基于神经网络广义逆的感应电机变频系统内模控制  

Internal model control of induction motor variable frequency speed control system based on neural network generalized inverse

作　　者：刘国海[1] 杨官学[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：《江苏大学学报（自然科学版）》2010年第1期63-67,共5页Journal of Jiangsu University：Natural Science Edition

基　　金：国家自然科学基金资助项目(60874014);江苏省自然科学基金资助项目(BK2007094);教育部博士点基金资助项目(20050299009)

摘　　要：为提高感应电机变频调速系统的鲁棒性和抗干扰能力,提出了基于神经网络广义逆系统的内模控制方法.在分析原系统可逆性的基础上,先用动态神经网络逼近原系统的广义逆模型,从而串接在原系统之前组成广义伪线性复合系统,实现系统的线性化与开环稳定,有利于系统的综合.再对广义伪线性系统引入内模控制,保证系统的鲁棒稳定性.采用该系统进行了阶跃响应和跟踪效果试验.结果表明,该方法能够成功地实现系统的线性化,并且当系统存在建模误差和负载扰动的情况时,仍能使系统保持高性能的控制.In order to improve the robustness and anti-interference ability of induction motor variable frequency speed control system, an internal model control （IMC） method based on neural network generalized inverse（ NNGI） method is proposed. On the basis of reversibility analysis of original system, the generalized inverse model approximated by the dynamical BP neural network is connected with the original system, and the generalized pseudo-linear combined system is constructed. Based on the NNGI, linearization and open-loop stability of system can be reached, which benefits the integration of control system. Then the robust stability can be ensured by introducing internal model control in generalized pseudo-linear system. Experiments of step response and tracking response were implemented based on this system. The results show that the linearization of the system can be realized successfully and the high performance of speed eontrol can be ensured when the system has inverse modeling errors and changeable load.

关 键 词：感应电机 交流变频调速系统 神经网络 广义逆 内模控制 鲁棒稳定性 

分 类 号：TM343[电气工程—电机]