Dynamic system failure detection and diagnosis employing sliding mode observers and fuzzy neural networks

Author

Caminhas, Walmir M. ; Takahashi, Ricardo H C

Author_Institution

Dept. of Electr. Eng., Univ. Fed. de Minas Gerais, Belo Horizonte, Brazil

Volume

1

fYear

2001

fDate

25-28 July 2001

Firstpage

304

Abstract

A strategy for dynamic system failure detection and diagnosis is proposed, based on sliding mode observers, employed for residual generation with discrimination among the error subspaces, and a fuzzy neural network used for pattern classification. A control reconfiguration scheme is proposed, employing both the fault diagnosis information and the robust observer generated data. The resulting structure has been evaluated in a simulated D.C. electric drive

Keywords

DC machines; digital simulation; fault diagnosis; fuzzy neural nets; neurocontrollers; observers; pattern classification; power system simulation; variable structure systems; control reconfiguration scheme; dynamic system failure detection; dynamic system failure diagnosis; error subspaces; fault diagnosis information; fuzzy neural network; pattern classification; residual generation; robust observer generated data; simulated DC electric drive; sliding mode observers; Fault detection; Fault diagnosis; Fuzzy control; Fuzzy neural networks; Fuzzy systems; Integrated circuit modeling; Neural networks; Observers; Pattern classification; Sliding mode control;

fLanguage

English

Publisher

ieee

Conference_Titel

IFSA World Congress and 20th NAFIPS International Conference, 2001. Joint 9th

Conference_Location

Vancouver, BC

Print_ISBN

0-7803-7078-3

Type

conf

DOI

10.1109/NAFIPS.2001.944269

Filename

944269