两电机变频调速系统的改进RLS逆模型辨识  

Inverse model identification for two-motor variable frequency speed-regulating system based on modified RLS algorithm

作　　者：张懿[1] 魏海峰[1] 

机构地区：[1]江苏科技大学电子信息学院,江苏镇江212003

出　　处：《江苏大学学报（自然科学版）》2013年第4期435-439,共5页Journal of Jiangsu University：Natural Science Edition

基　　金：国家自然科学基金资助项目(51077066);光机电装备技术北京市重点实验室基金资助项目(KF2012-04);江苏高校优势学科建设工程项目(苏政办发[2011]6号)

摘　　要：为弥补现有两电机变频调速系统逆模型辨识中存在的不足,提出一种多模型LSSVM逆模型辨识方案.依据多模型思想,利用LSSVM拟合系统局部逆模型中的非线性映射,将各局部逆模型加权输出,建立离线初始逆模型.根据逆模型输出与系统输入的偏差,通过改进的RLS算法自适应调整局部逆模型权值,对初始逆模型在线校正,使其适应对象的变化,提高辨识精度和收敛速度.分析了两电机变频调速系统及可逆性,阐述了改进的RLS算法和LSSVM算法,给出了多模型LSSVM辨识方案的实现步骤,并对辨识效果进行了仿真试验.仿真结果表明,新型辨识方案是可行有效的,适用于两电机变频调速系统的逆模型辨识.To solve the defects of conventional inverse model identification methods for two-motor variable frequency speed-regulating system, a multi-model least squares support vector machines （LSSVM） modeling method was proposed. Based on multi-model, the LSSVM was used to fit the nonlinear mapping of local inverse models. The estimation of every LSSVM local model was fused by computing the weighted sum of local models to build the initial off-line inverse model of the system. According to system devia- tion, the modified recursive least-squares （RLS） algorithm was adopted to adjust the weights adaptively. The initial inverse model was corrected online to improve identification accuracy and convergence rate. The two-motor variable frequency speed-regulating system and the corresponding invertibility were ana- lyzed, and the improved RLS algorithm and L$SVM algorithm were described. The steps of realizing multiple-model LSSVM identification scheme was provided to achieve the simulation of identification effect. The simulation results show that the proposed method is suitable for the inverse model identification of two-motor variable frequency speed-regulating system.

关 键 词：逆模型辨识 两电机变频调速系统 最小二乘支持向量机 递归最小二乘算法 多模型 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]