Particle filtering based multiple-model approach to fault diagnosis in nonlinear stochastic systems

Author

Ping Li ; Kadirkamanathan, Visakan

Author_Institution

Dept. of Autom. Control & Syst. Eng., Univ. of Sheffield, Sheffield, UK

fYear

2001

fDate

4-7 Sept. 2001

Firstpage

1378

Lastpage

1383

Abstract

A novel approach to fault diagnosis in nonlinear stochastic systems is proposed. It is based on the particle filtering (PF) algorithm, a Monte Carlo technique based state estimation method, and the multiple model (MM) approach. The simulation results on a univariate model are provided and the fault detection and isolation performance are compared with that using the extended Kalman filter which demonstrate the effectiveness of the proposed approach.

Keywords

Monte Carlo methods; fault diagnosis; nonlinear systems; particle filtering (numerical methods); reliability theory; state estimation; stochastic systems; Monte Carlo technique; extended Kalman filter; fault detection and isolation performance; fault diagnosis; multiple-model approach; nonlinear stochastic systems; particle filtering algorithm; state estimation method; univariate model; Atmospheric measurements; Kalman filters; Mathematical model; Particle measurements; Solid modeling; Stochastic systems; Statistical approaches to fault diagnosis Nonlinear systems Stochastic systems Particle filters Bayes estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (ECC), 2001 European

Conference_Location

Porto

Print_ISBN

978-3-9524173-6-2

Type

conf

Filename

7076109