Application of LSSVM with AGA optimizing parameters to nonlinear modeling of SRM

Considering nonlinear magnetization characteristics of a switched reluctance motor (SRM), this paper presents a nonlinear model of SRM based on the integration of least square support vector machine (LSSVM) and adaptive genetic algorithm (AGA), known as LSSVM-AGA. The real-valued AGA is applied to optimize the parameters of LSSVM, and then the LSSVM using the optimal parameters forms a very efficient mapping structure for the nonlinear SRM. The hybrid method for modeling SRM is tested through sufficient sample data to verify its validation and feasibility. The sample data comprise flux linkage, current and rotor position, which obtained from the experimental SRM by the dc-excitation method. The forecasted data of the SRM model with LSSVM-AGA are compared with measured data, and error analyses are given to determine performances of the model. The experimental results demonstrate that LSSVM optimized by AGA performs better forecast accuracy and successful modeling of SRM.

[1]  S.F. Ghousia,et al.  Performance Analysis of an 8/6 Switched Reluctance Machine Using Finite-Element Method , 2007, 2007 IEEE Power Engineering Society General Meeting.

[2]  Liu Zhen.  Modeling of Switched Reluctance Motors Based on LS-SVM , 2007 .

[3]  Johan A. K. Suykens,et al.  Least Squares Support Vector Machine Classifiers , 1999, Neural Processing Letters.

[4]  M. M. Morcos,et al.  A simple model for switched reluctance motors , 2000 .

[5]  Seref Sagiroglu,et al.  Modelling of a nonlinear switched reluctance drive based on artificial neural networks , 1994 .

[6]  Zhang Yihuang,et al.  Nonlinear modeling of switched reluctance motor based on combination of neural network and genetic algorithm , 2005, 2005 International Conference on Electrical Machines and Systems.

[7]  R. Krishnan,et al.  Measurement and instrumentation of a switched reluctance motor , 1989, Conference Record of the IEEE Industry Applications Society Annual Meeting,.

[8]  Seref Sagiroglu,et al.  Nonlinear modelling of a switched reluctance drive based on neural networks , 1994, Proceedings of MELECON '94. Mediterranean Electrotechnical Conference.

[9]  D.W.J. Pulle,et al.  New data base for switched reluctance drive simulation , 1991 .

[10]  M. F. Rahman,et al.  Dynamic modeling of a four-phase 8/6 switched reluctance motor using current and torque look-up tables , 2002, IEEE 2002 28th Annual Conference of the Industrial Electronics Society. IECON 02.

[11]  Xin Feng,et al.  Modeling torque in a switched reluctance motor for adaptive control purposes using self-organizing neural networks , 1992, [Proceedings 1992] The First IEEE Conference on Control Applications.

[12]  Ping-Feng Pai,et al.  Forecasting regional electricity load based on recurrent support vector machines with genetic algorithms , 2005 .

[13]  Gunnar Rätsch,et al.  Predicting Time Series with Support Vector Machines , 1997, ICANN.

[14]  J. H. Lang,et al.  Modelling a nonlinear variable-reluctance motor drive , 1990 .

[15]  Dimitri P. Solomatine,et al.  Model Induction with Support Vector Machines: Introduction and Applications , 2001 .

[16]  J. Corda,et al.  Computation of torque and current in doubly salient reluctance motors from nonlinear magnetisation data , 1979 .

[17]  Johan A. K. Suykens,et al.  Automatic relevance determination for Least Squares Support Vector Machines classifiers , 2001, ESANN.

[18]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[19]  C. Roux,et al.  On the Use of a Simplified Model for Switched Reluctance Motors , 2002, IEEE Power Engineering Review.

[20]  Longya Xu,et al.  Direct modeling of switched reluctance machine by coupled field-circuit method , 1995 .

[21]  Changliang Xia,et al.  Adaptive PWM Speed Control for Switched Reluctance Motors Based on RBF Neural Network , 2006, 2006 6th World Congress on Intelligent Control and Automation.