cutting parameters viz. Spindle speed, Feed and Depth of Cut on surface roughness of AISI 1020 mild steel bar in turning was investigated and optimized to obtain minimum surface roughness. All the experiments are conducted on HMT LB25 lathe machine using M2 HSS cutting tool. Ranges of parameters of interest have been decided through some preliminary experimentation (One Factor At a Time experiments). Finally a combined experiment has been carried out using Taguchi’s L27 Orthogonal Array (OA) to study the main effect and interaction effect of the all three parameters. The experimental results were analyzed with raw data ANOVA (Analysis of Variance) and S/N data (Signal to Noise ratio) ANOVA. Results show that Spindle speed, Feed and Depth of Cut have significant effects on both mean and variation of surface roughness in turning AISI 1020 mild steel. Mild two factors interactions are observed among the aforesaid factors with significant effects only on the mean of the output variable. From the Taguchi parameter optimization the optimum factor combination is found to be 630 rpm spindle speed, 0.05 mm/rev feed and 1.25 mm depth of cut with estimated surface roughness 2.358 ± 0.970 µm. A confirmatory experiment was conducted with the optimum factor combination to verify the results. In the confirmatory experiment the average value of surface roughness is found to be 2.408 µm which is well within the range (0.418 µm to 4.299 µm) predicted for confirmatory experiment.

Bias in error estimation when using cross-validation for model selection.

PubMed

Varma, Sudhir; Simon, Richard

2006-02-23

Cross-validation (CV) is an effective method for estimating the prediction error of a classifier. Some recent articles have proposed methods for optimizing classifiers by choosing classifier parameter values that minimize the CV error estimate. We have evaluated the validity of using the CV error estimate of the optimized classifier as an estimate of the true error expected on independent data. We used CV to optimize the classification parameters for two kinds of classifiers; Shrunken Centroids and Support Vector Machines (SVM). Random training datasets were created, with no difference in the distribution of the features between the two classes. Using these "null" datasets, we selected classifier parameter values that minimized the CV error estimate. 10-fold CV was used for Shrunken Centroids while Leave-One-Out-CV (LOOCV) was used for the SVM. Independent test data was created to estimate the true error. With "null" and "non null" (with differential expression between the classes) data, we also tested a nested CV procedure, where an inner CV loop is used to perform the tuning of the parameters while an outer CV is used to compute an estimate of the error. The CV error estimate for the classifier with the optimal parameters was found to be a substantially biased estimate of the true error that the classifier would incur on independent data. Even though there is no real difference between the two classes for the "null" datasets, the CV error estimate for the Shrunken Centroid with the optimal parameters was less than 30% on 18.5% of simulated training data-sets. For SVM with optimal parameters the estimated error rate was less than 30% on 38% of "null" data-sets. Performance of the optimized classifiers on the independent test set was no better than chance. The nested CV procedure reduces the bias considerably and gives an estimate of the error that is very close to that obtained on the independent testing set for both Shrunken Centroids and SVM classifiers for "null" and "non-null" data distributions. We show that using CV to compute an error estimate for a classifier that has itself been tuned using CV gives a significantly biased estimate of the true error. Proper use of CV for estimating true error of a classifier developed using a well defined algorithm requires that all steps of the algorithm, including classifier parameter tuning, be repeated in each CV loop. A nested CV procedure provides an almost unbiased estimate of the true error.

Process Parameters Optimization in Single Point Incremental Forming

NASA Astrophysics Data System (ADS)

Gulati, Vishal; Aryal, Ashmin; Katyal, Puneet; Goswami, Amitesh

2016-04-01

This work aims to optimize the formability and surface roughness of parts formed by the single-point incremental forming process for an Aluminium-6063 alloy. The tests are based on Taguchi's L18 orthogonal array selected on the basis of DOF. The tests have been carried out on vertical machining center (DMC70V); using CAD/CAM software (SolidWorks V5/MasterCAM). Two levels of tool radius, three levels of sheet thickness, step size, tool rotational speed, feed rate and lubrication have been considered as the input process parameters. Wall angle and surface roughness have been considered process responses. The influential process parameters for the formability and surface roughness have been identified with the help of statistical tool (response table, main effect plot and ANOVA). The parameter that has the utmost influence on formability and surface roughness is lubrication. In the case of formability, lubrication followed by the tool rotational speed, feed rate, sheet thickness, step size and tool radius have the influence in descending order. Whereas in surface roughness, lubrication followed by feed rate, step size, tool radius, sheet thickness and tool rotational speed have the influence in descending order. The predicted optimal values for the wall angle and surface roughness are found to be 88.29° and 1.03225 µm. The confirmation experiments were conducted thrice and the value of wall angle and surface roughness were found to be 85.76° and 1.15 µm respectively.

Two-qubit quantum cloning machine and quantum correlation broadcasting

NASA Astrophysics Data System (ADS)

Kheirollahi, Azam; Mohammadi, Hamidreza; Akhtarshenas, Seyed Javad

2016-11-01

Due to the axioms of quantum mechanics, perfect cloning of an unknown quantum state is impossible. But since imperfect cloning is still possible, a question arises: "Is there an optimal quantum cloning machine?" Buzek and Hillery answered this question and constructed their famous B-H quantum cloning machine. The B-H machine clones the state of an arbitrary single qubit in an optimal manner and hence it is universal. Generalizing this machine for a two-qubit system is straightforward, but during this procedure, except for product states, this machine loses its universality and becomes a state-dependent cloning machine. In this paper, we propose some classes of optimal universal local quantum state cloners for a particular class of two-qubit systems, more precisely, for a class of states with known Schmidt basis. We then extend our machine to the case that the Schmidt basis of the input state is deviated from the local computational basis of the machine. We show that more local quantum coherence existing in the input state corresponds to less fidelity between the input and output states. Also we present two classes of a state-dependent local quantum copying machine. Furthermore, we investigate local broadcasting of two aspects of quantum correlations, i.e., quantum entanglement and quantum discord, defined, respectively, within the entanglement-separability paradigm and from an information-theoretic perspective. The results show that although quantum correlation is, in general, very fragile during the broadcasting procedure, quantum discord is broadcasted more robustly than quantum entanglement.

An Effective Mechanism for Virtual Machine Placement using Aco in IAAS Cloud

NASA Astrophysics Data System (ADS)

Shenbaga Moorthy, Rajalakshmi; Fareentaj, U.; Divya, T. K.

2017-08-01

Cloud computing provides an effective way to dynamically provide numerous resources to meet customer demands. A major challenging problem for cloud providers is designing efficient mechanisms for optimal virtual machine Placement (OVMP). Such mechanisms enable the cloud providers to effectively utilize their available resources and obtain higher profits. In order to provide appropriate resources to the clients an optimal virtual machine placement algorithm is proposed. Virtual machine placement is NP-Hard problem. Such NP-Hard problem can be solved using heuristic algorithm. In this paper, Ant Colony Optimization based virtual machine placement is proposed. Our proposed system focuses on minimizing the cost spending in each plan for hosting virtual machines in a multiple cloud provider environment and the response time of each cloud provider is monitored periodically, in such a way to minimize delay in providing the resources to the users. The performance of the proposed algorithm is compared with greedy mechanism. The proposed algorithm is simulated in Eclipse IDE. The results clearly show that the proposed algorithm minimizes the cost, response time and also number of migrations.

Optimal Model-Based Fault Estimation and Correction for Particle Accelerators and Industrial Plants Using Combined Support Vector Machines and First Principles Models

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sayyar-Rodsari, Bijan; Schweiger, Carl; /SLAC /Pavilion Technologies, Inc., Austin, TX

2010-08-25

Timely estimation of deviations from optimal performance in complex systems and the ability to identify corrective measures in response to the estimated parameter deviations has been the subject of extensive research over the past four decades. The implications in terms of lost revenue from costly industrial processes, operation of large-scale public works projects and the volume of the published literature on this topic clearly indicates the significance of the problem. Applications range from manufacturing industries (integrated circuits, automotive, etc.), to large-scale chemical plants, pharmaceutical production, power distribution grids, and avionics. In this project we investigated a new framework for buildingmore » parsimonious models that are suited for diagnosis and fault estimation of complex technical systems. We used Support Vector Machines (SVMs) to model potentially time-varying parameters of a First-Principles (FP) description of the process. The combined SVM & FP model was built (i.e. model parameters were trained) using constrained optimization techniques. We used the trained models to estimate faults affecting simulated beam lifetime. In the case where a large number of process inputs are required for model-based fault estimation, the proposed framework performs an optimal nonlinear principal component analysis of the large-scale input space, and creates a lower dimension feature space in which fault estimation results can be effectively presented to the operation personnel. To fulfill the main technical objectives of the Phase I research, our Phase I efforts have focused on: (1) SVM Training in a Combined Model Structure - We developed the software for the constrained training of the SVMs in a combined model structure, and successfully modeled the parameters of a first-principles model for beam lifetime with support vectors. (2) Higher-order Fidelity of the Combined Model - We used constrained training to ensure that the output of the SVM (i.e. the parameters of the beam lifetime model) are physically meaningful. (3) Numerical Efficiency of the Training - We investigated the numerical efficiency of the SVM training. More specifically, for the primal formulation of the training, we have developed a problem formulation that avoids the linear increase in the number of the constraints as a function of the number of data points. (4) Flexibility of Software Architecture - The software framework for the training of the support vector machines was designed to enable experimentation with different solvers. We experimented with two commonly used nonlinear solvers for our simulations. The primary application of interest for this project has been the sustained optimal operation of particle accelerators at the Stanford Linear Accelerator Center (SLAC). Particle storage rings are used for a variety of applications ranging from 'colliding beam' systems for high-energy physics research to highly collimated x-ray generators for synchrotron radiation science. Linear accelerators are also used for collider research such as International Linear Collider (ILC), as well as for free electron lasers, such as the Linear Coherent Light Source (LCLS) at SLAC. One common theme in the operation of storage rings and linear accelerators is the need to precisely control the particle beams over long periods of time with minimum beam loss and stable, yet challenging, beam parameters. We strongly believe that beyond applications in particle accelerators, the high fidelity and cost benefits of a combined model-based fault estimation/correction system will attract customers from a wide variety of commercial and scientific industries. Even though the acquisition of Pavilion Technologies, Inc. by Rockwell Automation Inc. in 2007 has altered the small business status of the Pavilion and it no longer qualifies for a Phase II funding, our findings in the course of the Phase I research have convinced us that further research will render a workable model-based fault estimation and correction for particle accelerators and industrial plants feasible.« less

Impact of Spot Size and Spacing on the Quality of Robustly Optimized Intensity Modulated Proton Therapy Plans for Lung Cancer.

PubMed

Liu, Chenbin; Schild, Steven E; Chang, Joe Y; Liao, Zhongxing; Korte, Shawn; Shen, Jiajian; Ding, Xiaoning; Hu, Yanle; Kang, Yixiu; Keole, Sameer R; Sio, Terence T; Wong, William W; Sahoo, Narayan; Bues, Martin; Liu, Wei

2018-06-01

To investigate how spot size and spacing affect plan quality, robustness, and interplay effects of robustly optimized intensity modulated proton therapy (IMPT) for lung cancer. Two robustly optimized IMPT plans were created for 10 lung cancer patients: first by a large-spot machine with in-air energy-dependent large spot size at isocenter (σ: 6-15 mm) and spacing (1.3 σ), and second by a small-spot machine with in-air energy-dependent small spot size (σ: 2-6 mm) and spacing (5 mm). Both plans were generated by optimizing radiation dose to internal target volume on averaged 4-dimensional computed tomography scans using an in-house-developed IMPT planning system. The dose-volume histograms band method was used to evaluate plan robustness. Dose evaluation software was developed to model time-dependent spot delivery to incorporate interplay effects with randomized starting phases for each field per fraction. Patient anatomy voxels were mapped phase-to-phase via deformable image registration, and doses were scored using in-house-developed software. Dose-volume histogram indices, including internal target volume dose coverage, homogeneity, and organs at risk (OARs) sparing, were compared using the Wilcoxon signed-rank test. Compared with the large-spot machine, the small-spot machine resulted in significantly lower heart and esophagus mean doses, with comparable target dose coverage, homogeneity, and protection of other OARs. Plan robustness was comparable for targets and most OARs. With interplay effects considered, significantly lower heart and esophagus mean doses with comparable target dose coverage and homogeneity were observed using smaller spots. Robust optimization with a small spot-machine significantly improves heart and esophagus sparing, with comparable plan robustness and interplay effects compared with robust optimization with a large-spot machine. A small-spot machine uses a larger number of spots to cover the same tumors compared with a large-spot machine, which gives the planning system more freedom to compensate for the higher sensitivity to uncertainties and interplay effects for lung cancer treatments. Copyright © 2018 Elsevier Inc. All rights reserved.

DOE Office of Scientific and Technical Information (OSTI.GOV)

Durt, Thomas; Fiurasek, Jaromir; Department of Optics, Palacky University, 17. listopadu 50, 77200 Olomouc

The possibility of cloning a d-dimensional quantum system without an ancilla is explored, extending on the economical phase-covariant cloning machine for qubits found in Phys. Rev. A 60, 2764 (1999). We prove the impossibility of constructing an economical version of the optimal universal 1{yields}2 cloning machine in any dimension. We also show, using an ansatz on the generic form of cloning machines, that the d-dimensional 1{yields}2 phase-covariant cloner, which optimally clones all balanced superpositions with arbitrary phases, can be realized economically only in dimension d=2. The used ansatz is supported by numerical evidence up to d=7. An economical phase-covariant clonermore » can nevertheless be constructed for d>2, albeit with a slightly lower fidelity than that of the optimal cloner requiring an ancilla. Finally, using again an ansatz on cloning machines, we show that an economical version of the 1{yields}2 Fourier-covariant cloner, which optimally clones the computational basis and its Fourier transform, is also possible only in dimension d=2.« less

Economical quantum cloning in any dimension

NASA Astrophysics Data System (ADS)

Durt, Thomas; Fiurášek, Jaromír; Cerf, Nicolas J.

