Nonlinear learning approach to robust fault diagnosis

Author

Vemuri, A.T. ; Polycarpou, M.M.

Author_Institution

Dept. of Engine & Vehicle Res., Southwest Res. Inst., San Antonio, TX, USA

fYear

1999

fDate

Aug. 31 1999-Sept. 3 1999

Firstpage

4387

Lastpage

4392

Abstract

This paper presents an overview of a learning methodology for detecting and diagnosing faults in nonlinear dynamic systems. The main idea behind this approach is to monitor the plant for any off-nominal behavior due to faults utilizing on-line approximators. In the presence of a failure, the on-line approximator can be used as an estimate of the nonlinear fault function for fault diagnosis purposes. Furthermore, during the initial stage of monitoring, the learning capabilities of the on-line approximator can be used to learn the modeling errors, thereby enhancing the robustness properties of the fault diagnosis scheme.

Keywords

approximation theory; fault diagnosis; learning systems; nonlinear control systems; nonlinear dynamical systems; robust control; fault detection; learning capabilities; learning methodology; modeling errors; nonlinear dynamic systems; nonlinear fault function; nonlinear learning approach; off-nominal behavior; on-line approximators; plant monitoring; robust fault diagnosis; robustness properties; Adaptation models; Approximation algorithms; Approximation methods; Fault diagnosis; Mathematical model; Robustness; Uncertainty; learning algorithm; nonlinear fault diagnosis; on-line approximation;

fLanguage

English

Publisher

ieee

Conference_Titel

Control Conference (ECC), 1999 European

Conference_Location

Karlsruhe

Print_ISBN

978-3-9524173-5-5

Type

conf

Filename

7100024