基于LS-SVM的无轴承同步磁阻电动机逆模型辨识及解耦控制  

Inverse-Model Identification and Decoupling Control of Bearingless Synchronous Reluctance Motor Based on LS-SVM

作　　者：杨泽斌[1] 汪明涛[1] 孙晓东[1] 朱熀秋[1] 

机构地区：[1]江苏大学电气信息工程学院,江苏镇江212013

出　　处：《轴承》2013年第6期5-10,共6页Bearing

基　　金：国家自然科学基金资助项目(61104016;60974053;61174055);江苏省高校自然科学基金资助项目(11KJB510002);江苏高校优势学科建设工程资助项目(苏政办发[2011]6号)

摘　　要：针对无轴承同步磁阻电动机多变量、非线性、强耦合等特点,提出一种基于最小二乘支持向量机逆模型辩识与解耦控制新策略。利用支持向量机函数拟合能力,离线建立无轴承同步磁阻电动机非线性逆模型,并将得到的逆模型串联在原对象之前,将原系统解耦成3个独立的单变量伪线性系统。为进一步克服逆模型建模误差,提高系统鲁棒性,提出将逆模型作为前馈控制器、PID作为反馈控制器的复合控制方法,并对转子起浮、稳定、解耦等性能进行仿真分析,结果表明,系统能实现旋转力与悬浮力之间的动态解耦,且具有良好的动、静态性能。An Inverse - model identification and decoupling control strategy of inverse system based on least squares support vector machine （ LS - SVM） is presented for the bearingless synchronous reluctance motor （BSRM） possessing the characteristics of multi - input - multi - output, nonlinearity, strong coupling and so on. The nonlinear inverse model for bearingless synchronous reluctance motor is obtained offline using ability of function fitting of support vector machine. The inverse - model is connected in series with original system to decouple the system to three single - input - single - output pseudo linear systems. In order to further compensate the modeling error of inverse - model and improve robust performance of system, the PID feedback controller is designed, which together with inverse feedforward controller gives a composite control strategy, and the suspending, stability and decoupling performances are simulated and analyzed. The results show that the system is able to realize the dynamic decoupling between rotating force and sus- pending force, and which has fine dynamic and static performances.

关 键 词：无轴承同步磁阻电动机 逆模型 最小二乘支持向量机 辨识 解耦 

分 类 号：TM301.2[电气工程—电机]