Online fault detection and isolation of nonlinear systems

Author

Chan, C.W. ; Cheung, K.C. ; Wang, Y. ; Chan, W.C.

Author_Institution

Dept. of Mech. Eng., Hong Kong Univ., Hong Kong

Volume

6

fYear

1999

fDate

1999

Firstpage

3980

Abstract

This paper describes an online fault detection scheme for a class of nonlinear dynamic systems with modelling uncertainty and inaccessible states. Only the inputs and outputs of the system can be measured. The faults are assumed to be functions of the state, instead of the output and the input of the system. A nonlinear online approximator using dynamic recurrent neural network is utilised to monitor the faults in the system. The construction and the learning algorithm of the online approximator are presented. The stability, robustness and sensitivity of the fault detection scheme under certain assumptions are analysed. An example demonstrates the efficiency of the proposed fault detection scheme

Keywords

approximation theory; computerised monitoring; fault diagnosis; learning (artificial intelligence); nonlinear dynamical systems; observers; real-time systems; recurrent neural nets; sensitivity analysis; computerised monitoring; dynamic recurrent neural network; fault detection; fault isolation; learning algorithm; nonlinear dynamic systems; nonlinear online approximator; observer; sensitivity; stability; Fault detection; Linear systems; Mechanical engineering; Monitoring; Nonlinear dynamical systems; Nonlinear systems; Recurrent neural networks; Robust stability; Robustness; Stability analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

American Control Conference, 1999. Proceedings of the 1999

Conference_Location

San Diego, CA

ISSN

0743-1619

Print_ISBN

0-7803-4990-3

Type

conf

DOI

10.1109/ACC.1999.786267

Filename

786267