基于递归神经网络的永磁同步电机控制器设计  

Design of Permanent Magnet Synchronous Motor Controller Based on Recurrent Neural Network

作　　者：沈艳霞[1] 江俊[1] 纪志成[1] 

机构地区：[1]江南大学电气自动化研究所,江苏无锡214122

出　　处：《南京理工大学学报（社会科学版）》2005年第S1期79-82,共4页Journal of Nanjing University of Science and Technology：Social Sciences

基　　金：江苏省高技术研究计划(工业)(BG2005014)

摘　　要：在永磁同步电机矢量控制系统中,采用递归神经网络控制器作为速度控制器来模拟在电机参数变化和负载扰动下的最优速度输出。神经网络采用扩展卡尔曼滤波方法实现在线训练,并在Lyapunov稳定性意义下对网络的学习率进行了分析。该神经网络矢量控制系统具有良好的动、静态特性,同时在变速和变负载情况下效果理想。该方法在一台1.2 kW永磁同步电机驱动系统上验证通过。A novel vector control method of a permanent magnet synchronous motor (PMSM) using recurrent neural network(RNN) is presented.The RNN controller is used as a speed controller to mimic an optimized speed output under the condition of motor parameters variations and load perturbation.The RNN is trained online by using the extended Kalman filter(EKF) algorithm,and the learning rates are obtained in the sense of Lyapunov stability theory.The proposed RNN vector controller has shown good performance in the transient and steady states,and also at either variable-speed operation or load variation.The validity and the usefulness of the proposed algorithm are thoroughly verified with experiments on fully digitalized 1.2 kW PMSM drive systems.

关 键 词：永磁同步电机 递归神经网络 扩展卡尔曼滤波 

分 类 号：TM341[电气工程—电机]