2005-11-01

The possibility of cloning a d -dimensional quantum system without an ancilla is explored, extending on the economical phase-covariant cloning machine for qubits found in Phys. Rev. A 60, 2764 (1999). We prove the impossibility of constructing an economical version of the optimal universal 1→2 cloning machine in any dimension. We also show, using an ansatz on the generic form of cloning machines, that the d -dimensional 1→2 phase-covariant cloner, which optimally clones all balanced superpositions with arbitrary phases, can be realized economically only in dimension d=2 . The used ansatz is supported by numerical evidence up to d=7 . An economical phase-covariant cloner can nevertheless be constructed for d>2 , albeit with a slightly lower fidelity than that of the optimal cloner requiring an ancilla. Finally, using again an ansatz on cloning machines, we show that an economical version of the 1→2 Fourier-covariant cloner, which optimally clones the computational basis and its Fourier transform, is also possible only in dimension d=2 .

Comparative Investigation on Tool Wear during End Milling of AISI H13 Steel with Different Tool Path Strategies

NASA Astrophysics Data System (ADS)

Adesta, Erry Yulian T.; Riza, Muhammad; Avicena

2018-03-01

Tool wear prediction plays a significant role in machining industry for proper planning and control machining parameters and optimization of cutting conditions. This paper aims to investigate the effect of tool path strategies that are contour-in and zigzag tool path strategies applied on tool wear during pocket milling process. The experiments were carried out on CNC vertical machining centre by involving PVD coated carbide inserts. Cutting speed, feed rate and depth of cut were set to vary. In an experiment with three factors at three levels, Response Surface Method (RSM) design of experiment with a standard called Central Composite Design (CCD) was employed. Results obtained indicate that tool wear increases significantly at higher range of feed per tooth compared to cutting speed and depth of cut. This result of this experimental work is then proven statistically by developing empirical model. The prediction model for the response variable of tool wear for contour-in strategy developed in this research shows a good agreement with experimental work.

Detection of Splice Sites Using Support Vector Machine

NASA Astrophysics Data System (ADS)

Varadwaj, Pritish; Purohit, Neetesh; Arora, Bhumika

Automatic identification and annotation of exon and intron region of gene, from DNA sequences has been an important research area in field of computational biology. Several approaches viz. Hidden Markov Model (HMM), Artificial Intelligence (AI) based machine learning and Digital Signal Processing (DSP) techniques have extensively and independently been used by various researchers to cater this challenging task. In this work, we propose a Support Vector Machine based kernel learning approach for detection of splice sites (the exon-intron boundary) in a gene. Electron-Ion Interaction Potential (EIIP) values of nucleotides have been used for mapping character sequences to corresponding numeric sequences. Radial Basis Function (RBF) SVM kernel is trained using EIIP numeric sequences. Furthermore this was tested on test gene dataset for detection of splice site by window (of 12 residues) shifting. Optimum values of window size, various important parameters of SVM kernel have been optimized for a better accuracy. Receiver Operating Characteristic (ROC) curves have been utilized for displaying the sensitivity rate of the classifier and results showed 94.82% accuracy for splice site detection on test dataset.

Advancing three-dimensional MEMS by complimentary laser micro manufacturing

NASA Astrophysics Data System (ADS)

Palmer, Jeremy A.; Williams, John D.; Lemp, Tom; Lehecka, Tom M.; Medina, Francisco; Wicker, Ryan B.

2006-01-01

This paper describes improvements that enable engineers to create three-dimensional MEMS in a variety of materials. It also provides a means for selectively adding three-dimensional, high aspect ratio features to pre-existing PMMA micro molds for subsequent LIGA processing. This complimentary method involves in situ construction of three-dimensional micro molds in a stand-alone configuration or directly adjacent to features formed by x-ray lithography. Three-dimensional micro molds are created by micro stereolithography (MSL), an additive rapid prototyping technology. Alternatively, three-dimensional features may be added by direct femtosecond laser micro machining. Parameters for optimal femtosecond laser micro machining of PMMA at 800 nanometers are presented. The technical discussion also includes strategies for enhancements in the context of material selection and post-process surface finish. This approach may lead to practical, cost-effective 3-D MEMS with the surface finish and throughput advantages of x-ray lithography. Accurate three-dimensional metal microstructures are demonstrated. Challenges remain in process planning for micro stereolithography and development of buried features following femtosecond laser micro machining.

Optimization of machining parameters in dry EDM of EN31 steel

NASA Astrophysics Data System (ADS)

Brar, G. S.

2018-03-01

Dry electric discharge machining (Dry EDM) is one of the novel EDM technology in which gases namely helium, argon, oxygen, nitrogen etc. are used as a dielectric medium at high pressure instead of oil based liquid dielectric. The present study investigates dry electric discharge machining (with rotary tool) of EN-31 steel to achieve lower tool wear rate (TWR) and better surface roughness (Ra) by performing a set of exploratory experiments with oxygen gas as dielectric. The effect of polarity, discharge current, gas flow pressure, pulse-on time, R.P.M. and gap voltage on the MRR, TWR and surface roughness (Ra) in dry EDM was studied with copper as rotary tool. The significant factors affecting MRR are discharge current and pulse on time. The significant factors affecting TWR are gas flow pressure, pulse on time and R.P.M. TWR was found close to zero in most of the experiments. The significant factors affecting Ra are pulse on time, gas flow pressure and R.P.M. It was found that polarity has nearly zero effect on all the three output variables.

Exploring the capabilities of support vector machines in detecting silent data corruptions

DOE Office of Scientific and Technical Information (OSTI.GOV)

Subasi, Omer; Di, Sheng; Bautista-Gomez, Leonardo

As the exascale era approaches, the increasing capacity of high-performance computing (HPC) systems with targeted power and energy budget goals introduces significant challenges in reliability. Silent data corruptions (SDCs), or silent errors, are one of the major sources that corrupt the execution results of HPC applications without being detected. Here in this paper, we explore a set of novel SDC detectors – by leveraging epsilon-insensitive support vector machine regression – to detect SDCs that occur in HPC applications. The key contributions are threefold. (1) Our exploration takes temporal, spatial, and spatiotemporal features into account and analyzes different detectors based onmore » different features. (2) We provide an in-depth study on the detection ability and performance with different parameters, and we optimize the detection range carefully. (3) Experiments with eight real-world HPC applications show that support-vector-machine-based detectors can achieve detection sensitivity (i.e., recall) up to 99% yet suffer a less than 1% false positive rate for most cases. Our detectors incur low performance overhead, 5% on average, for all benchmarks studied in this work.« less

Exploring the capabilities of support vector machines in detecting silent data corruptions

DOE PAGES

Subasi, Omer; Di, Sheng; Bautista-Gomez, Leonardo; ...

2018-02-01

As the exascale era approaches, the increasing capacity of high-performance computing (HPC) systems with targeted power and energy budget goals introduces significant challenges in reliability. Silent data corruptions (SDCs), or silent errors, are one of the major sources that corrupt the execution results of HPC applications without being detected. Here in this paper, we explore a set of novel SDC detectors – by leveraging epsilon-insensitive support vector machine regression – to detect SDCs that occur in HPC applications. The key contributions are threefold. (1) Our exploration takes temporal, spatial, and spatiotemporal features into account and analyzes different detectors based onmore » different features. (2) We provide an in-depth study on the detection ability and performance with different parameters, and we optimize the detection range carefully. (3) Experiments with eight real-world HPC applications show that support-vector-machine-based detectors can achieve detection sensitivity (i.e., recall) up to 99% yet suffer a less than 1% false positive rate for most cases. Our detectors incur low performance overhead, 5% on average, for all benchmarks studied in this work.« less

DOE Office of Scientific and Technical Information (OSTI.GOV)

Camingue, Pamela; Christian, Rochelle; Ng, Davin

The purpose of this study was to compare 4 different external beam radiation therapy treatment techniques for the treatment of T1-2, N0, M0 glottic cancers: traditional lateral beams with wedges (3D), 5-field intensity-modulated radiation therapy (IMRT), volumetric modulated arc therapy (VMAT), and proton therapy. Treatment plans in each technique were created for 10 patients using consistent planning parameters. The photon treatment plans were optimized using Philips Pinnacle{sub 3} v.9 and the IMRT and VMAT plans used the Direct Machine Parameter Optimization algorithm. The proton treatment plans were optimized using Varian Eclipse Proton v.8.9. The prescription used for each plan wasmore » 63 Gy in 28 fractions. The contours for spinal cord, right carotid artery, left carotid artery, and normal tissue were created with respect to the patient's bony anatomy so that proper comparisons of doses could be made with respect to volume. An example of the different isodose distributions will be shown. The data collection for comparison purposes includes: clinical treatment volume coverage, dose to spinal cord, dose to carotid arteries, and dose to normal tissue. Data comparisons will be displayed graphically showing the maximum, mean, median, and ranges of doses.« less

Stochastic parameter estimation in nonlinear time-delayed vibratory systems with distributed delay

NASA Astrophysics Data System (ADS)

Torkamani, Shahab; Butcher, Eric A.

2013-07-01

The stochastic estimation of parameters and states in linear and nonlinear time-delayed vibratory systems with distributed delay is explored. The approach consists of first employing a continuous time approximation to approximate the delayed integro-differential system with a large set of ordinary differential equations having stochastic excitations. Then the problem of state and parameter estimation in the resulting stochastic ordinary differential system is represented as an optimal filtering problem using a state augmentation technique. By adapting the extended Kalman-Bucy filter to the augmented filtering problem, the unknown parameters of the time-delayed system are estimated from noise-corrupted, possibly incomplete measurements of the states. Similarly, the upper bound of the distributed delay can also be estimated by the proposed technique. As an illustrative example to a practical problem in vibrations, the parameter, delay upper bound, and state estimation from noise-corrupted measurements in a distributed force model widely used for modeling machine tool vibrations in the turning operation is investigated.

A Combination of Geographically Weighted Regression, Particle Swarm Optimization and Support Vector Machine for Landslide Susceptibility Mapping: A Case Study at Wanzhou in the Three Gorges Area, China

PubMed Central

Yu, Xianyu; Wang, Yi; Niu, Ruiqing; Hu, Youjian

2016-01-01

In this study, a novel coupling model for landslide susceptibility mapping is presented. In practice, environmental factors may have different impacts at a local scale in study areas. To provide better predictions, a geographically weighted regression (GWR) technique is firstly used in our method to segment study areas into a series of prediction regions with appropriate sizes. Meanwhile, a support vector machine (SVM) classifier is exploited in each prediction region for landslide susceptibility mapping. To further improve the prediction performance, the particle swarm optimization (PSO) algorithm is used in the prediction regions to obtain optimal parameters for the SVM classifier. To evaluate the prediction performance of our model, several SVM-based prediction models are utilized for comparison on a study area of the Wanzhou district in the Three Gorges Reservoir. Experimental results, based on three objective quantitative measures and visual qualitative evaluation, indicate that our model can achieve better prediction accuracies and is more effective for landslide susceptibility mapping. For instance, our model can achieve an overall prediction accuracy of 91.10%, which is 7.8%–19.1% higher than the traditional SVM-based models. In addition, the obtained landslide susceptibility map by our model can demonstrate an intensive correlation between the classified very high-susceptibility zone and the previously investigated landslides. PMID:27187430

A Combination of Geographically Weighted Regression, Particle Swarm Optimization and Support Vector Machine for Landslide Susceptibility Mapping: A Case Study at Wanzhou in the Three Gorges Area, China.

PubMed

Yu, Xianyu; Wang, Yi; Niu, Ruiqing; Hu, Youjian

2016-05-11

In this study, a novel coupling model for landslide susceptibility mapping is presented. In practice, environmental factors may have different impacts at a local scale in study areas. To provide better predictions, a geographically weighted regression (GWR) technique is firstly used in our method to segment study areas into a series of prediction regions with appropriate sizes. Meanwhile, a support vector machine (SVM) classifier is exploited in each prediction region for landslide susceptibility mapping. To further improve the prediction performance, the particle swarm optimization (PSO) algorithm is used in the prediction regions to obtain optimal parameters for the SVM classifier. To evaluate the prediction performance of our model, several SVM-based prediction models are utilized for comparison on a study area of the Wanzhou district in the Three Gorges Reservoir. Experimental results, based on three objective quantitative measures and visual qualitative evaluation, indicate that our model can achieve better prediction accuracies and is more effective for landslide susceptibility mapping. For instance, our model can achieve an overall prediction accuracy of 91.10%, which is 7.8%-19.1% higher than the traditional SVM-based models. In addition, the obtained landslide susceptibility map by our model can demonstrate an intensive correlation between the classified very high-susceptibility zone and the previously investigated landslides.

SU-E-T-113: Dose Distribution Using Respiratory Signals and Machine Parameters During Treatment

DOE Office of Scientific and Technical Information (OSTI.GOV)

Imae, T; Haga, A; Saotome, N

Purpose: Volumetric modulated arc therapy (VMAT) is a rotational intensity-modulated radiotherapy (IMRT) technique capable of acquiring projection images during treatment. Treatment plans for lung tumors using stereotactic body radiotherapy (SBRT) are calculated with planning computed tomography (CT) images only exhale phase. Purpose of this study is to evaluate dose distribution by reconstructing from only the data such as respiratory signals and machine parameters acquired during treatment. Methods: Phantom and three patients with lung tumor underwent CT scans for treatment planning. They were treated by VMAT while acquiring projection images to derive their respiratory signals and machine parameters including positions ofmore » multi leaf collimators, dose rates and integrated monitor units. The respiratory signals were divided into 4 and 10 phases and machine parameters were correlated with the divided respiratory signals based on the gantry angle. Dose distributions of each respiratory phase were calculated from plans which were reconstructed from the respiratory signals and the machine parameters during treatment. The doses at isocenter, maximum point and the centroid of target were evaluated. Results and Discussion: Dose distributions during treatment were calculated using the machine parameters and the respiratory signals detected from projection images. Maximum dose difference between plan and in treatment distribution was −1.8±0.4% at centroid of target and dose differences of evaluated points between 4 and 10 phases were no significant. Conclusion: The present method successfully evaluated dose distribution using respiratory signals and machine parameters during treatment. This method is feasible to verify the actual dose for moving target.« less

Channel Efficiency with Security Enhancement for Remote Condition Monitoring of Multi Machine System Using Hybrid Huffman Coding

NASA Astrophysics Data System (ADS)

Datta, Jinia; Chowdhuri, Sumana; Bera, Jitendranath

2016-12-01

This paper presents a novel scheme of remote condition monitoring of multi machine system where a secured and coded data of induction machine with different parameters is communicated between a state-of-the-art dedicated hardware Units (DHU) installed at the machine terminal and a centralized PC based machine data management (MDM) software. The DHUs are built for acquisition of different parameters from the respective machines, and hence are placed at their nearby panels in order to acquire different parameters cost effectively during their running condition. The MDM software collects these data through a communication channel where all the DHUs are networked using RS485 protocol. Before transmitting, the parameter's related data is modified with the adoption of differential pulse coded modulation (DPCM) and Huffman coding technique. It is further encrypted with a private key where different keys are used for different DHUs. In this way a data security scheme is adopted during its passage through the communication channel in order to avoid any third party attack into the channel. The hybrid mode of DPCM and Huffman coding is chosen to reduce the data packet length. A MATLAB based simulation and its practical implementation using DHUs at three machine terminals (one healthy three phase, one healthy single phase and one faulty three phase machine) proves its efficacy and usefulness for condition based maintenance of multi machine system. The data at the central control room are decrypted and decoded using MDM software. In this work it is observed that Chanel efficiency with respect to different parameter measurements has been increased very much.

