Stable learning scheme for failure detection and accommodation

Author

Polycarpou, Marios M.

Author_Institution

Dept. of Electr. & Comput. Eng., Cincinnati Univ., OH, USA

fYear

1994

fDate

16-18 Aug 1994

Firstpage

315

Lastpage

320

Abstract

This paper presents a methodology for constructing automated fault diagnosis and accommodation architectures using online approximators and adaptation/learning schemes. In this framework, neural network models constitute an important class of online approximators. Changes in the system dynamics are monitored by an online approximation model, which is used not only for detecting but also for accommodating system failures. A systematic procedure for constructing nonlinear estimation algorithms and stable learning schemes is developed, and simulation studies are used to illustrate the results

Keywords

diagnostic expert systems; fault diagnosis; learning (artificial intelligence); neural nets; stability; adaptation/learning schemes; automated fault diagnosis architectures; failure accommodation; failure detection; neural network models; nonlinear estimation algorithms; online approximators; stable learning scheme; Condition monitoring; Costs; Fault diagnosis; Hardware; Mathematical model; Neural networks; Physics computing; Redundancy; Reliability engineering; Safety;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Control, 1994., Proceedings of the 1994 IEEE International Symposium on

Conference_Location

Columbus, OH

ISSN

2158-9860

Print_ISBN

0-7803-1990-7

Type

conf

DOI

10.1109/ISIC.1994.367798

Filename

367798