Robust fault identification of a polytopic LPV system with neural network

Author

Luzar, Marcel ; Witczak, Marcin ; Mrugalski, Marcin ; Kanski, Zbigniew

Author_Institution

Inst. of Control & Comput. Eng., Univ. of Zielona Gor, Zielona Góra, Poland

fYear

2014

fDate

8-10 Oct. 2014

Firstpage

1614

Lastpage

1619

Abstract

In this paper, a discrete-time Linear Parameter-Varying (LPV) system identification method using artificial neural network is described. In particular, neural network is transformed to obtain LPV model of the non-linear system. Moreover, a novel robust fault diagnosis scheme is developed, which is based on an observer within H_∞ framework for a class of non-linear systems. The effectiveness of the proposed approach is illustrated by the faults estimation in the multi-tank system.

Keywords

H^∞ control; discrete time systems; neurocontrollers; nonlinear systems; robust control; time-varying systems; LPV model; LPV system identification method; artificial neural network; discrete-time linear parameter-varying system identification method; fault estimation; multitank system; nonlinear systems; polytopic LPV system; robust fault diagnosis scheme; robust fault identification; Computational modeling; Data models; Fault diagnosis; Neural networks; Observers; Robustness; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control (ISIC), 2014 IEEE International Symposium on

Conference_Location

Juan Les Pins

Type

conf

DOI

10.1109/ISIC.2014.6967628

Filename

6967628