Exploration on Wire Discharge Machining Added Powder for Metal-Based Diamond Grinding Wheel on Wire EDM Dressing and Truing of Grinding Tungsten Carbide Material

NASA Astrophysics Data System (ADS)

Chow, H. M.; Yang, L. D.; Lin, Y. C.; Lin, C. L.

2017-12-01

In this paper, the effects of material removal rate and abrasive grain protrusion on the metal-based diamond grinding wheel were studied to find the optimal parameters for adding powder and wire discharge. In addition, this kind of electric discharge method to add powder on the metal-based diamond grinding wheel on line after dressing and truing will be applied on tungsten carbide to study the grinding material removal rate, grinding wheel wear, surface roughness, and surface micro-hardness.

A study on the applications of AI in finishing of additive manufacturing parts

NASA Astrophysics Data System (ADS)

Fathima Patham, K.

2017-06-01

Artificial intelligent and computer simulation are the technological powerful tools for solving complex problems in the manufacturing industries. Additive Manufacturing is one of the powerful manufacturing techniques that provide design flexibilities to the products. The products with complex shapes are directly manufactured without the need of any machining and tooling using Additive Manufacturing. However, the main drawback of the components produced using the Additive Manufacturing processes is the quality of the surfaces. This study aims to minimize the defects caused during Additive Manufacturing with the aid of Artificial Intelligence. The developed AI system has three layers, each layer is trying to eliminate or minimize the production errors. The first layer of the AI system optimizes the digitization of the 3D CAD model of the product and hence reduces the stair case errors. The second layer of the AI system optimizes the 3D printing machine parameters in order to eliminate the warping effect. The third layer of AI system helps to choose the surface finishing technique suitable for the printed component based on the Degree of Complexity of the product and the material. The efficiency of the developed AI system was examined on the functional parts such as gears.

SVM2Motif—Reconstructing Overlapping DNA Sequence Motifs by Mimicking an SVM Predictor

PubMed Central

Vidovic, Marina M. -C.; Görnitz, Nico; Müller, Klaus-Robert; Rätsch, Gunnar; Kloft, Marius

2015-01-01

Identifying discriminative motifs underlying the functionality and evolution of organisms is a major challenge in computational biology. Machine learning approaches such as support vector machines (SVMs) achieve state-of-the-art performances in genomic discrimination tasks, but—due to its black-box character—motifs underlying its decision function are largely unknown. As a remedy, positional oligomer importance matrices (POIMs) allow us to visualize the significance of position-specific subsequences. Although being a major step towards the explanation of trained SVM models, they suffer from the fact that their size grows exponentially in the length of the motif, which renders their manual inspection feasible only for comparably small motif sizes, typically k ≤ 5. In this work, we extend the work on positional oligomer importance matrices, by presenting a new machine-learning methodology, entitled motifPOIM, to extract the truly relevant motifs—regardless of their length and complexity—underlying the predictions of a trained SVM model. Our framework thereby considers the motifs as free parameters in a probabilistic model, a task which can be phrased as a non-convex optimization problem. The exponential dependence of the POIM size on the oligomer length poses a major numerical challenge, which we address by an efficient optimization framework that allows us to find possibly overlapping motifs consisting of up to hundreds of nucleotides. We demonstrate the efficacy of our approach on a synthetic data set as well as a real-world human splice site data set. PMID:26690911

Machine-Learning Approach for Design of Nanomagnetic-Based Antennas

NASA Astrophysics Data System (ADS)

Gianfagna, Carmine; Yu, Huan; Swaminathan, Madhavan; Pulugurtha, Raj; Tummala, Rao; Antonini, Giulio

2017-08-01

We propose a machine-learning approach for design of planar inverted-F antennas with a magneto-dielectric nanocomposite substrate. It is shown that machine-learning techniques can be efficiently used to characterize nanomagnetic-based antennas by accurately mapping the particle radius and volume fraction of the nanomagnetic material to antenna parameters such as gain, bandwidth, radiation efficiency, and resonant frequency. A modified mixing rule model is also presented. In addition, the inverse problem is addressed through machine learning as well, where given the antenna parameters, the corresponding design space of possible material parameters is identified.

Optimization of morphological parameters for mitigation pits on rear KDP surface: experiments and numerical modeling.

PubMed

Yang, Hao; Cheng, Jian; Chen, Mingjun; Wang, Jian; Liu, Zhichao; An, Chenhui; Zheng, Yi; Hu, Kehui; Liu, Qi

2017-07-24

In high power laser systems, precision micro-machining is an effective method to mitigate the laser-induced surface damage growth on potassium dihydrogen phosphate (KDP) crystal. Repaired surfaces with smooth spherical and Gaussian contours can alleviate the light field modulation caused by damage site. To obtain the optimal repairing structure parameters, finite element method (FEM) models for simulating the light intensification caused by the mitigation pits on rear KDP surface were established. The light intensity modulation of these repairing profiles was compared by changing the structure parameters. The results indicate the modulation is mainly caused by the mutual interference between the reflected and incident lights on the rear surface. Owing to the total reflection, the light intensity enhancement factors (LIEFs) of the spherical and Gaussian mitigation pits sharply increase when the width-depth ratios are near 5.28 and 3.88, respectively. To achieve the optimal mitigation effect, the width-depth ratios greater than 5.3 and 4.3 should be applied to the spherical and Gaussian repaired contours. Particularly, for the cases of width-depth ratios greater than 5.3, the spherical repaired contour is preferred to achieve lower light intensification. The laser damage test shows that when the width-depth ratios are larger than 5.3, the spherical repaired contour presents higher laser damage resistance than that of Gaussian repaired contour, which agrees well with the simulation results.

[Hyperspectral remote sensing image classification based on SVM optimized by clonal selection].

PubMed

Liu, Qing-Jie; Jing, Lin-Hai; Wang, Meng-Fei; Lin, Qi-Zhong

2013-03-01

Model selection for support vector machine (SVM) involving kernel and the margin parameter values selection is usually time-consuming, impacts training efficiency of SVM model and final classification accuracies of SVM hyperspectral remote sensing image classifier greatly. Firstly, based on combinatorial optimization theory and cross-validation method, artificial immune clonal selection algorithm is introduced to the optimal selection of SVM (CSSVM) kernel parameter a and margin parameter C to improve the training efficiency of SVM model. Then an experiment of classifying AVIRIS in India Pine site of USA was performed for testing the novel CSSVM, as well as a traditional SVM classifier with general Grid Searching cross-validation method (GSSVM) for comparison. And then, evaluation indexes including SVM model training time, classification overall accuracy (OA) and Kappa index of both CSSVM and GSSVM were all analyzed quantitatively. It is demonstrated that OA of CSSVM on test samples and whole image are 85.1% and 81.58, the differences from that of GSSVM are both within 0.08% respectively; And Kappa indexes reach 0.8213 and 0.7728, the differences from that of GSSVM are both within 0.001; While the ratio of model training time of CSSVM and GSSVM is between 1/6 and 1/10. Therefore, CSSVM is fast and accurate algorithm for hyperspectral image classification and is superior to GSSVM.

Support Vector Data Description Model to Map Specific Land Cover with Optimal Parameters Determined from a Window-Based Validation Set.

PubMed

Zhang, Jinshui; Yuan, Zhoumiqi; Shuai, Guanyuan; Pan, Yaozhong; Zhu, Xiufang

2017-04-26

This paper developed an approach, the window-based validation set for support vector data description (WVS-SVDD), to determine optimal parameters for support vector data description (SVDD) model to map specific land cover by integrating training and window-based validation sets. Compared to the conventional approach where the validation set included target and outlier pixels selected visually and randomly, the validation set derived from WVS-SVDD constructed a tightened hypersphere because of the compact constraint by the outlier pixels which were located neighboring to the target class in the spectral feature space. The overall accuracies for wheat and bare land achieved were as high as 89.25% and 83.65%, respectively. However, target class was underestimated because the validation set covers only a small fraction of the heterogeneous spectra of the target class. The different window sizes were then tested to acquire more wheat pixels for validation set. The results showed that classification accuracy increased with the increasing window size and the overall accuracies were higher than 88% at all window size scales. Moreover, WVS-SVDD showed much less sensitivity to the untrained classes than the multi-class support vector machine (SVM) method. Therefore, the developed method showed its merits using the optimal parameters, tradeoff coefficient ( C ) and kernel width ( s ), in mapping homogeneous specific land cover.

Design and Performance Improvement of AC Machines Sharing a Common Stator

NASA Astrophysics Data System (ADS)

Guo, Lusu

With the increasing demand on electric motors in various industrial applications, especially electric powered vehicles (electric cars, more electric aircrafts and future electric ships and submarines), both synchronous reluctance machines (SynRMs) and interior permanent magnet (IPM) machines are recognized as good candidates for high performance variable speed applications. Developing a single stator design which can be used for both SynRM and IPM motors is a good way to reduce manufacturing and maintenance cost. SynRM can be used as a low cost solution for many electric driving applications and IPM machines can be used in power density crucial circumstances or work as generators to meet the increasing demand for electrical power on board. In this research, SynRM and IPM machines are designed sharing a common stator structure. The prototype motors are designed with the aid of finite element analysis (FEA). Machine performances with different stator slot and rotor pole numbers are compared by FEA. An 18-slot, 4-pole structure is selected based on the comparison for this prototype design. Sometimes, torque pulsation is the major drawback of permanent magnet synchronous machines. There are several sources of torque pulsations, such as back-EMF distortion, inductance variation and cogging torque due to presence of permanent magnets. To reduce torque pulsations in permanent magnet machines, all the efforts can be classified into two categories: one is from the design stage, the structure of permanent magnet machines can be optimized with the aid of finite element analysis. The other category of reducing torque pulsation is after the permanent magnet machine has been manufactured or the machine structure cannot be changed because of other reasons. The currents fed into the permanent magnet machine can be controlled to follow a certain profile which will make the machine generate a smoother torque waveform. Torque pulsation reduction methods in both categories will be discussed in this dissertation. In the design stage, an optimization method based on orthogonal experimental design will be introduced. Besides, a universal current profiling technique is proposed to minimize the torque pulsation along with the stator copper losses in modular interior permanent magnet motors. Instead of sinusoidal current waveforms, this algorithm will calculate the proper currents which can minimize the torque pulsation. Finite element analysis and Matlab programing will be used to develop this optimal current profiling algorithm. Permanent magnet machines are becoming more attractive in some modern traction applications, such as traction motors and generators for an electrified vehicle. The operating speed or the load condition in these applications may be changing all the time. Compared to electric machines used to operate at a constant speed and constant load, better control performance is required. In this dissertation, a novel model reference adaptive control (MRAC) used on five-phase interior permanent magnet motor drives is presented. The primary controller is designed based on artificial neural network (ANN) to simulate the nonlinear characteristics of the system without knowledge of accurate motor model or parameters. The proposed motor drive decouples the torque and flux components of five-phase IPM motors by applying a multiple reference frame transformation. Therefore, the motor can be easily driven below the rated speed with the maximum torque per ampere (MTPA) operation or above the rated speed with the flux weakening operation. The ANN based primary controller consists of a radial basis function (RBF) network which is trained on-line to adapt system uncertainties. The complete IPM motor drive is simulated in Matlab/Simulink environment and implemented experimentally utilizing dSPACE DS1104 DSP board on a five-phase prototype IPM motor. The proposed model reference adaptive control method has been applied on the commons stator SynRM and IPM machine as well.

A survey of compiler optimization techniques

NASA Technical Reports Server (NTRS)

Schneck, P. B.

1972-01-01

Major optimization techniques of compilers are described and grouped into three categories: machine dependent, architecture dependent, and architecture independent. Machine-dependent optimizations tend to be local and are performed upon short spans of generated code by using particular properties of an instruction set to reduce the time or space required by a program. Architecture-dependent optimizations are global and are performed while generating code. These optimizations consider the structure of a computer, but not its detailed instruction set. Architecture independent optimizations are also global but are based on analysis of the program flow graph and the dependencies among statements of source program. A conceptual review of a universal optimizer that performs architecture-independent optimizations at source-code level is also presented.

Influence of tumor location on the intensity-modulated radiation therapy plan of helical tomotherapy.

