基于PSO-LS-SVM的磁悬浮开关磁阻电机电感模型  

Inductance Model of Bearingless Switched Reluctance Motors Based on PSO-LS-SVM

作　　者：蒋维婷 孙玉坤[1,2] 朱志莹[1] 

机构地区：[1]江苏大学电气信息工程学院,江苏镇江212013 [2]南京工程学院电力工程学院,南京211167

出　　处：《微电机》2013年第11期1-5,共5页Micromotors

基　　金：国家自然科学基金项目(61074019)

摘　　要：磁悬浮开关磁阻电机(BSRM)的电感矩阵是电机建模的基础,本文提出了基于最小二乘支持向量机(LS-SVM)的电机电感辨识建模方法。首先通过对BSRM电感特性的有限元分析,获得各参数对电感的影响规律,然后结合LSSVM在有限样本数据下对高维非线性的逼近能力,离线建立BSRM各种运行工况下的电感模型。另外在建模中,针对LS-SVM超参数选取问题,采用粒子群优化算法(PSO)对其进行自动寻优,以提高电感模型精度。最后通过对比仿真研究,表明PSO-LS-SVM模型能够准确反映电机磁饱和下的电感特性,这为BSRM磁饱和模型的构建奠定了基础。The inductance matrix is very important for the model of bearingless switched reluctance motors （BSRM）. A novel modeling method of the inductance for BSRM using least squares-support vector machine （LS-SVM） was presented. First, the inductance characteristic of BSRM was analyzed by the finite elements method （FEM）. For the nonlinear character of the inductance, this approach takes advantage of LS-SVM with better solution for small-sample learning problem and good generalization ability. Through the off-line learning, a better LS-SYM was built to form an efficient nonlinear mapping for the inductance mode of BSRM. Then, the particle swarm optimization （PSO） ~algorithm was used to optimize parameters of LS-SVM to improve the accuracy of the inductance model. Finally, the comparative simulation research showed that the PSO-LS-SVM model could accurately reflect the inductance characteristics of BSRM under magnetic satu- ration. This makes a contribution to the model of BSRM considering the characteristic of magnetic saturation.

关 键 词：磁悬浮开关磁阻电机 支持向量机 粒子群优化 建模 

分 类 号：TM352[电气工程—电机]