The detection, diagnosis, and accommodation of system failures or degradations is becoming increasingly more important in modern engineering problems. This paper presents a general framework for constructing automated fault diagnosis and accommodation architectures using on-line approximators and adaptation/learning schemes. In this framework, neural network models constitute an important class of on-line approximators. Changes in the system dynamics are monitored by an on-line approximation model, which is used not only for detecting but also for accommodating failures. A systematic procedure for constructing nonlinear estimation algorithms and stable learning schemes is developed and illustrated by a simulation example.
An On-Line Approximation Approach to Fault Monitoring, Diagnosis and Accommodation
Sae Technical Papers
Aerospace Atlantic Conference & Exposition ; 1994
01.04.1994
Aufsatz (Konferenz)
Englisch
An On-Line Approximation Approach to Fault Monitoring, Diagnosis and Accommodation
British Library Conference Proceedings | 1994
|Thruster fault diagnosis and accommodation for open-frame underwater vehicles
Tema Archiv | 2004
|On-line sensor fault detection, isolation, and accommodation in automotive engines
Tema Archiv | 2003
|Adaptive Control of AUV: Fault Accommodation
British Library Conference Proceedings | 1995
|