PubMed

Xu, Yingjie; Yan, Hui; Hu, Zhihui; Ma, Pan; Men, Kuo; Huang, Peng; Ren, Wenting; Dai, Jianrong; Li, Yexiong

2017-01-01

Given the design of the Helical TomoTherapy device, the patient's central axis is routinely aligned with the machine's rotational axis to prevent the patient's body from colliding with the machine walls. However, for treatment of tumors located away from the patient's central axis, this position may not be optimal as the adequate radiation dose may not reach the affected site. Our study aimed to investigate the influence of tumor location on dose quality and delivery efficiency of tomotherapy plans. A phantom and 15 patients were selected for this study. Two plans, A and B, were implemented for each case. In plan A, the patient's central axis was aligned with the machine's rotational axis, whereas in plan B, the center of the planning target volume (PTV) was aligned with the machine's rotational axis. Both plans were optimized with the same planning parameters, and the dose quality of the plans was evaluated using dosimetrics. The delivery efficiency was determined from delivery time and monitor units (MUs). A paired t-test or nonparametric Wilcoxon signed-rank test was performed for statistical comparison. In the phantom study, the median delivery times were 358 and 336 seconds for plans A and B, respectively, and this difference was significant (p = 0.005). In the patient study, the median delivery times were 348 and 317 seconds for plans A and B, respectively, and this difference was also significant (p = 0.001). The dose qualities of both plans for each patient were nearly identical. No significant differences were found in the conformal index, heterogeneity index, and mean dose delivered to normal tissue between the plans. Both phantom and patient studies showed that for normal-sized patients, the delivery time reduced as the distance between the PTV and the patient's central axis increased when the PTV center was aligned with the machine axis. In conclusion, aligning the PTV center with the machine's rotational axis by shifting the patient during tomotherapy reduces the delivery time without compromising the dose quality of intensity-modulated radiation therapy. Copyright © 2017 American Association of Medical Dosimetrists. Published by Elsevier Inc. All rights reserved.

A Module Experimental Process System Development Unit (MEPSDU)

NASA Technical Reports Server (NTRS)

1981-01-01

The purpose of this program is to demonstrate the technical readiness of a cost effective process sequence that has the potential for the production of flat plate photovoltaic modules which met the price goal in 1986 of $.70 or less per watt peak. Program efforts included: preliminary design review, preliminary cell fabrication using the proposed process sequence, verification of sandblasting back cleanup, study of resist parameters, evaluation of pull strength of the proposed metallization, measurement of contact resistance of Electroless Ni contacts, optimization of process parameter, design of the MEPSDU module, identification and testing of insulator tapes, development of a lamination process sequence, identification, discussions, demonstrations and visits with candidate equipment vendors, evaluation of proposals for tabbing and stringing machine.

Modeling and simulation of five-axis virtual machine based on NX

NASA Astrophysics Data System (ADS)

Li, Xiaoda; Zhan, Xianghui

2018-04-01

Virtual technology in the machinery manufacturing industry has shown the role of growing. In this paper, the Siemens NX software is used to model the virtual CNC machine tool, and the parameters of the virtual machine are defined according to the actual parameters of the machine tool so that the virtual simulation can be carried out without loss of the accuracy of the simulation. How to use the machine builder of the CAM module to define the kinematic chain and machine components of the machine is described. The simulation of virtual machine can provide alarm information of tool collision and over cutting during the process to users, and can evaluate and forecast the rationality of the technological process.

Comparison of effects of overload on parameters and performance of samarium-cobalt and strontium-ferrite radially oriented permanent magnet brushless DC motors

DOE Office of Scientific and Technical Information (OSTI.GOV)

Demerdash, N.A.; Nehl, T.W.; Nyamusa, T.A.

1985-08-01

Effects of high momentary overloads on the samarium-cobalt and strontium-ferrite permanent magnets and the magnetic field in electronically commutated brushless dc machines, as well as their impact on the associated machine parameters were studied. The effect of overload on the machine parameters, and subsequently on the machine system performance was also investigated. This was accomplished through the combined use of finite element analysis of the magnetic field in such machines, perturbation of the magnetic energies to determine machine inductances, and dynamic simulation of the performance of brushless dc machines, when energized from voltage source inverters. These effects were investigated throughmore » application of the above methods to two equivalent 15 hp brushless dc motors, one of which was built with samarium-cobalt magnets, while the other was built with strontium- ferrite magnets. For momentary overloads as high as 4.5 p.u. magnet flux reductions of 29% and 42% of the no load flux were obtained in the samarium-cobalt and strontiumferrite machines, respectively. Corresponding reductions in the line to line armature inductances of 52% and 46% of the no load values were reported for the samarium-cobalt and strontium-ferrite cases, respectively. The overload affected the profiles and magnitudes of armature induced back emfs. Subsequently, the effects of overload on machine parameters were found to have significant impact on the performance of the machine systems, where findings indicate that the samarium-cobalt unit is more suited for higher overload duties than the strontium-ferrite machine.« less

DOE Office of Scientific and Technical Information (OSTI.GOV)

Hill, Mary Ann; Dombrowski, David E.; Clarke, Kester Diederik

U-10 wt. % Mo (U-10Mo) alloys are being developed as low enrichment monolithic fuel for the CONVERT program. Optimization of processing for the monolithic fuel is being pursued with the use of electrical discharge machining (EDM) under CONVERT HPRR WBS 1.2.4.5 Optimization of Coupon Preparation. The process is applicable to manufacturing experimental fuel plate specimens for the Mini-Plate-1 (MP-1) irradiation campaign. The benefits of EDM are reduced machining costs, ability to achieve higher tolerances, stress-free, burr-free surfaces eliminating the need for milling, and the ability to machine complex shapes. Kerf losses are much smaller with EDM (tenths of mm) comparedmore » to conventional machining (mm). Reliable repeatability is achievable with EDM due to its computer-generated machining programs.« less

Intelligent method for diagnosing structural faults of rotating machinery using ant colony optimization.

PubMed

Li, Ke; Chen, Peng

2011-01-01

Structural faults, such as unbalance, misalignment and looseness, etc., often occur in the shafts of rotating machinery. These faults may cause serious machine accidents and lead to great production losses. This paper proposes an intelligent method for diagnosing structural faults of rotating machinery using ant colony optimization (ACO) and relative ratio symptom parameters (RRSPs) in order to detect faults and distinguish fault types at an early stage. New symptom parameters called "relative ratio symptom parameters" are defined for reflecting the features of vibration signals measured in each state. Synthetic detection index (SDI) using statistical theory has also been defined to evaluate the applicability of the RRSPs. The SDI can be used to indicate the fitness of a RRSP for ACO. Lastly, this paper also compares the proposed method with the conventional neural networks (NN) method. Practical examples of fault diagnosis for a centrifugal fan are provided to verify the effectiveness of the proposed method. The verification results show that the structural faults often occurring in the centrifugal fan, such as unbalance, misalignment and looseness states are effectively identified by the proposed method, while these faults are difficult to detect using conventional neural networks.

Novel Approaches to Improve Iris Recognition System Performance Based on Local Quality Evaluation and Feature Fusion

PubMed Central

2014-01-01

For building a new iris template, this paper proposes a strategy to fuse different portions of iris based on machine learning method to evaluate local quality of iris. There are three novelties compared to previous work. Firstly, the normalized segmented iris is divided into multitracks and then each track is estimated individually to analyze the recognition accuracy rate (RAR). Secondly, six local quality evaluation parameters are adopted to analyze texture information of each track. Besides, particle swarm optimization (PSO) is employed to get the weights of these evaluation parameters and corresponding weighted coefficients of different tracks. Finally, all tracks' information is fused according to the weights of different tracks. The experimental results based on subsets of three public and one private iris image databases demonstrate three contributions of this paper. (1) Our experimental results prove that partial iris image cannot completely replace the entire iris image for iris recognition system in several ways. (2) The proposed quality evaluation algorithm is a self-adaptive algorithm, and it can automatically optimize the parameters according to iris image samples' own characteristics. (3) Our feature information fusion strategy can effectively improve the performance of iris recognition system. PMID:24693243

Novel approaches to improve iris recognition system performance based on local quality evaluation and feature fusion.

PubMed

Chen, Ying; Liu, Yuanning; Zhu, Xiaodong; Chen, Huiling; He, Fei; Pang, Yutong

2014-01-01

For building a new iris template, this paper proposes a strategy to fuse different portions of iris based on machine learning method to evaluate local quality of iris. There are three novelties compared to previous work. Firstly, the normalized segmented iris is divided into multitracks and then each track is estimated individually to analyze the recognition accuracy rate (RAR). Secondly, six local quality evaluation parameters are adopted to analyze texture information of each track. Besides, particle swarm optimization (PSO) is employed to get the weights of these evaluation parameters and corresponding weighted coefficients of different tracks. Finally, all tracks' information is fused according to the weights of different tracks. The experimental results based on subsets of three public and one private iris image databases demonstrate three contributions of this paper. (1) Our experimental results prove that partial iris image cannot completely replace the entire iris image for iris recognition system in several ways. (2) The proposed quality evaluation algorithm is a self-adaptive algorithm, and it can automatically optimize the parameters according to iris image samples' own characteristics. (3) Our feature information fusion strategy can effectively improve the performance of iris recognition system.

Machining of bone: Analysis of cutting force and surface roughness by turning process.

PubMed

Noordin, M Y; Jiawkok, N; Ndaruhadi, P Y M W; Kurniawan, D

2015-11-01

There are millions of orthopedic surgeries and dental implantation procedures performed every year globally. Most of them involve machining of bones and cartilage. However, theoretical and analytical study on bone machining is lagging behind its practice and implementation. This study views bone machining as a machining process with bovine bone as the workpiece material. Turning process which makes the basis of the actually used drilling process was experimented. The focus is on evaluating the effects of three machining parameters, that is, cutting speed, feed, and depth of cut, to machining responses, that is, cutting forces and surface roughness resulted by the turning process. Response surface methodology was used to quantify the relation between the machining parameters and the machining responses. The turning process was done at various cutting speeds (29-156 m/min), depths of cut (0.03 -0.37 mm), and feeds (0.023-0.11 mm/rev). Empirical models of the resulted cutting force and surface roughness as the functions of cutting speed, depth of cut, and feed were developed. Observation using the developed empirical models found that within the range of machining parameters evaluated, the most influential machining parameter to the cutting force is depth of cut, followed by feed and cutting speed. The lowest cutting force was obtained at the lowest cutting speed, lowest depth of cut, and highest feed setting. For surface roughness, feed is the most significant machining condition, followed by cutting speed, and with depth of cut showed no effect. The finest surface finish was obtained at the lowest cutting speed and feed setting. © IMechE 2015.

Cost Minimization for Joint Energy Management and Production Scheduling Using Particle Swarm Optimization

NASA Astrophysics Data System (ADS)

Shah, Rahul H.

Production costs account for the largest share of the overall cost of manufacturing facilities. With the U.S. industrial sector becoming more and more competitive, manufacturers are looking for more cost and resource efficient working practices. Operations management and production planning have shown their capability to dramatically reduce manufacturing costs and increase system robustness. When implementing operations related decision making and planning, two fields that have shown to be most effective are maintenance and energy. Unfortunately, the current research that integrates both is limited. Additionally, these studies fail to consider parameter domains and optimization on joint energy and maintenance driven production planning. Accordingly, production planning methodology that considers maintenance and energy is investigated. Two models are presented to achieve well-rounded operating strategy. The first is a joint energy and maintenance production scheduling model. The second is a cost per part model considering maintenance, energy, and production. The proposed methodology will involve a Time-of-Use electricity demand response program, buffer and holding capacity, station reliability, production rate, station rated power, and more. In practice, the scheduling problem can be used to determine a joint energy, maintenance, and production schedule. Meanwhile, the cost per part model can be used to: (1) test the sensitivity of the obtained optimal production schedule and its corresponding savings by varying key production system parameters; and (2) to determine optimal system parameter combinations when using the joint energy, maintenance, and production planning model. Additionally, a factor analysis on the system parameters is conducted and the corresponding performance of the production schedule under variable parameter conditions, is evaluated. Also, parameter optimization guidelines that incorporate maintenance and energy parameter decision making in the production planning framework are discussed. A modified Particle Swarm Optimization solution technique is adopted to solve the proposed scheduling problem. The algorithm is described in detail and compared to Genetic Algorithm. Case studies are presented to illustrate the benefits of using the proposed model and the effectiveness of the Particle Swarm Optimization approach. Numerical Experiments are implemented and analyzed to test the effectiveness of the proposed model. The proposed scheduling strategy can achieve savings of around 19 to 27 % in cost per part when compared to the baseline scheduling scenarios. By optimizing key production system parameters from the cost per part model, the baseline scenarios can obtain around 20 to 35 % in savings for the cost per part. These savings further increase by 42 to 55 % when system parameter optimization is integrated with the proposed scheduling problem. Using this method, the most influential parameters on the cost per part are the rated power from production, the production rate, and the initial machine reliabilities. The modified Particle Swarm Optimization algorithm adopted allows greater diversity and exploration compared to Genetic Algorithm for the proposed joint model which results in it being more computationally efficient in determining the optimal scheduling. While Genetic Algorithm could achieve a solution quality of 2,279.63 at an expense of 2,300 seconds in computational effort. In comparison, the proposed Particle Swarm Optimization algorithm achieved a solution quality of 2,167.26 in less than half the computation effort which is required by Genetic Algorithm.

Nanosecond multi-pulse laser milling for certain area removal of metal coating on plastics surface

NASA Astrophysics Data System (ADS)

Zhao, Kai; Jia, Zhenyuan; Ma, Jianwei; Liu, Wei; Wang, Ling

2014-12-01

Metal coating with functional pattern on engineering plastics surface plays an important role in industry applications; it can be obtained by adding or removing certain area of metal coating on engineering plastics surface. However, the manufacturing requirements are improved continuously and the plastic substrate presents three-dimensional (3D) structure-many of these parts cannot be fabricated by conventional processing methods, and a new manufacturing method is urgently needed. As the laser-processing technology has many advantages like high machining accuracy and constraints free substrate structure, the machining of the parts is studied through removing certain area of metal coating based on the nanosecond multi-pulse laser milling. To improve the edge quality of the functional pattern, generation mechanism and corresponding avoidance strategy of the processing defects are studied. Additionally, a prediction model for the laser ablation depth is proposed, which can effectively avoid the existence of residual metal coating and reduces the damage of substrate. With the optimal machining parameters, an equiangular spiral pattern on copper-clad polyimide (CCPI) is machined based on the laser milling at last. The experimental results indicate that the edge of the pattern is smooth and consistent, the substrate is flat and without damage. The achievements in this study could be applied in industrial production.

Myocardial perfusion characteristics during machine perfusion for heart transplantation.

