Nonlinear Modeling of the Inverse Force Function for the Planar Switched Reluctance Motor Using Sparse Least Squares Support Vector Machines

Abstract

In advanced manufacturing industry, planar switched reluctance motors (PSRMs) have proved to be a promising candidate due to their advantages of high precision, low cost, low heat loss, and ease of manufacture. However, their inverse force function, which provides vital phase current command for precise motion, is highly nonlinear and hard to be accurately modeled. This paper proposes a novel inverse force function using sparse least squares support vector machines (LS-SVMs) to achieve nonlinear modeling for precise motion of a PSRM. The required training and testing sets of sparse LS-SVMs are firstly obtained from experimental measurement. A sparse LS-SVMs regression is further developed using training set to accurately model the inverse force function. Accordingly, the function is tested via the testing set to assess its feasibility. Finally, the proposed approach is applied to the PSRM system with dSPACE controller for trajectory tracking, and its effectiveness and superior performance are verified through experimental results. Her research interests include design and control of planar switched reluctance motors, and control theory and its application.Guang-Zhong Cao (M'15) received the B.Sc., M.Sc., and Ph.D. degrees in electrical engineering and automation from Xi'an Jiaotong University, He has published more than 60 articles in refereed journals and conferences. His research interests include motor control, and control theory and its application.Zheng-You He (M'10-SM'13) received the B.Sc. and M.Sc. degrees in computational mechanics from Chongqing University, Chongqing, China, in 1992 and 1995, respectively, and the Ph.D. degree in electrical engineering from Southwest . His research interests include signal processing and information theory applied to power system, and application of wavelet transforms in power system. J. F. Pan received the B.Sc. degree in electrical engineering from ChangChun

KNN-FSVM for Fault Detection in High-Speed Trains

“…SVM solves nonlinear classification problems by mapping the original data into a high-dimensional feature space where the problem becomes linear [20]. As shown in Figure 1, The optimal hyperplane position is constrained largely by the support vectors [27].…”

A New Design Optimization Method for Permanent Magnet Synchronous Linear Motors

“…Exploring the objective function-F(x), which can calculate any output value y for any input x, is the essence of SVM [27][28][29][30][31]. The multi-SVM is the modified SVM algorithm, which contains the multidimensional vector output y.…”

Inductance Surface Learning for Model Predictive Current Control of Switched Reluctance Motors

“…In SRMs, since the flux linkage and current go to zero periodically, the phase flux linkage may be obtained from the integral of the phase voltages [34], [44]. More advanced techniques have been utilized to form regression mechanisms for the inductance or the force profiles such as utilizing a support vector machine in [45] and with the addition of a kernel based regression in [46]. In this paper, a closed-loop inductance estimation is of interest to ensure the convergence to the true profile of the machine.…”