A Gaussian process regression based on variable parameters fuzzy dominance genetic algorithm for B-TFPMM torque estimation

Abstract Transverse Flux Permanent Magnet Motor (TFPMM) has received extensive attention in the field of electric vehicles. The magnetic circuit of TFPMM is three-dimensional and non-linear, which leads to the high nonlinearity of electromagnetic torque. Although the three-dimensional finite element method (3DFEM) could be used to estimate torque, it is very time-consuming. Instead of it, this study adopts a kind of machine learning method—Gaussian process regression (GPR). For the hyper-parameters optimization of GPR, most previous studies used single-objective algorithms for improving the regression accuracy. However, GPR is an algorithm of probability prediction and it could not guarantee to have the satisfactory confidence interval characteristic simultaneously while the regression precision achieves optimal. Therefore this paper proposes a variable parameters fuzzy dominance genetic algorithm (VPFDGA) which is suitable for the multi-objective optimization, including the optimization of regression precision, confidence interval reliability, confidence interval width and skill score. By combining GPR with VPFDGA, the electromagnetic torque of a building-block transverse flux permanent magnet motor (B-TFPMM) is estimated by VPFDGA-GPR (GPR based on variable parameters fuzzy dominance genetic algorithm). Besides, two other GPRs based multi-objective optimization, three GPRs based on single-objective optimization and a GPR based on weighted sum method that is the classic multi-objective optimization algorithm are all implemented to compare with VPFDGA-GPR. The results of comparison show that VPFDGA-GPR has the better performances including the higher regression precision, more powerful ability of probability prediction, higher stability, less convergence time and so on.

[1]  Tao Chen,et al.  Bagging for Gaussian process regression , 2009, Neurocomputing.

[2]  Fabrizio Marignetti,et al.  Electromagnetic Design and Analysis of a Novel Axial-Transverse Flux Permanent Magnet Synchronous Machine , 2017 .

[3]  Do-Hyun Kang,et al.  Determination of Parameters Considering Magnetic Nonlinearity in Solid Core Transverse Flux Linear Motor for Dynamic Simulation , 2008, IEEE Transactions on Magnetics.

[4]  Zhong Yi Wan,et al.  Reduced-space Gaussian Process Regression for data-driven probabilistic forecast of chaotic dynamical systems , 2016, 1611.01583.

[5]  P Pinson,et al.  Conditional Prediction Intervals of Wind Power Generation , 2010, IEEE Transactions on Power Systems.

[6]  N. D. Hatziargyriou,et al.  Probabilistic Wind Power Forecasting Using Radial Basis Function Neural Networks , 2012, IEEE Transactions on Power Systems.

[7]  H R Karimi,et al.  Modeling and output tracking of transverse flux permanent magnet machines using high gain observer and RBF neural network. , 2005, ISA transactions.

[8]  Yan Li,et al.  Zen-ReqOptimizer: a search-based approach for requirements assignment optimization , 2015, Empirical Software Engineering.

[9]  Chong Xu,et al.  Traffic Flow Forecasting for Road Tunnel Using PSO-GPR Algorithm with Combined Kernel Function , 2017 .

[10]  Massimiliano Gobbi,et al.  A fuzzy-optima definition based multiobjective optimization of a racing car tyre-suspension system , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[11]  Marco Farina,et al.  A fuzzy definition of "optimality" for many-criteria optimization problems , 2004, IEEE Trans. Syst. Man Cybern. Part A.

[12]  Peng Chen,et al.  Uncertainty propagation using infinite mixture of Gaussian processes and variational Bayesian inference , 2015, J. Comput. Phys..

[13]  S. M. Sharkh,et al.  An insight into torque production and power factor in transverse-flux machines , 2016, 2016 XXII International Conference on Electrical Machines (ICEM).

[14]  Xu Chong,et al.  INTELLIGENT ANALYSIS MODEL OF SLOPE NONLINEAR DISPLACEMENT TIME SERIES BASED ON GENETIC-GAUSSIAN PROCESS REGRESSION ALGORITHM OF COMBINED KERNEL FUNCTION , 2009 .

