DocumentCode :
2828881
Title :
An intelligent sensor and actuator fault detection and isolation scheme for nonlinear systems
Author :
Talebi, H.A. ; Khorasani, K.
Author_Institution :
Amirkabir Univ. of Technol., Tehran
fYear :
2007
fDate :
12-14 Dec. 2007
Firstpage :
2620
Lastpage :
2625
Abstract :
This paper presents a robust fault detection and isolation (FDI) scheme for a general nonlinear system using a neural network-based observer. Both actuator and sensor faults are considered. The nonlinear system is subject to state and sensor uncertainties and disturbances. Two recurrent neural networks are employed to identify general unknown actuator and sensor faults. The neural network weights are updated according to a modified backpropagation scheme. Unlike many previous methods in the literature, the proposed FDI scheme does not rely on the availability of full state measurements. The stability of the overall fault detection scheme in presence of unknown sensor and actuator faults as well as plant and sensor uncertainties is shown by using Lyapunov´s direct method. The stability analysis presented imposes no restrictive assumptions or constraints on the system and/or the FDI algorithm. Magnetorquer type actuators and magnetometer type sensors that are commonly utilized in the attitude determination and control of low-Earth orbit (LEO) satellites are considered as case studies. The effectiveness of our proposed fault diagnosis strategy is demonstrated through numerical simulations.
Keywords :
Lyapunov methods; artificial satellites; attitude control; backpropagation; fault diagnosis; intelligent actuators; intelligent sensors; magnetometers; neurocontrollers; nonlinear control systems; observers; recurrent neural nets; stability; uncertain systems; Lyapunov´s direct method; actuator fault detection; attitude determination; fault isolation scheme; intelligent sensor; low-Earth orbit satellites control; magnetometer type sensors; magnetorquer type actuators; modified backpropagation scheme; neural network-based observer; nonlinear systems; numerical simulations; recurrent neural networks; robust fault detection; sensor uncertainties; stability analysis; state uncertainties; Fault detection; Fault diagnosis; Intelligent actuators; Intelligent sensors; Magnetic sensors; Neural networks; Nonlinear systems; Recurrent neural networks; Robustness; Sensor systems;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Decision and Control, 2007 46th IEEE Conference on
Conference_Location :
New Orleans, LA
ISSN :
0191-2216
Print_ISBN :
978-1-4244-1497-0
Electronic_ISBN :
0191-2216
Type :
conf
DOI :
10.1109/CDC.2007.4434839
Filename :
4434839
Link To Document :
بازگشت