English

应用科学学报 ›› 2004, Vol. 22 ›› Issue (1): 124-126.

• 论文 • 上一篇    

基于神经网络自适应观测器的鲁棒故障检测

周川, 胡维礼, 陈庆伟   

  1. 南京理工大学自动化系 江苏南京 210094
  • 收稿日期:2002-07-14 修回日期:2003-08-30 出版日期:2004-03-31 发布日期:2004-03-31
  • 作者简介:周川(1970-),男,江苏南京人,副教授,博士;胡维礼(1941-),男,江苏东台人,教授,博导.
  • 基金资助:
    国家自然科学基金(60174019);清华大学智能技术与系统重点实验室基金;南京理工大学科研发展基金资助项目

Robust Fault Detection Based on Neural Network Adaptive Observers

ZHOU Chuan, HU Wei-li, CHEN Qing-wei   

  1. Department of Automation, Nanjing University of Science and Technology, Nanjing 210094, China
  • Received:2002-07-14 Revised:2003-08-30 Online:2004-03-31 Published:2004-03-31

PDF

67

被引次数

26

摘要： 提出一种基于动态神经网络的不确定非线性系统鲁棒故障检测方法,该方法通过构造神经网络自适应观测器来获取反映系统故障的残差信息以进行快速的故障检测,并采用Lyapunov稳定理论证明了闭环误差系统的一致最终有界稳定性.针对某型飞机舵面故障的仿真验证了本文方法的有效性.

关键词: 动态神经网络, 自适应观测器, 故障检测

Abstract: A fault detection method based on dynamic recurrent neural networks for uncertain nonlinear system is presented in this paper. A residual information is obtained by using adaptive neural networks observers, so the system faults can be detected rapidly. The uniformly ultimately bounded stability of closed-loop error system is guaranteed by Lyapunov stability theory. Finally simulation results of a fighter's control surface failure reveal the effectiveness of this method.

Key words: dynamic neural networks, adaptive observer, fault detection

中图分类号: