Modeling of SRM Based on XS-LSSVR Optimized by GDS

Author

Likun, Hou ; Qingxin, Yang ; Jinlong, An

Author_Institution

Province-Minist. Joint Key Lab. of Electromagn. Field & Electr. Apparatus Reliability, Hebei Univ. of Technol., Tianjin, China

Volume

20

Issue

3

fYear

2010

fDate

6/1/2010 12:00:00 AM

Firstpage

1102

Lastpage

1105

Abstract

Considering nonlinear magnetization characteristic of switched reluctance motor (SRM), this paper describes a nonlinear model of SRM based on an improved least square support vector machine regression (LSSVR) algorithm optimized by grid-diamond searching (GDS) method. The experimental results show that the GDS method can choose proper parameters of LSSVR while providing better simulation result. Modeling with the optimization parameter, the forecasted data of the model are compared with the experimental data on a four-phase, 8/6 SRM. It is shown that XS-LSSVR optimized by GDS is effectiveness method and performs better forecast accuracy and successful modeling of SRM.

Keywords

least squares approximations; regression analysis; reluctance machines; search problems; support vector machines; GDS method; SRM; XS-LSSVR; grid diamond searching method; least square support vector machine regression algorithm; switched reluctance motor; Grid-diamond searching; least square support vector machine regression; modeling; switched reluctance motor;

fLanguage

English

Journal_Title

Applied Superconductivity, IEEE Transactions on

Publisher

ieee

ISSN

1051-8223

Type

jour

DOI

10.1109/TASC.2010.2043518

Filename

5438860