基于DRNN动态整定PMSM的SVPWM控制

作者：胡雪峰1，谭国俊2 日期：2007-07-09/span> 浏览：4367 查看PDF文档

                              基于DRNN动态整定PMSM的SVPWM控制
                                          胡雪峰1，谭国俊2

（1.安徽工业大学 电气学院，安徽 马鞍山 243002； 2.中国矿业大学 信电学院，江苏 徐州 221008）

摘 要：为解决传统的永磁同步电机控制系统中存在的低速转矩脉动大以及由此引起的高频噪声、动态响应慢等问题，提出了一种基于对角神经网络动态自整定的永磁同步电机矢量控制系统的实施方案。给出了基于对角递归神经网络的PID动态自整定控制器的结构，以及PID参数动态自整定的学习控制算法，并将这种综合控制策略引入永磁同步电机空间电压矢量PWM控制中。仿真结果表明，系统低速性能好，转矩脉动小，谐波含量少，当电机参数改变或者受到外部扰动时，系统具有良好的动态特性。
关键词：对角递归神经网络；动态整定；空间矢量脉宽调制；综合控制；永磁同步电机

                     SVPWM control of PMSM based on DRNN dynamic tuning
                                HU Xuefeng1, TAN Guojun2
(1.College of Electrical Engineering, Anhui University of Technology, Maanshan 243002, China；
2.College of Electrical Engineering & Information, China University of Mining & Technology, Xuzhou 221008, China)
Abstract: To sovle those prolems associated with conventional control systems of permanent magnet synchronous motor (PMSM), such as high torque ripple at low speed, high frequence noise by torque ripple and slow response, the implementation of digonal recurrent neural network dynamic speed controller for space vector PWM control of a permanent magnet synchronous motor was presented. The structure of dynamic PID speed controller based on digonal recurrent neural network, and an dynamic learning algorithm was given. The results of simulation were provided to demonstrate the system had low torque ripple, few harmonics and the effectiveness of the proposed DRNN dynamic speed controller under the occurrence of parameter variations and external disturbance.
Key words: digonal recurrent neural network(DRNN); dynamic tuning; space vector pulse width modulation(SVPWM); synthesis control; permanent magnet synchronous motor(PMSM)

参考文献(Reference)：
［1］LI Sandong. Modeling and Simulation of PMSM control system based on Matlab［J］. Journal of Southern Yangtze University,2004,3(2):115-125.
［2］VLADIMIR B. Analysis of a hybrid PWM based on modified spacevector and trianglecomparison methods［J］. IEEE. Trans. on Industry Applications,1997,33(3):756-763.
［3］BROECK H W, SKUDELNY H C. Analysis and realication of a pulse width modulator based on voltage space vectors［J］.IEEE Trans. on Industry Applications,1998,24(1):142-149.
［4］TAN Guojun, KUAI Songyan, HE Fengyou. Simulation and analysis on switched reluetance motor nonlinear characteristie under chopped voltage control[J]. Journal of System Simulation,2006,18(2):478-481.
［5］徐丽娜.神经网络控制［M］.哈尔滨：哈尔滨工业大学出版社，1999.
［6］飞思科技研发中心.神经网络理论与实现［M］.北京:电子工业出版社，2005.
［7］KU C C, LEE K Y. Digonal recurrent neural networks for dynamic system control［J］. IEEE. Trans on Netral Netwoks,1995，6（1）:144-155.
［8］XIONG Jian, KANG Yong, ZHANG Kai, et al. Comparison study of Voltage space vector PWM and conventional SPWM[J]. Power Electronics,1999,33(1):25-28.