引用本文:孙国法,田宇,王素珍.严格反馈非线性系统的自适应神经网络输出反馈控制[J].控制理论与应用,2017,34(3):375~382.[点击复制]
sunguofa,Tian-Yu,Wang Su-zhen.Adaptive neural output feedback control for strict feedback nonlinear system[J].Control Theory and Technology,2017,34(3):375~382.[点击复制]
严格反馈非线性系统的自适应神经网络输出反馈控制
Adaptive neural output feedback control for strict feedback nonlinear system
摘要点击 3088  全文点击 3241  投稿时间:2016-07-13  修订日期:2016-12-25
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2017.60509
  2017,34(3):375-382
中文关键词  状态观测器  动态面控制  自抗扰控制  神经网络
英文关键词  state observer  dynamic surface control  active disturbance rejection control  neural network
基金项目  中国博士后科学基金项目(2013M541939), 国家自然科学基金项目(61640302)资助.
作者单位E-mail
孙国法* 青岛理工大学 sunguofa_bo@163.com 
田宇 北京航天自动控制研究所  
王素珍 青岛理工大学 sunguofa_bo@163.com 
中文摘要
      基于非线性反馈函数, 文章设计神经网络状态观测器, 解决一类非线性系统的输出反馈控制问题. 非线性反馈神经网络观测器在系统存在不确定性函数的情况下实时估计系统状态. 利用所获得的状态信号, 设计了自适 应神经网络动态面控制器, 同时保证了闭环系统的稳定性和所有信号的有界性. 通过调节设计参数的取值能够达到期望的闭环跟踪性能. 数值仿真表明, 所设计的状态观测器不需要对原系统做状态变换, 能够克服输出反馈滑模控制器带来的抖震问题.
英文摘要
      Based on nonlinear feedback function, this paper investigates output feedback control problem for a class of nonlinear systems. In the case of systems with uncertain functions, nonlinear feedback neural network observer estimates system states in real time. Employing the obtained state signals, an adaptive neural network controller is designed to guarantee the stability of the closed-loop system and the boundedness of all signals. The desired closed-loop tracking performance can be achieved by adjusting the value of the design parameters. Numerical simulation results show that,without state transformation, the state observer overcomes the chattering problem caused by the output feedback sliding mode controller.