PubMed

Peltz, Matthias; Cobert, Michael L; Rosenbaum, David H; West, LaShondra M; Jessen, Michael E

2008-08-01

Optimal parameters for machine perfusion preservation of hearts prior to transplantation have not been determined. We sought to define regional myocardial perfusion characteristics of a machine perfusion device over a range of conditions in a large animal model. Dog hearts were connected to a perfusion device (LifeCradle, Organ Transport Systems, Inc, Frisco, TX) and cold perfused at differing flow rates (1) at initial device startup and (2) over the storage interval. Myocardial perfusion was determined by entrapment of colored microspheres. Myocardial oxygen consumption (MVO(2)) was estimated from inflow and outflow oxygen differences. Intra-myocardial lactate was determined by (1)H magnetic resonance spectroscopy. MVO(2) and tissue perfusion increased up to flows of 15 mL/100 g/min, and the ratio of epicardial:endocardial perfusion remained near 1:1. Perfusion at lower flow rates and when low rates were applied during startup resulted in decreased capillary flow and greater non-nutrient flow. Increased tissue perfusion correlated with lower myocardial lactate accumulation but greater edema. Myocardial perfusion is influenced by flow rates during device startup and during the preservation interval. Relative declines in nutrient flow at low flow rates may reflect greater aortic insufficiency. These factors may need to be considered in clinical transplant protocols using machine perfusion.

Machine Learning methods for Quantitative Radiomic Biomarkers.

PubMed

Parmar, Chintan; Grossmann, Patrick; Bussink, Johan; Lambin, Philippe; Aerts, Hugo J W L

2015-08-17

Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pre-treatment computed tomography (CT) images of 464 lung cancer patients. To ensure the unbiased evaluation of different machine-learning methods, publicly available implementations along with reported parameter configurations were used. Furthermore, we used two independent radiomic cohorts for training (n = 310 patients) and validation (n = 154 patients). We identified that Wilcoxon test based feature selection method WLCX (stability = 0.84 ± 0.05, AUC = 0.65 ± 0.02) and a classification method random forest RF (RSD = 3.52%, AUC = 0.66 ± 0.03) had highest prognostic performance with high stability against data perturbation. Our variability analysis indicated that the choice of classification method is the most dominant source of performance variation (34.21% of total variance). Identification of optimal machine-learning methods for radiomic applications is a crucial step towards stable and clinically relevant radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor-phenotypic characteristics in clinical practice.

Differentially Private Empirical Risk Minimization

PubMed Central

Chaudhuri, Kamalika; Monteleoni, Claire; Sarwate, Anand D.

2011-01-01

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the ε-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving machine learning algorithm design. This method entails perturbing the objective function before optimizing over classifiers. If the loss and regularizer satisfy certain convexity and differentiability criteria, we prove theoretical results showing that our algorithms preserve privacy, and provide generalization bounds for linear and nonlinear kernels. We further present a privacy-preserving technique for tuning the parameters in general machine learning algorithms, thereby providing end-to-end privacy guarantees for the training process. We apply these results to produce privacy-preserving analogues of regularized logistic regression and support vector machines. We obtain encouraging results from evaluating their performance on real demographic and benchmark data sets. Our results show that both theoretically and empirically, objective perturbation is superior to the previous state-of-the-art, output perturbation, in managing the inherent tradeoff between privacy and learning performance. PMID:21892342

Fuzzy classification for strawberry diseases-infection using machine vision and soft-computing techniques

NASA Astrophysics Data System (ADS)

Altıparmak, Hamit; Al Shahadat, Mohamad; Kiani, Ehsan; Dimililer, Kamil

2018-04-01

Robotic agriculture requires smart and doable techniques to substitute the human intelligence with machine intelligence. Strawberry is one of the important Mediterranean product and its productivity enhancement requires modern and machine-based methods. Whereas a human identifies the disease infected leaves by his eye, the machine should also be capable of vision-based disease identification. The objective of this paper is to practically verify the applicability of a new computer-vision method for discrimination between the healthy and disease infected strawberry leaves which does not require neural network or time consuming trainings. The proposed method was tested under outdoor lighting condition using a regular DLSR camera without any particular lens. Since the type and infection degree of disease is approximated a human brain a fuzzy decision maker classifies the leaves over the images captured on-site having the same properties of human vision. Optimizing the fuzzy parameters for a typical strawberry production area at a summer mid-day in Cyprus produced 96% accuracy for segmented iron deficiency and 93% accuracy for segmented using a typical human instant classification approximation as the benchmark holding higher accuracy than a human eye identifier. The fuzzy-base classifier provides approximate result for decision making on the leaf status as if it is healthy or not.

Fabric wrinkle characterization and classification using modified wavelet coefficients and optimized support-vector-machine classifier

USDA-ARS?s Scientific Manuscript database

This paper presents a novel wrinkle evaluation method that uses modified wavelet coefficients and an optimized support-vector-machine (SVM) classification scheme to characterize and classify wrinkle appearance of fabric. Fabric images were decomposed with the wavelet transform (WT), and five parame...

[Determination of calcium and magnesium in tobacco by near-infrared spectroscopy and least squares-support vector machine].

PubMed

Tian, Kuang-da; Qiu, Kai-xian; Li, Zu-hong; Lü, Ya-qiong; Zhang, Qiu-ju; Xiong, Yan-mei; Min, Shun-geng

2014-12-01

The purpose of the present paper is to determine calcium and magnesium in tobacco using NIR combined with least squares-support vector machine (LS-SVM). Five hundred ground and dried tobacco samples from Qujing city, Yunnan province, China, were surveyed by a MATRIX-I spectrometer (Bruker Optics, Bremen, Germany). At the beginning of data processing, outliers of samples were eliminated for stability of the model. The rest 487 samples were divided into several calibration sets and validation sets according to a hybrid modeling strategy. Monte-Carlo cross validation was used to choose the best spectral preprocess method from multiplicative scatter correction (MSC), standard normal variate transformation (SNV), S-G smoothing, 1st derivative, etc., and their combinations. To optimize parameters of LS-SVM model, the multilayer grid search and 10-fold cross validation were applied. The final LS-SVM models with the optimizing parameters were trained by the calibration set and accessed by 287 validation samples picked by Kennard-Stone method. For the quantitative model of calcium in tobacco, Savitzky-Golay FIR smoothing with frame size 21 showed the best performance. The regularization parameter λ of LS-SVM was e16.11, while the bandwidth of the RBF kernel σ2 was e8.42. The determination coefficient for prediction (Rc(2)) was 0.9755 and the determination coefficient for prediction (Rp(2)) was 0.9422, better than the performance of PLS model (Rc(2)=0.9593, Rp(2)=0.9344). For the quantitative analysis of magnesium, SNV made the regression model more precise than other preprocess. The optimized λ was e15.25 and σ2 was e6.32. Rc(2) and Rp(2) were 0.9961 and 0.9301, respectively, better than PLS model (Rc(2)=0.9716, Rp(2)=0.8924). After modeling, the whole progress of NIR scan and data analysis for one sample was within tens of seconds. The overall results show that NIR spectroscopy combined with LS-SVM can be efficiently utilized for rapid and accurate analysis of calcium and magnesium in tobacco.

Evolutionary design optimization of traffic signals applied to Quito city.

PubMed

Armas, Rolando; Aguirre, Hernán; Daolio, Fabio; Tanaka, Kiyoshi

2017-01-01

This work applies evolutionary computation and machine learning methods to study the transportation system of Quito from a design optimization perspective. It couples an evolutionary algorithm with a microscopic transport simulator and uses the outcome of the optimization process to deepen our understanding of the problem and gain knowledge about the system. The work focuses on the optimization of a large number of traffic lights deployed on a wide area of the city and studies their impact on travel time, emissions and fuel consumption. An evolutionary algorithm with specialized mutation operators is proposed to search effectively in large decision spaces, evolving small populations for a short number of generations. The effects of the operators combined with a varying mutation schedule are studied, and an analysis of the parameters of the algorithm is also included. In addition, hierarchical clustering is performed on the best solutions found in several runs of the algorithm. An analysis of signal clusters and their geolocation, estimation of fuel consumption, spatial analysis of emissions, and an analysis of signal coordination provide an overall picture of the systemic effects of the optimization process.

Evolutionary design optimization of traffic signals applied to Quito city

PubMed Central

2017-01-01

This work applies evolutionary computation and machine learning methods to study the transportation system of Quito from a design optimization perspective. It couples an evolutionary algorithm with a microscopic transport simulator and uses the outcome of the optimization process to deepen our understanding of the problem and gain knowledge about the system. The work focuses on the optimization of a large number of traffic lights deployed on a wide area of the city and studies their impact on travel time, emissions and fuel consumption. An evolutionary algorithm with specialized mutation operators is proposed to search effectively in large decision spaces, evolving small populations for a short number of generations. The effects of the operators combined with a varying mutation schedule are studied, and an analysis of the parameters of the algorithm is also included. In addition, hierarchical clustering is performed on the best solutions found in several runs of the algorithm. An analysis of signal clusters and their geolocation, estimation of fuel consumption, spatial analysis of emissions, and an analysis of signal coordination provide an overall picture of the systemic effects of the optimization process. PMID:29236733

Articulated Arm Coordinate Measuring Machine Calibration by Laser Tracker Multilateration

PubMed Central

Majarena, Ana C.; Brau, Agustín; Velázquez, Jesús

2014-01-01

A new procedure for the calibration of an articulated arm coordinate measuring machine (AACMM) is presented in this paper. First, a self-calibration algorithm of four laser trackers (LTs) is developed. The spatial localization of a retroreflector target, placed in different positions within the workspace, is determined by means of a geometric multilateration system constructed from the four LTs. Next, a nonlinear optimization algorithm for the identification procedure of the AACMM is explained. An objective function based on Euclidean distances and standard deviations is developed. This function is obtained from the captured nominal data (given by the LTs used as a gauge instrument) and the data obtained by the AACMM and compares the measured and calculated coordinates of the target to obtain the identified model parameters that minimize this difference. Finally, results show that the procedure presented, using the measurements of the LTs as a gauge instrument, is very effective by improving the AACMM precision. PMID:24688418

Explosive hazard detection using MIMO forward-looking ground penetrating radar

NASA Astrophysics Data System (ADS)

Shaw, Darren; Ho, K. C.; Stone, Kevin; Keller, James M.; Popescu, Mihail; Anderson, Derek T.; Luke, Robert H.; Burns, Brian

2015-05-01

This paper proposes a machine learning algorithm for subsurface object detection on multiple-input-multiple-output (MIMO) forward-looking ground-penetrating radar (FLGPR). By detecting hazards using FLGPR, standoff distances of up to tens of meters can be acquired, but this is at the degradation of performance due to high false alarm rates. The proposed system utilizes an anomaly detection prescreener to identify potential object locations. Alarm locations have multiple one-dimensional (ML) spectral features, two-dimensional (2D) spectral features, and log-Gabor statistic features extracted. The ability of these features to reduce the number of false alarms and increase the probability of detection is evaluated for both co-polarizations present in the Akela MIMO array. Classification is performed by a Support Vector Machine (SVM) with lane-based cross-validation for training and testing. Class imbalance and optimized SVM kernel parameters are considered during classifier training.

Experimental control of a fluidic pinball using genetic programming

NASA Astrophysics Data System (ADS)

Raibaudo, Cedric; Zhong, Peng; Noack, Bernd R.; Martinuzzi, Robert J.

2017-11-01

The wake stabilization of a triangular cluster of three rotating cylinders was investigated in the present study. Experiments were performed at Reynolds number Re 6000, and compared with URANS-2D simulations at same flow conditions. 2D2C PIV measurements and constant temperature anemometry were used to characterize the flow without and with actuation. Open-loop actuation was first considered for the identification of particular control strategies. Machine learning control was also implemented for the experimental study. Linear genetic programming has been used for the optimization of open-loop parameters and closed-loop controllers. Considering a cost function J based on the fluctuations of the velocity measured by the hot-wire sensor, significant performances were achieved using the machine learning approach. The present work is supported by the senior author's (R. J. Martinuzzi) NSERC discovery Grant. C. Raibaudo acknowledges the financial support of the University of Calgary Eyes-High PDF program.

Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations

PubMed Central

Zhang, Yi; Ren, Jinchang; Jiang, Jianmin

2015-01-01

Maximum likelihood classifier (MLC) and support vector machines (SVM) are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions. PMID:26089862

Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations.

PubMed

Zhang, Yi; Ren, Jinchang; Jiang, Jianmin

2015-01-01

Maximum likelihood classifier (MLC) and support vector machines (SVM) are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions.

A support vector machine based control application to the experimental three-tank system.

PubMed

Iplikci, Serdar

2010-07-01

This paper presents a support vector machine (SVM) approach to generalized predictive control (GPC) of multiple-input multiple-output (MIMO) nonlinear systems. The possession of higher generalization potential and at the same time avoidance of getting stuck into the local minima have motivated us to employ SVM algorithms for modeling MIMO systems. Based on the SVM model, detailed and compact formulations for calculating predictions and gradient information, which are used in the computation of the optimal control action, are given in the paper. The proposed MIMO SVM-based GPC method has been verified on an experimental three-tank liquid level control system. Experimental results have shown that the proposed method can handle the control task successfully for different reference trajectories. Moreover, a detailed discussion on data gathering, model selection and effects of the control parameters have been given in this paper. 2010 ISA. Published by Elsevier Ltd. All rights reserved.

Machine-Thermal Coupling Stresses Analysis of the Fin-Type Structural Thermoelectric Generator

NASA Astrophysics Data System (ADS)

Zhang, Zheng; Yue, Hao; Chen, Dongbo; Qin, Delei; Chen, Zijian

2017-05-01

The design structure and heat-transfer mechanism of a thermoelectric generator (TEG) determine its body temperature state. Thermal stress and thermal deformation generated by the temperature variation directly affect the stress state of thermoelectric modules (TEMs). Therefore, the rated temperature and pressing force of TEMs are important parameters in TEG design. Here, the relationships between structural of a fin-type TEG (FTEG) and these parameters are studied by modeling and "machine-thermal" coupling simulation. An indirect calculation method is adopted in the coupling simulation. First, numerical heat transfer calculations of a three-dimensional FTEG model are conducted according to an orthogonal simulation table. The influences of structural parameters for heat transfer in the channel and outer fin temperature distribution are analyzed. The optimal structural parameters are obtained and used to simulate temperature field of the outer fins. Second, taking the thermal calculation results as the initial condition, the thermal-solid coupling calculation is adopted. The thermal stresses of outer fin, mechanical force of spring-angle pressing mechanism, and clamping force on a TEM are analyzed. The simulation results show that the heat transfer area of the inner fin and the physical parameters of the metal materials are the keys to determining the FTEG temperature field. The pressing mechanism's mechanical force can be reduced by reducing the outer fin angle. In addition, a corrugated cooling water pipe, which has cooling and spring functionality, is conducive to establishing an adaptable clamping force to avoid the TEMs being crushed by the thermal stresses in the body.

MLBCD: a machine learning tool for big clinical data.

PubMed

Luo, Gang

2015-01-01

Predictive modeling is fundamental for extracting value from large clinical data sets, or "big clinical data," advancing clinical research, and improving healthcare. Machine learning is a powerful approach to predictive modeling. Two factors make machine learning challenging for healthcare researchers. First, before training a machine learning model, the values of one or more model parameters called hyper-parameters must typically be specified. Due to their inexperience with machine learning, it is hard for healthcare researchers to choose an appropriate algorithm and hyper-parameter values. Second, many clinical data are stored in a special format. These data must be iteratively transformed into the relational table format before conducting predictive modeling. This transformation is time-consuming and requires computing expertise. This paper presents our vision for and design of MLBCD (Machine Learning for Big Clinical Data), a new software system aiming to address these challenges and facilitate building machine learning predictive models using big clinical data. The paper describes MLBCD's design in detail. By making machine learning accessible to healthcare researchers, MLBCD will open the use of big clinical data and increase the ability to foster biomedical discovery and improve care.

Catalytic aided electrical discharge machining of polycrystalline diamond - parameter analysis of finishing condition

NASA Astrophysics Data System (ADS)

Haikal Ahmad, M. A.; Zulafif Rahim, M.; Fauzi, M. F. Mohd; Abdullah, Aslam; Omar, Z.; Ding, Songlin; Ismail, A. E.; Rasidi Ibrahim, M.

2018-01-01

Polycrystalline diamond (PCD) is regarded as among the hardest material in the world. Electrical Discharge Machining (EDM) typically used to machine this material because of its non-contact process nature. This investigation was purposely done to compare the EDM performances of PCD when using normal electrode of copper (Cu) and newly proposed graphitization catalyst electrode of copper nickel (CuNi). Two level full factorial design of experiment with 4 center points technique was used to study the influence of main and interaction effects of the machining parameter namely; pulse-on, pulse-off, sparking current, and electrode materials (categorical factor). The paper shows interesting discovery in which the newly proposed electrode presented positive impact to the machining performance. With the same machining parameters of finishing, CuNi delivered more than 100% better in Ra and MRR than ordinary Cu electrode.

MRR and TWR evaluation on electrical discharge machining of Ti-6Al-4V using tungsten : copper composite electrode

NASA Astrophysics Data System (ADS)

Prasanna, J.; Rajamanickam, S.; Amith Kumar, O.; Karthick Raj, G.; Sathya Narayanan, P. V. V.

2017-05-01

In this paper Ti-6Al-4V used as workpiece material and it is keenly seen in variety of field including medical, chemical, marine, automotive, aerospace, aviation, electronic industries, nuclear reactor, consumer products etc., The conventional machining of Ti-6Al-4V is very difficult due to its distinctive properties. The Electrical Discharge Machining (EDM) is right choice of machining this material. The tungsten copper composite material is employed as tool material. The gap voltage, peak current, pulse on time and duty factor is considered as the machining parameter to analyze the machining characteristics Material Removal Rate (MRR) and Tool Wear Rate (TWR). The Taguchi method is provided to work for finding the significant parameter of EDM. It is found that for MRR significant parameters rated in the following order Gap Voltage, Pulse On-Time, Peak Current and Duty Factor. On the other hand for TWR significant parameters are listed in line of Gap Voltage, Duty Factor, Peak Current and Pulse On-Time.

Optical Coherence Tomography Machine Learning Classifiers for Glaucoma Detection: A Preliminary Study

PubMed Central

Burgansky-Eliash, Zvia; Wollstein, Gadi; Chu, Tianjiao; Ramsey, Joseph D.; Glymour, Clark; Noecker, Robert J.; Ishikawa, Hiroshi; Schuman, Joel S.

2007-01-01

Purpose Machine-learning classifiers are trained computerized systems with the ability to detect the relationship between multiple input parameters and a diagnosis. The present study investigated whether the use of machine-learning classifiers improves optical coherence tomography (OCT) glaucoma detection. Methods Forty-seven patients with glaucoma (47 eyes) and 42 healthy subjects (42 eyes) were included in this cross-sectional study. Of the glaucoma patients, 27 had early disease (visual field mean deviation [MD] ≥ −6 dB) and 20 had advanced glaucoma (MD < −6 dB). Machine-learning classifiers were trained to discriminate between glaucomatous and healthy eyes using parameters derived from OCT output. The classifiers were trained with all 38 parameters as well as with only 8 parameters that correlated best with the visual field MD. Five classifiers were tested: linear discriminant analysis, support vector machine, recursive partitioning and regression tree, generalized linear model, and generalized additive model. For the last two classifiers, a backward feature selection was used to find the minimal number of parameters that resulted in the best and most simple prediction. The cross-validated receiver operating characteristic (ROC) curve and accuracies were calculated. Results The largest area under the ROC curve (AROC) for glaucoma detection was achieved with the support vector machine using eight parameters (0.981). The sensitivity at 80% and 95% specificity was 97.9% and 92.5%, respectively. This classifier also performed best when judged by cross-validated accuracy (0.966). The best classification between early glaucoma and advanced glaucoma was obtained with the generalized additive model using only three parameters (AROC = 0.854). Conclusions Automated machine classifiers of OCT data might be useful for enhancing the utility of this technology for detecting glaucomatous abnormality. PMID:16249492

On approaches to analyze the sensitivity of simulated hydrologic fluxes to model parameters in the community land model

DOE PAGES

Bao, Jie; Hou, Zhangshuan; Huang, Maoyi; ...

2015-12-04

Here, effective sensitivity analysis approaches are needed to identify important parameters or factors and their uncertainties in complex Earth system models composed of multi-phase multi-component phenomena and multiple biogeophysical-biogeochemical processes. In this study, the impacts of 10 hydrologic parameters in the Community Land Model on simulations of runoff and latent heat flux are evaluated using data from a watershed. Different metrics, including residual statistics, the Nash-Sutcliffe coefficient, and log mean square error, are used as alternative measures of the deviations between the simulated and field observed values. Four sensitivity analysis (SA) approaches, including analysis of variance based on the generalizedmore » linear model, generalized cross validation based on the multivariate adaptive regression splines model, standardized regression coefficients based on a linear regression model, and analysis of variance based on support vector machine, are investigated. Results suggest that these approaches show consistent measurement of the impacts of major hydrologic parameters on response variables, but with differences in the relative contributions, particularly for the secondary parameters. The convergence behaviors of the SA with respect to the number of sampling points are also examined with different combinations of input parameter sets and output response variables and their alternative metrics. This study helps identify the optimal SA approach, provides guidance for the calibration of the Community Land Model parameters to improve the model simulations of land surface fluxes, and approximates the magnitudes to be adjusted in the parameter values during parametric model optimization.« less

a Fully Automated Pipeline for Classification Tasks with AN Application to Remote Sensing

NASA Astrophysics Data System (ADS)

Suzuki, K.; Claesen, M.; Takeda, H.; De Moor, B.

2016-06-01

Nowadays deep learning has been intensively in spotlight owing to its great victories at major competitions, which undeservedly pushed `shallow' machine learning methods, relatively naive/handy algorithms commonly used by industrial engineers, to the background in spite of their facilities such as small requisite amount of time/dataset for training. We, with a practical point of view, utilized shallow learning algorithms to construct a learning pipeline such that operators can utilize machine learning without any special knowledge, expensive computation environment, and a large amount of labelled data. The proposed pipeline automates a whole classification process, namely feature-selection, weighting features and the selection of the most suitable classifier with optimized hyperparameters. The configuration facilitates particle swarm optimization, one of well-known metaheuristic algorithms for the sake of generally fast and fine optimization, which enables us not only to optimize (hyper)parameters but also to determine appropriate features/classifier to the problem, which has conventionally been a priori based on domain knowledge and remained untouched or dealt with naïve algorithms such as grid search. Through experiments with the MNIST and CIFAR-10 datasets, common datasets in computer vision field for character recognition and object recognition problems respectively, our automated learning approach provides high performance considering its simple setting (i.e. non-specialized setting depending on dataset), small amount of training data, and practical learning time. Moreover, compared to deep learning the performance stays robust without almost any modification even with a remote sensing object recognition problem, which in turn indicates that there is a high possibility that our approach contributes to general classification problems.

EV drivetrain inverter with V/HZ optimization

DOEpatents

Gritter, David J.; O'Neil, Walter K.

1986-01-01

An inverter (34) which provides power to an A.C. machine (28) is controlled by a circuit (36) employing PWM control strategy whereby A.C. power is supplied to the machine at a preselectable frequency and preselectable voltage. This is accomplished by the technique of waveform notching in which the shapes of the notches are varied to determine the average energy content of the overall waveform. Through this arrangement, the operational efficiency of the A.C. machine is optimized. The control circuit includes a micro-computer which calculates optimized machine control data signals from various parametric inputs and during steady state load conditions, seeks a best V/HZ ratio to minimize battery current drawn (system losses) from a D.C. power source (32). In the preferred embodiment, the present invention is incorporated within an electric vehicle (10) employing a 144 VDC battery pack and a three-phase induction motor (18).

Influence of Feedstock Materials and Spray Parameters on Thermal Conductivity of Wire-Arc-Sprayed Coatings

NASA Astrophysics Data System (ADS)

Yao, H. H.; Zhou, Z.; Wang, G. H.; He, D. Y.; Bobzin, K.; Zhao, L.; Öte, M.; Königstein, T.

2017-03-01

To manufacture a protective coating with high thermal conductivity on drying cylinders in paper production machines, a FeCrB-cored wire was developed, and the spraying parameters for wire-arc spraying were optimized in this study. The conventional engineering materials FeCrAl and FeCrMo coatings were produced as the reference coatings under the same experimental condition. It has been shown that the oxide content in coating influences the thermal conductivity of coating significantly. The FeCrB coating exhibits a relative higher thermal conductivity due to the lower oxide content in comparison with conventional FeCrAl and FeCrMo coatings. Moreover, the oxidation of in-flight particles can be reduced by decreasing the standoff distance contributing to the increase in the thermal conductivity of coating. Total energy consumption of a papermaking machine can be significantly reduced if the coatings applied to dryer section exhibit high thermal conductivity. Therefore, the FeCrB coating developed in this study is a highly promising coating system for drying cylinders regarding the improved thermal conductivity and low operation costs in paper production industry.

Experimental study of electrical discharge drilling of stainless steel UNS S30400

NASA Astrophysics Data System (ADS)

Hanash, E. A. H.; Ali, M. Y.

2018-01-01

In this study, overcut and taper angle were investigated in machining of stainless steel UNS S30400 against three different electrical discharge machining parameters which are electric current (Ip), pulse on-time (Ton) and pulse off-time (Toff). The electrode used was of 1 mm diameter with aspect ratio of 10. Dimensional accuracy was measured by evaluating overcut and taper angle. Those two measurements were performed using optical microscope model (Olympus BX41M, Japan). The experimentation planning, evaluation, analysis and optimization have been carried out using DOE software version 10.0.3 RSM based method with total number of twenty experiments. The research reveals that, discharge current was found to have the most significant effect on overcut and taper angle followed by pulse on-time and pulse off-time. As the discharge current and pulse on-time increase, overcut and taper angle are increased. However, when pulse off-time increases, overcut and taper angle decrease. The outcome result of this study will be very useful in the manufacturing industry to select the appropriate parameters for the selected work material. The model has shown a great accuracy with percentage error of less than 5%.

Design and Mechanical Evaluation of a Capacitive Sensor-Based Indexed Platform for Verification of Portable Coordinate Measuring Instruments

PubMed Central

Avila, Agustín Brau; Mazo, Jorge Santolaria; Martín, Juan José Aguilar

2014-01-01

During the last years, the use of Portable Coordinate Measuring Machines (PCMMs) in industry has increased considerably, mostly due to their flexibility for accomplishing in-line measuring tasks as well as their reduced costs and operational advantages as compared to traditional coordinate measuring machines (CMMs). However, their operation has a significant drawback derived from the techniques applied in the verification and optimization procedures of their kinematic parameters. These techniques are based on the capture of data with the measuring instrument from a calibrated gauge object, fixed successively in various positions so that most of the instrument measuring volume is covered, which results in time-consuming, tedious and expensive verification procedures. In this work the mechanical design of an indexed metrology platform (IMP) is presented. The aim of the IMP is to increase the final accuracy and to radically simplify the calibration, identification and verification of geometrical parameter procedures of PCMMs. The IMP allows us to fix the calibrated gauge object and move the measuring instrument in such a way that it is possible to cover most of the instrument working volume, reducing the time and operator fatigue to carry out these types of procedures. PMID:24451458

Design and mechanical evaluation of a capacitive sensor-based indexed platform for verification of portable coordinate measuring instruments.

PubMed

Avila, Agustín Brau; Mazo, Jorge Santolaria; Martín, Juan José Aguilar

2014-01-02

During the last years, the use of Portable Coordinate Measuring Machines (PCMMs) in industry has increased considerably, mostly due to their flexibility for accomplishing in-line measuring tasks as well as their reduced costs and operational advantages as compared to traditional coordinate measuring machines (CMMs). However, their operation has a significant drawback derived from the techniques applied in the verification and optimization procedures of their kinematic parameters. These techniques are based on the capture of data with the measuring instrument from a calibrated gauge object, fixed successively in various positions so that most of the instrument measuring volume is covered, which results in time-consuming, tedious and expensive verification procedures. In this work the mechanical design of an indexed metrology platform (IMP) is presented. The aim of the IMP is to increase the final accuracy and to radically simplify the calibration, identification and verification of geometrical parameter procedures of PCMMs. The IMP allows us to fix the calibrated gauge object and move the measuring instrument in such a way that it is possible to cover most of the instrument working volume, reducing the time and operator fatigue to carry out these types of procedures.

