Deterministic learning and fault diagnosis for nonlinear oscillation system

Author

Chen, Tianrui ; Wang, Cong

Author_Institution

Coll. of Autom. & Center for Control & Optimization, South China Univ. of Technol., Guangzhou

fYear

2008

fDate

25-27 June 2008

Firstpage

3654

Lastpage

3659

Abstract

The diagnosis of faults is one of the important tasks in engineering systems. In this paper, based on the recent results on deterministic learning (DL) theory and rapid dynamical pattern recognition, a rapid fault diagnosis scheme is proposed for nonlinear oscillation systems. Firstly, a neural network bank for fault detection and isolation (FDI) is established through DL. Secondly, a mechanism for rapid FDI is presented, by which a fault occurred can be detected and isolated by patten recognition. Simulation studies are included to demonstrate the effectiveness of the proposed approach.

Keywords

fault diagnosis; learning (artificial intelligence); neural nets; nonlinear systems; oscillations; pattern recognition; deterministic learning theory; engineering systems; fault detection and isolation; neural network bank; nonlinear oscillation system; patten recognition; rapid dynamical pattern recognition; rapid fault diagnosis scheme; Automation; Fault detection; Fault diagnosis; Mathematical model; Neural networks; Nonlinear dynamical systems; Nonlinear systems; Parameter estimation; Pattern recognition; Systems engineering and theory; Fault detection and isolation; deterministic learning; dynamic pattern recognition; nonlinear oscillation systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control and Automation, 2008. WCICA 2008. 7th World Congress on

Conference_Location

Chongqing

Print_ISBN

978-1-4244-2113-8

Electronic_ISBN

978-1-4244-2114-5

Type

conf

DOI

10.1109/WCICA.2008.4593508

Filename

4593508