[15]  Johannes J. H. Paulides,et al.  Toward Accurate Design of a Transverse Flux Machine Using an Analytical 3-D Magnetic Charge Model , 2015, IEEE Transactions on Magnetics.

[16]  Yuanjun Zhou,et al.  Torque ripple suppression of a new in-wheel motor based on quantum genetic algorithm , 2016, 2016 23rd International Conference on Mechatronics and Machine Vision in Practice (M2VIP).

[17]  Ilias Bilionis,et al.  Multi-output local Gaussian process regression: Applications to uncertainty quantification , 2012, J. Comput. Phys..

[18]  Ali Jahan,et al.  A state-of-the-art survey on the influence of normalization techniques in ranking: Improving the materials selection process in engineering design , 2015 .

[19]  Giampiero Mastinu,et al.  Optimising a Car Chassis , 1999 .

[20]  Christopher K. I. Williams,et al.  Understanding Gaussian Process Regression Using the Equivalent Kernel , 2004, Deterministic and Statistical Methods in Machine Learning.

[21]  Bo Wang,et al.  Bayesian variable selection for Gaussian process regression: Application to chemometric calibration of spectrometers , 2010, Neurocomputing.

[22]  D. Hong,et al.  Optimum Design of Transverse Flux Linear Motor for Weight Reduction and Improvement Thrust Force Using Response Surface Methodology , 2008, IEEE Transactions on Magnetics.

[23]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[24]  Zheng Xiang.  Progress of Research on Multi-Objective Evolutionary Algorithms , 2007 .

[25]  I. Y. Kim,et al.  Adaptive weighted-sum method for bi-objective optimization: Pareto front generation , 2005 .

[26]  R. Marler,et al.  The weighted sum method for multi-objective optimization: new insights , 2010 .

[27]  C. Hwang,et al.  Fuzzy Mathematical Programming: Methods and Applications , 1995 .

[28]  Jung-Pyo Hong,et al.  Computation of inductance and static thrust of a permanent-magnet-type transverse flux linear motor , 2006 .

[29]  Lothar Thiele,et al.  An evolutionary algorithm for multiobjective optimization: the strength Pareto approach , 1998 .

[30]  Lu Ding,et al.  Cognitive state recognition using wavelet singular entropy and ARMA entropy with AFPA optimized GP classification , 2016, Neurocomputing.

[31]  Romain Hérault,et al.  Advances in artificial neural networks, machine learning and computational intelligence , 2017, Neurocomputing.

[32]  Alessandro Ghio,et al.  Developments in computational intelligence and machine learning , 2015, Neurocomputing.

[33]  J. Ramik.  Fuzzy multi-criteria optimization based on fuzzy relations , 2002, 2002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE'02. Proceedings (Cat. No.02CH37291).

[34]  Ian C. Parmee,et al.  Multiobjective Satisfaction within an Interactive Evolutionary Design Environment , 2000, Evolutionary Computation.

[35]  Pierre Pinson,et al.  Non‐parametric probabilistic forecasts of wind power: required properties and evaluation , 2007 .

[36]  Erich Schmidt.  Finite element analysis of a novel design of a three phase transverse flux machine with an external rotor , 2010, Digests of the 2010 14th Biennial IEEE Conference on Electromagnetic Field Computation.

[37]  Martin Doppelbauer,et al.  Multi-Objective Optimization of a Transverse Flux Machine With Claw-Pole and Flux-Concentrating Structure , 2016, IEEE Transactions on Magnetics.

[38]  J. Weston,et al.  Approximation Methods for Gaussian Process Regression , 2007 .

[39]  Yuanjun Zhou,et al.  Research on the mechanical characteristic of a novel building-block transverse flux permanent-magnetic motor (B-TFPM) , 2016 .

[40]  Abbas Rohani,et al.  A novel soft computing model (Gaussian process regression with K-fold cross validation) for daily and monthly solar radiation forecasting (Part: I) , 2018 .