Object-based classification of earthquake damage from high-resolution optical imagery using machine learning

NASA Astrophysics Data System (ADS)

Bialas, James; Oommen, Thomas; Rebbapragada, Umaa; Levin, Eugene

2016-07-01

Object-based approaches in the segmentation and classification of remotely sensed images yield more promising results compared to pixel-based approaches. However, the development of an object-based approach presents challenges in terms of algorithm selection and parameter tuning. Subjective methods are often used, but yield less than optimal results. Objective methods are warranted, especially for rapid deployment in time-sensitive applications, such as earthquake damage assessment. Herein, we used a systematic approach in evaluating object-based image segmentation and machine learning algorithms for the classification of earthquake damage in remotely sensed imagery. We tested a variety of algorithms and parameters on post-event aerial imagery for the 2011 earthquake in Christchurch, New Zealand. Results were compared against manually selected test cases representing different classes. In doing so, we can evaluate the effectiveness of the segmentation and classification of different classes and compare different levels of multistep image segmentations. Our classifier is compared against recent pixel-based and object-based classification studies for postevent imagery of earthquake damage. Our results show an improvement against both pixel-based and object-based methods for classifying earthquake damage in high resolution, post-event imagery.

Next Generation Munitions Handler: Human-Machine Interface and Preliminary Performance Evaluation

DOE Office of Scientific and Technical Information (OSTI.GOV)

Draper, J.V.; Jansen, J.F.; Pin, F.G.

1999-04-25

The Next Generation Munitions Handler/Advanced Technology Demonstrator (NGMI-VATTD) is a technology demonstrator for the application of an advanced robotic device for re-arming U.S. Air Force (USAF) and U.S. Navy (USN) tactical fighters. It comprises two key hardware components: a heavy-lift dexterous manipulator (HDM) and a nonholonomic mobility platform. The NGMWATTD is capable of lifting weapons up to 4400 kg (2000 lb) and placing them on any weapons rack on existing fighters (including the F-22 Raptor). This report describes the NGMH mission with particular reference to human-machine interfaces. It also describes preliminary testing to garner feedback about the heavy-lift manipulator armmore » from experienced fighter load crewmen. The purpose of the testing was to provide preliminary information about control system parameters and to gather feed- back from users about manipulator arm functionality. To that end, the Air Force load crewmen interacted with the NGMWATTD in an informal testing session and provided feedback about the performance of the system. Certain con- trol system parameters were changed during the course of the testing and feedback from the participants was used to make a rough estimate of "good" initial operating parameters. Later, formal testing will concentrate within this range to identify optimal operating parameters. User reactions to the HDM were generally positive, All of the USAF personnel were favorably impressed with the capabilities of the system. Fine-tuning operating parameters created a system even more favorably regarded by the load crews. Further adjustment to control system parameters will result in a system that is operationally efficient, easy to use, and well accepted by users.« less

An evolutionary sensor approach for self-organizing production chains

NASA Astrophysics Data System (ADS)

Mocan, M.; Gillich, E. V.; Mituletu, I. C.; Korka, Z. I.

2018-01-01

Industry 4.0 is the actual great step in industrial progress. Convergence of industrial equipment with the power of advanced computing and analysis, low-cost sensing, and new connecting technologies are presumed to bring unexpected advancements in automation, flexibility, and efficiency. In this context, sensors ensure information regarding three essential areas: the number of processed elements, the quality of production and the condition of tools and equipment. To obtain this valuable information, the data resulted from a sensor has to be firstly processed and afterward used by the different stakeholders. If machines are linked together, this information can be employed to organize the production chain with few or without human intervention. We describe here the implementation of a sensor in a milling machine that is part of a simple production chain, capable of providing information regarding the number of manufactured pieces. It is used by the other machines in the production chain, in order to define the type and number of pieces to be manufactured by them and/or to set optimal parameters for their working regime. Secondly, the information achieved by monitoring the machine and manufactured piece dynamic behavior is used to evaluate the product quality. This information is used to warn about the need of maintenance, being transmitted to the specialized department. It is also transmitted to the central unit, in order to reorganize the production by involving other machines or by reconsidering the manufacturing regime of the existing machines. A special attention is drawn on analyzing and classifying the signals acquired via optical sensor from simulated processes.

Three-dimensionally printed biological machines powered by skeletal muscle.

PubMed

Cvetkovic, Caroline; Raman, Ritu; Chan, Vincent; Williams, Brian J; Tolish, Madeline; Bajaj, Piyush; Sakar, Mahmut Selman; Asada, H Harry; Saif, M Taher A; Bashir, Rashid

2014-07-15

Combining biological components, such as cells and tissues, with soft robotics can enable the fabrication of biological machines with the ability to sense, process signals, and produce force. An intuitive demonstration of a biological machine is one that can produce motion in response to controllable external signaling. Whereas cardiac cell-driven biological actuators have been demonstrated, the requirements of these machines to respond to stimuli and exhibit controlled movement merit the use of skeletal muscle, the primary generator of actuation in animals, as a contractile power source. Here, we report the development of 3D printed hydrogel "bio-bots" with an asymmetric physical design and powered by the actuation of an engineered mammalian skeletal muscle strip to result in net locomotion of the bio-bot. Geometric design and material properties of the hydrogel bio-bots were optimized using stereolithographic 3D printing, and the effect of collagen I and fibrin extracellular matrix proteins and insulin-like growth factor 1 on the force production of engineered skeletal muscle was characterized. Electrical stimulation triggered contraction of cells in the muscle strip and net locomotion of the bio-bot with a maximum velocity of ∼ 156 μm s(-1), which is over 1.5 body lengths per min. Modeling and simulation were used to understand both the effect of different design parameters on the bio-bot and the mechanism of motion. This demonstration advances the goal of realizing forward-engineered integrated cellular machines and systems, which can have a myriad array of applications in drug screening, programmable tissue engineering, drug delivery, and biomimetic machine design.

INTEGRATING DATA ANALYTICS AND SIMULATION METHODS TO SUPPORT MANUFACTURING DECISION MAKING

PubMed Central

Kibira, Deogratias; Hatim, Qais; Kumara, Soundar; Shao, Guodong

2017-01-01

Modern manufacturing systems are installed with smart devices such as sensors that monitor system performance and collect data to manage uncertainties in their operations. However, multiple parameters and variables affect system performance, making it impossible for a human to make informed decisions without systematic methodologies and tools. Further, the large volume and variety of streaming data collected is beyond simulation analysis alone. Simulation models are run with well-prepared data. Novel approaches, combining different methods, are needed to use this data for making guided decisions. This paper proposes a methodology whereby parameters that most affect system performance are extracted from the data using data analytics methods. These parameters are used to develop scenarios for simulation inputs; system optimizations are performed on simulation data outputs. A case study of a machine shop demonstrates the proposed methodology. This paper also reviews candidate standards for data collection, simulation, and systems interfaces. PMID:28690363

Camera calibration based on the back projection process

NASA Astrophysics Data System (ADS)

Gu, Feifei; Zhao, Hong; Ma, Yueyang; Bu, Penghui

2015-12-01

Camera calibration plays a crucial role in 3D measurement tasks of machine vision. In typical calibration processes, camera parameters are iteratively optimized in the forward imaging process (FIP). However, the results can only guarantee the minimum of 2D projection errors on the image plane, but not the minimum of 3D reconstruction errors. In this paper, we propose a universal method for camera calibration, which uses the back projection process (BPP). In our method, a forward projection model is used to obtain initial intrinsic and extrinsic parameters with a popular planar checkerboard pattern. Then, the extracted image points are projected back into 3D space and compared with the ideal point coordinates. Finally, the estimation of the camera parameters is refined by a non-linear function minimization process. The proposed method can obtain a more accurate calibration result, which is more physically useful. Simulation and practical data are given to demonstrate the accuracy of the proposed method.

Deep learning for neuroimaging: a validation study.

PubMed

Plis, Sergey M; Hjelm, Devon R; Salakhutdinov, Ruslan; Allen, Elena A; Bockholt, Henry J; Long, Jeffrey D; Johnson, Hans J; Paulsen, Jane S; Turner, Jessica A; Calhoun, Vince D

2014-01-01

Deep learning methods have recently made notable advances in the tasks of classification and representation learning. These tasks are important for brain imaging and neuroscience discovery, making the methods attractive for porting to a neuroimager's toolbox. Success of these methods is, in part, explained by the flexibility of deep learning models. However, this flexibility makes the process of porting to new areas a difficult parameter optimization problem. In this work we demonstrate our results (and feasible parameter ranges) in application of deep learning methods to structural and functional brain imaging data. These methods include deep belief networks and their building block the restricted Boltzmann machine. We also describe a novel constraint-based approach to visualizing high dimensional data. We use it to analyze the effect of parameter choices on data transformations. Our results show that deep learning methods are able to learn physiologically important representations and detect latent relations in neuroimaging data.

Experimental investigations on the effect of process parameters with the use of minimum quantity solid lubrication in turning

NASA Astrophysics Data System (ADS)

Makhesana, Mayur A.; Patel, K. M.; Mawandiya, B. K.

2018-04-01

Turning process is a very basic process in any field of mechanical application. During turning process, most of the energy is converted into heat because of the friction between work piece and tool. Heat generation can affect the surface quality of the work piece and tool life. To reduce the heat generation, Conventional Lubrication process is used in most of the industry. Minimum quantity lubrication has been an effective alternative to improve the performance of machining process. In this present work, effort has been made to study the effect of various process parameters on the surface roughness and power consumption during turning of EN8 steel material. Result revealed the effect of depth of cut and feed on the obtained surface roughness value. Further the effect of solid lubricant has been also studied and optimization of process parameters is also done for the turning process.

Application of Taguchi method to optimization of surface roughness during precise turning of NiTi shape memory alloy

NASA Astrophysics Data System (ADS)

Kowalczyk, M.

2017-08-01

This paper describes the research results of surface quality research after the NiTi shape memory alloy (Nitinol) precise turning by the tools with edges made of polycrystalline diamonds (PCD). Nitinol, a nearly equiatomic nickel-titanium shape memory alloy, has wide applications in the arms industry, military, medicine and aerospace industry, and industrial robots. Due to their specific properties NiTi alloys are known to be difficult-to-machine materials particularly by using conventional techniques. The research trials were conducted for three independent parameters (vc, f, ap) affecting the surface roughness were analyzed. The choice of parameter configurations were performed by factorial design methods using orthogonal plan type L9, with three control factors, changing on three levels, developed by G. Taguchi. S/N ratio and ANOVA analyses were performed to identify the best of cutting parameters influencing surface roughness.

Optimizing cutting conditions on sustainable machining of aluminum alloy to minimize power consumption

NASA Astrophysics Data System (ADS)

Nur, Rusdi; Suyuti, Muhammad Arsyad; Susanto, Tri Agus

2017-06-01

Aluminum is widely utilized in the industrial sector. There are several advantages of aluminum, i.e. good flexibility and formability, high corrosion resistance and electrical conductivity, and high heat. Despite of these characteristics, however, pure aluminum is rarely used because of its lacks of strength. Thus, most of the aluminum used in the industrial sectors was in the form of alloy form. Sustainable machining can be considered to link with the transformation of input materials and energy/power demand into finished goods. Machining processes are responsible for environmental effects accepting to their power consumption. The cutting conditions have been optimized to minimize the cutting power, which is the power consumed for cutting. This paper presents an experimental study of sustainable machining of Al-11%Si base alloy that was operated without any cooling system to assess the capacity in reducing power consumption. The cutting force was measured and the cutting power was calculated. Both of cutting force and cutting power were analyzed and modeled by using the central composite design (CCD). The result of this study indicated that the cutting speed has an effect on machining performance and that optimum cutting conditions have to be determined, while sustainable machining can be followed in terms of minimizing power consumption and cutting force. The model developed from this study can be used for evaluation process and optimization to determine optimal cutting conditions for the performance of the whole process.

Deep neural nets as a method for quantitative structure-activity relationships.

PubMed

Ma, Junshui; Sheridan, Robert P; Liaw, Andy; Dahl, George E; Svetnik, Vladimir

2015-02-23

Neural networks were widely used for quantitative structure-activity relationships (QSAR) in the 1990s. Because of various practical issues (e.g., slow on large problems, difficult to train, prone to overfitting, etc.), they were superseded by more robust methods like support vector machine (SVM) and random forest (RF), which arose in the early 2000s. The last 10 years has witnessed a revival of neural networks in the machine learning community thanks to new methods for preventing overfitting, more efficient training algorithms, and advancements in computer hardware. In particular, deep neural nets (DNNs), i.e. neural nets with more than one hidden layer, have found great successes in many applications, such as computer vision and natural language processing. Here we show that DNNs can routinely make better prospective predictions than RF on a set of large diverse QSAR data sets that are taken from Merck's drug discovery effort. The number of adjustable parameters needed for DNNs is fairly large, but our results show that it is not necessary to optimize them for individual data sets, and a single set of recommended parameters can achieve better performance than RF for most of the data sets we studied. The usefulness of the parameters is demonstrated on additional data sets not used in the calibration. Although training DNNs is still computationally intensive, using graphical processing units (GPUs) can make this issue manageable.

Parameter optimization and stretch enhancement of AISI 316 sheet using rapid prototyping technique

NASA Astrophysics Data System (ADS)

Moayedfar, M.; Rani, A. M.; Hanaei, H.; Ahmad, A.; Tale, A.

2017-10-01

Incremental sheet forming is a flexible manufacturing process which uses the indenter point-to-point force to shape the sheet metal workpiece into manufactured parts in batch production series. However, the problem sometimes arising from this process is the low plastic point in the stress-strain diagram of the material which leads the low stretching amount before ultra-tensile strain point. Hence, a set of experiments is designed to find the optimum forming parameters in this process for optimum sheet thickness distribution while both sides of the sheet are considered for the surface quality improvement. A five-axis high-speed CNC milling machine is employed to deliver the proper motion based on the programming system while the clamping system for holding the sheet metal was a blank mould. Finally, an electron microscope and roughness machine are utilized to evaluate the surface structure of final parts, illustrate any defect may cause during the forming process and examine the roughness of the final part surface accordingly. The best interaction between parameters is obtained with the optimum values which lead the maximum sheet thickness distribution of 4.211e-01 logarithmic elongation when the depth was 24mm with respect to the design. This study demonstrates that this rapid forming method offers an alternative solution for surface quality improvement of 65% avoiding the low probability of cracks and low probability of crystal structure changes.

Apparatus and method for fluid analysis

DOEpatents

Wilson, Bary W.; Peters, Timothy J.; Shepard, Chester L.; Reeves, James H.

2004-11-02

The present invention is an apparatus and method for analyzing a fluid used in a machine or in an industrial process line. The apparatus has at least one meter placed proximate the machine or process line and in contact with the machine or process fluid for measuring at least one parameter related to the fluid. The at least one parameter is a standard laboratory analysis parameter. The at least one meter includes but is not limited to viscometer, element meter, optical meter, particulate meter, and combinations thereof.

Discrete particle swarm optimization to solve multi-objective limited-wait hybrid flow shop scheduling problem

NASA Astrophysics Data System (ADS)

Santosa, B.; Siswanto, N.; Fiqihesa

2018-04-01

This paper proposes a discrete Particle Swam Optimization (PSO) to solve limited-wait hybrid flowshop scheduing problem with multi objectives. Flow shop schedulimg represents the condition when several machines are arranged in series and each job must be processed at each machine with same sequence. The objective functions are minimizing completion time (makespan), total tardiness time, and total machine idle time. Flow shop scheduling model always grows to cope with the real production system accurately. Since flow shop scheduling is a NP-Hard problem then the most suitable method to solve is metaheuristics. One of metaheuristics algorithm is Particle Swarm Optimization (PSO), an algorithm which is based on the behavior of a swarm. Originally, PSO was intended to solve continuous optimization problems. Since flow shop scheduling is a discrete optimization problem, then, we need to modify PSO to fit the problem. The modification is done by using probability transition matrix mechanism. While to handle multi objectives problem, we use Pareto Optimal (MPSO). The results of MPSO is better than the PSO because the MPSO solution set produced higher probability to find the optimal solution. Besides the MPSO solution set is closer to the optimal solution

A Bayesian least squares support vector machines based framework for fault diagnosis and failure prognosis

NASA Astrophysics Data System (ADS)

Khawaja, Taimoor Saleem

A high-belief low-overhead Prognostics and Health Management (PHM) system is desired for online real-time monitoring of complex non-linear systems operating in a complex (possibly non-Gaussian) noise environment. This thesis presents a Bayesian Least Squares Support Vector Machine (LS-SVM) based framework for fault diagnosis and failure prognosis in nonlinear non-Gaussian systems. The methodology assumes the availability of real-time process measurements, definition of a set of fault indicators and the existence of empirical knowledge (or historical data) to characterize both nominal and abnormal operating conditions. An efficient yet powerful Least Squares Support Vector Machine (LS-SVM) algorithm, set within a Bayesian Inference framework, not only allows for the development of real-time algorithms for diagnosis and prognosis but also provides a solid theoretical framework to address key concepts related to classification for diagnosis and regression modeling for prognosis. SVM machines are founded on the principle of Structural Risk Minimization (SRM) which tends to find a good trade-off between low empirical risk and small capacity. The key features in SVM are the use of non-linear kernels, the absence of local minima, the sparseness of the solution and the capacity control obtained by optimizing the margin. The Bayesian Inference framework linked with LS-SVMs allows a probabilistic interpretation of the results for diagnosis and prognosis. Additional levels of inference provide the much coveted features of adaptability and tunability of the modeling parameters. The two main modules considered in this research are fault diagnosis and failure prognosis. With the goal of designing an efficient and reliable fault diagnosis scheme, a novel Anomaly Detector is suggested based on the LS-SVM machines. The proposed scheme uses only baseline data to construct a 1-class LS-SVM machine which, when presented with online data is able to distinguish between normal behavior and any abnormal or novel data during real-time operation. The results of the scheme are interpreted as a posterior probability of health (1 - probability of fault). As shown through two case studies in Chapter 3, the scheme is well suited for diagnosing imminent faults in dynamical non-linear systems. Finally, the failure prognosis scheme is based on an incremental weighted Bayesian LS-SVR machine. It is particularly suited for online deployment given the incremental nature of the algorithm and the quick optimization problem solved in the LS-SVR algorithm. By way of kernelization and a Gaussian Mixture Modeling (GMM) scheme, the algorithm can estimate "possibly" non-Gaussian posterior distributions for complex non-linear systems. An efficient regression scheme associated with the more rigorous core algorithm allows for long-term predictions, fault growth estimation with confidence bounds and remaining useful life (RUL) estimation after a fault is detected. The leading contributions of this thesis are (a) the development of a novel Bayesian Anomaly Detector for efficient and reliable Fault Detection and Identification (FDI) based on Least Squares Support Vector Machines, (b) the development of a data-driven real-time architecture for long-term Failure Prognosis using Least Squares Support Vector Machines, (c) Uncertainty representation and management using Bayesian Inference for posterior distribution estimation and hyper-parameter tuning, and finally (d) the statistical characterization of the performance of diagnosis and prognosis algorithms in order to relate the efficiency and reliability of the proposed schemes.

Evaluation of an Integrated Multi-Task Machine Learning System with Humans in the Loop

DTIC Science & Technology

2007-01-01

machine learning components natural language processing, and optimization...was examined with a test explicitly developed to measure the impact of integrated machine learning when used by a human user in a real world setting...study revealed that integrated machine learning does produce a positive impact on overall performance. This paper also discusses how specific machine learning components contributed to human-system

In Situ Roughness Measurements for the Solar Cell Industry Using an Atomic Force Microscope

PubMed Central

González-Jorge, Higinio; Alvarez-Valado, Victor; Valencia, Jose Luis; Torres, Soledad

2010-01-01

Areal roughness parameters always need to be under control in the thin film solar cell industry because of their close relationship with the electrical efficiency of the cells. In this work, these parameters are evaluated for measurements carried out in a typical fabrication area for this industry. Measurements are made using a portable atomic force microscope on the CNC diamond cutting machine where an initial sample of transparent conductive oxide is cut into four pieces. The method is validated by making a comparison between the parameters obtained in this process and in the laboratory under optimal conditions. Areal roughness parameters and Fourier Spectral Analysis of the data show good compatibility and open the possibility to use this type of measurement instrument to perform in situ quality control. This procedure gives a sample for evaluation without destroying any of the transparent conductive oxide; in this way 100% of the production can be tested, so improving the measurement time and rate of production. PMID:22319338

In situ roughness measurements for the solar cell industry using an atomic force microscope.

PubMed

González-Jorge, Higinio; Alvarez-Valado, Victor; Valencia, Jose Luis; Torres, Soledad

2010-01-01

Areal roughness parameters always need to be under control in the thin film solar cell industry because of their close relationship with the electrical efficiency of the cells. In this work, these parameters are evaluated for measurements carried out in a typical fabrication area for this industry. Measurements are made using a portable atomic force microscope on the CNC diamond cutting machine where an initial sample of transparent conductive oxide is cut into four pieces. The method is validated by making a comparison between the parameters obtained in this process and in the laboratory under optimal conditions. Areal roughness parameters and Fourier Spectral Analysis of the data show good compatibility and open the possibility to use this type of measurement instrument to perform in situ quality control. This procedure gives a sample for evaluation without destroying any of the transparent conductive oxide; in this way 100% of the production can be tested, so improving the measurement time and rate of production.

Discriminative parameter estimation for random walks segmentation.

PubMed

Baudin, Pierre-Yves; Goodman, Danny; Kumrnar, Puneet; Azzabou, Noura; Carlier, Pierre G; Paragios, Nikos; Kumar, M Pawan

2013-01-01

The Random Walks (RW) algorithm is one of the most efficient and easy-to-use probabilistic segmentation methods. By combining contrast terms with prior terms, it provides accurate segmentations of medical images in a fully automated manner. However, one of the main drawbacks of using the RW algorithm is that its parameters have to be hand-tuned. we propose a novel discriminative learning framework that estimates the parameters using a training dataset. The main challenge we face is that the training samples are not fully supervised. Specifically, they provide a hard segmentation of the images, instead of a probabilistic segmentation. We overcome this challenge by treating the optimal probabilistic segmentation that is compatible with the given hard segmentation as a latent variable. This allows us to employ the latent support vector machine formulation for parameter estimation. We show that our approach significantly outperforms the baseline methods on a challenging dataset consisting of real clinical 3D MRI volumes of skeletal muscles.

Inverse planning in the age of digital LINACs: station parameter optimized radiation therapy (SPORT)

NASA Astrophysics Data System (ADS)

Xing, Lei; Li, Ruijiang

2014-03-01

The last few years have seen a number of technical and clinical advances which give rise to a need for innovations in dose optimization and delivery strategies. Technically, a new generation of digital linac has become available which offers features such as programmable motion between station parameters and high dose-rate Flattening Filter Free (FFF) beams. Current inverse planning methods are designed for traditional machines and cannot accommodate these features of new generation linacs without compromising either dose conformality and/or delivery efficiency. Furthermore, SBRT is becoming increasingly important, which elevates the need for more efficient delivery, improved dose distribution. Here we will give an overview of our recent work in SPORT designed to harness the digital linacs and highlight the essential components of SPORT. We will summarize the pros and cons of traditional beamlet-based optimization (BBO) and direct aperture optimization (DAO) and introduce a new type of algorithm, compressed sensing (CS)-based inverse planning, that is capable of automatically removing the redundant segments during optimization and providing a plan with high deliverability in the presence of a large number of station control points (potentially non-coplanar, non-isocentric, and even multi-isocenters). We show that CS-approach takes the interplay between planning and delivery into account and allows us to balance the dose optimality and delivery efficiency in a controlled way and, providing a viable framework to address various unmet demands of the new generation linacs. A few specific implementation strategies of SPORT in the forms of fixed-gantry and rotational arc delivery are also presented.

Multi objective genetic algorithm to optimize the local heat treatment of a hardenable aluminum alloy

NASA Astrophysics Data System (ADS)

Piccininni, A.; Palumbo, G.; Franco, A. Lo; Sorgente, D.; Tricarico, L.; Russello, G.

2018-05-01

The continuous research for lightweight components for transport applications to reduce the harmful emissions drives the attention to the light alloys as in the case of Aluminium (Al) alloys, capable to combine low density with high values of the strength-to-weight ratio. Such advantages are partially counterbalanced by the poor formability at room temperature. A viable solution is to adopt a localized heat treatment by laser of the blank before the forming process to obtain a tailored distribution of material properties so that the blank can be formed at room temperature by means of conventional press machines. Such an approach has been extensively investigated for age hardenable alloys, but in the present work the attention is focused on the 5000 series; in particular, the optimization of the deep drawing process of the alloy AA5754 H32 is proposed through a numerical/experimental approach. A preliminary investigation was necessary to correctly tune the laser parameters (focus length, spot dimension) to effectively obtain the annealed state. Optimal process parameters were then obtained coupling a 2D FE model with an optimization platform managed by a multi-objective genetic algorithm. The optimal solution (i.e. able to maximize the LDR) in terms of blankholder force and extent of the annealed region was thus evaluated and validated through experimental trials. A good matching between experimental and numerical results was found. The optimal solution allowed to obtain an LDR of the locally heat treated blank larger than the one of the material either in the wrought condition (H32) either in the annealed condition (H111).

Heat transfer measurements for Stirling machine cylinders

NASA Technical Reports Server (NTRS)

Kornhauser, Alan A.; Kafka, B. C.; Finkbeiner, D. L.; Cantelmi, F. C.

1994-01-01

The primary purpose of this study was to measure the effects of inflow-produced heat turbulence on heat transfer in Stirling machine cylinders. A secondary purpose was to provide new experimental information on heat transfer in gas springs without inflow. The apparatus for the experiment consisted of a varying-volume piston-cylinder space connected to a fixed volume space by an orifice. The orifice size could be varied to adjust the level of inflow-produced turbulence, or the orifice plate could be removed completely so as to merge the two spaces into a single gas spring space. Speed, cycle mean pressure, overall volume ratio, and varying volume space clearance ratio could also be adjusted. Volume, pressure in both spaces, and local heat flux at two locations were measured. The pressure and volume measurements were used to calculate area averaged heat flux, heat transfer hysteresis loss, and other heat transfer-related effects. Experiments in the one space arrangement extended the range of previous gas spring tests to lower volume ratio and higher nondimensional speed. The tests corroborated previous results and showed that analytic models for heat transfer and loss based on volume ratio approaching 1 were valid for volume ratios ranging from 1 to 2, a range covering most gas springs in Stirling machines. Data from experiments in the two space arrangement were first analyzed based on lumping the two spaces together and examining total loss and averaged heat transfer as a function of overall nondimensional parameter. Heat transfer and loss were found to be significantly increased by inflow-produced turbulence. These increases could be modeled by appropriate adjustment of empirical coefficients in an existing semi-analytic model. An attempt was made to use an inverse, parameter optimization procedure to find the heat transfer in each of the two spaces. This procedure was successful in retrieving this information from simulated pressure-volume data with artificially generated noise, but it failed with the actual experimental data. This is evidence that the models used in the parameter optimization procedure (and to generate the simulated data) were not correct. Data from the surface heat flux sensors indicated that the primary shortcoming of these models was that they assumed turbulence levels to be constant over the cycle. Sensor data in the varying volume space showed a large increase in heat flux, probably due to turbulence, during the expansion stroke.

Optimization of large matrix calculations for execution on the Cray X-MP vector supercomputer

NASA Technical Reports Server (NTRS)

Hornfeck, William A.

1988-01-01

A considerable volume of large computational computer codes were developed for NASA over the past twenty-five years. This code represents algorithms developed for machines of earlier generation. With the emergence of the vector supercomputer as a viable, commercially available machine, an opportunity exists to evaluate optimization strategies to improve the efficiency of existing software. This result is primarily due to architectural differences in the latest generation of large-scale machines and the earlier, mostly uniprocessor, machines. A sofware package being used by NASA to perform computations on large matrices is described, and a strategy for conversion to the Cray X-MP vector supercomputer is also described.