English

应用科学学报 ›› 2004, Vol. 22 ›› Issue (1): 76-80.

• 论文 • 上一篇    下一篇

基于神经网络的一类非线性系统自适应滑模控制

陈谋, 姜长生   

  1. 南京航空航天大学自动化学院 江苏南京 210016
  • 收稿日期:2002-10-31 修回日期:2003-04-17 出版日期:2004-03-31 发布日期:2004-03-31
  • 作者简介:陈谋(1975-),男,四川蓬安人,博士;姜长生(1942-),男,江苏南京人,教授,博导.
  • 基金资助:
    国家自然科学基金资助项目(60174045)

Adaptive Sliding Mode Control for a Class of Nonlinear System Based on Neural Networks

CHEN Mou, JIANG Chang-sheng   

  1. College of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
  • Received:2002-10-31 Revised:2003-04-17 Online:2004-03-31 Published:2004-03-31

PDF

81

被引次数

31

摘要： 对一类非线性系统进行简化处理后,结合神经网络逼近方法、自适应滑模控制提出一种新的自适应控制方法.所设计的控制器分为两部分,一部分是等效控制器,另一部分是滑模控制器.滑模控制器用来减小系统的跟踪误差,起鲁棒控制作用.文中用神经网络逼近非线性函数,并将网络权值误差引入到神经网络权值的自适应律中用以改善系统的动态性能.最后给出的仿真算例证明所设计的控制器是十分有效的.

关键词: 神经网络, 滑模控制, 非线性系统, 自适应控制

Abstract: This paper is devoted to discussing a new control method which combine the approximation method of neural network with sliding mode control for a class of nonlinear systems. The controller is made up of an equivalent controller and an adaptive sliding mode controller. The sliding mode controller is a robust controller and it is used to diminish the track error of the control system. The neural networks are used to approximate the nonlinear functions and the approximation errors of the neural networks are introduced to the adaptive law in order to improve the quality of this system. Finally, an example is given to demonstrate the availability of this method.

Key words: neural networks, nonlinear systems, adaptive control, sliding mode control

中图分类号: