无刷双馈电机模糊神经网络PID转速控制  

Speed control of brushless doubly-fed machine based on fuzzy neural network proportion integration differentiation

作　　者：乔维德 QIAO Weide(Division of Scientific Research and Quality Control,Wuxi Open University,Wuxi 214011,Jiangsu,China)

机构地区：[1]无锡开放大学科研与质量控制处,江苏214011

出　　处：《上海电机学院学报》2020年第4期200-206,共7页Journal of Shanghai Dianji University

基　　金：无锡市社会事业领军人才基金项目(WX530/2019/043)。

摘　　要：无刷双馈电机(BDFM)控制系统是具有高度非线性、时变性的转速、电流双闭环调速系统,但转速控制器采用传统PID控制,难以实现快速、准确的转速响应要求。为此,提出一种基于控制的转速控制策略,采取粒子群人工蜂群(PSO-ABC)算法、改进BP算法优化训练网络以及输出PID控制器最优参数kp、ki、kd,所设计的递归模糊神经网络PID控制器能实现准确的转速跟踪,动态响应好,鲁棒性强。仿真分析与实验结果均取得较好的控制效果,从而验证控制方法的有效性。The control system of the brushless doubly-fed machine(BDFM)is a system with a high nonlinear and time-varying speed and a current double closed-loop speed.The speed controller adopts a traditional proportion integration differentiation(PID)control,which is difficult to achieve the fast and accurate speed response requirements.In this paper,a speed control strategy based on control is proposed.A particle swarm optimization-artificial bee colony(PSO-ABC)algorithm and an improved BP algorithm are adopted to optimize the training network,and the optimal parameters kp,ki,and kd of the PID controller are output.The designed recursive fuzzy neural network PID controller can achieve accurate speed tracking,good dynamic response,and strong robustness.The results of simulation and experiment show that the control method is effective.

关 键 词：无刷双馈电机 递归模糊神经网络 PID控制 粒子群人工蜂群算法 

分 类 号：TM301.2[电气工程—电机]