Automated Fault Detection and Diagnosis in Mechanical Systems
- 22 October 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews)
- Vol. 37 (6), 1360-1364
- https://doi.org/10.1109/tsmcc.2007.900623
Abstract
In this work, a fault detection method is developed based on a neural network (NN) learning model. The robust observer is designed for monitoring fault, without NN learning, when the system of concern is operating in the normal healthy mode. By comparing appropriate states with their signatures, the fault diagnosis can be carried out and the NN learning is then triggered to identify the fault function.Keywords
This publication has 9 references indexed in Scilit:
- Sensor bias fault isolation in a class of nonlinear systemsIEEE Transactions on Automatic Control, 2005
- Fault diagnosis of differential-algebraic systemsIEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans, 2001
- Computer-based monitoring and fault diagnosis: a chemical process case studyISA Transactions, 2001
- Automated fault diagnosis in nonlinear multivariable systems using a learning methodologyIEEE Transactions on Neural Networks, 2000
- Neural-network-based robust fault diagnosis in robotic systemsIEEE Transactions on Neural Networks, 1997
- Expert system framework for fault detection and fault tolerance in roboticsComputers and Electrical Engineering, 1994
- Fault diagnosis of machines via parameter estimation and knowledge processing—Tutorial paperAutomatica, 1993
- Strategies for DiagnosisIEEE Transactions on Systems, Man, and Cybernetics, 1987
- Process fault detection based on modeling and estimation methods—A surveyAutomatica, 1984