引用本文:李鸿儒, 顾树生.基于神经网络的PMSM自适应滑模控制[J].控制理论与应用,2005,22(3):461~464.[点击复制]
LI Hong-ru, GU Shu-sheng.Neural-network-based adaptive sliding mode control for PMSM[J].Control Theory and Technology,2005,22(3):461~464.[点击复制]
基于神经网络的PMSM自适应滑模控制
Neural-network-based adaptive sliding mode control for PMSM
摘要点击 1414  全文点击 2039  投稿时间：2002-08-22  修订日期：2004-05-27
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/j.issn.1000-8152.2005.3.023
  2005,22(3):461-464
中文关键词  永磁同步电机  滑模变结构控制  神经网络  抖振
英文关键词  permanent magnet synchronous motor (PMSM)  sliding-mode control  neural network  chattering
基金项目  973计划子课题资助项目(2002CB312200).
作者单位
李鸿儒, 顾树生 东北大学 教育部暨辽宁省流程工业综合自动化重点实验室,辽宁 沈阳 110004
东北大学 信息科学与工程学院,辽宁 沈阳 110004 
中文摘要
      结合滑模控制和神经网络各自的优点,对永磁同步电机(PMSM)提出了一种基于神经网络的PMSM自适应滑模控制方案.首先设计了带积分操作的滑模变结构位置控制器,通过递归神经网络的在线学习来实时估计系统参数变化和外部负载扰动等不确定性的界限,减小滑模控制器的控制量.进而,在滑模控制器中又引入饱和函数取代符号函数,进一步减弱"抖振"现象.理论分析和实验仿真对比研究的结果表明所提出方法具有优越的动态性能和鲁棒性.
英文摘要
      With the combination of the merits of sliding-mode control and neural network,a neural-network-based adaptive sliding-mode control scheme for permanent magnet synchronous motor (PMSM) is proposed.First,a sliding-mode controller with an integral-operation switching surface is designed.Then a recurrent neural network is used to estimate the upper bound of uncertainties in real-time,which include parameter variations and external load disturbance,such that the control effort of the sliding-mode controller is reduced.Furthermore,in order to reduce the chattering phenomenon,the sign function in sliding-mode controller is replaced by the saturation function.Theoretical analysis and experiment simulation results show that the proposed strategy has high-performance dynamic characteristics and stronger robustness.