Model-based incipient fault diagnosis - multi-step neuro-predictors and multiresolution signal processing
Authors:
- 25 June 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 317-322 vol.1
Abstract
Timely detection and diagnosis of incipient faults is desirable for online condition assessment purposes. In this paper, a model-based fault diagnosis system is developed for induction motors, using recurrent neural networks for multistep transient response prediction and multiresolution signal processing for nonstationary signal feature extraction. The proposed diagnosis system uses only measured motor terminal currents and voltages, and motor speed. The effectiveness of the diagnosis system is demonstrated through staged motor faults of electrical and mechanical origin. Scaling of the diagnosis system to machines with different power ratings is demonstrated with data from 2.2 kW, 373 kW and 597 kW induction motors.Keywords
This publication has 9 references indexed in Scilit:
- Multi-step-ahead prediction using dynamic recurrent neural networksNeural Networks, 2000
- Wavelet packet feature extraction for vibration monitoringIEEE Transactions on Industrial Electronics, 2000
- New results on recurrent network training: unifying the algorithms and accelerating convergenceIEEE Transactions on Neural Networks, 2000
- An adaptive statistical time-frequency method for detection of broken bars and bearing faults in motors using stator currentIEEE Transactions on Industry Applications, 1999
- AI techniques in induction machines diagnosis including the speed ripple effectIEEE Transactions on Industry Applications, 1998
- Machinery Diagnosis Based on Wavelet PacketsJournal of Vibration and Control, 1997
- Broken rotor bars: their effect on thetransient performanceof induction machinesIEE Proceedings - Electric Power Applications, 1996
- Motor bearing damage detection using stator current monitoringIEEE Transactions on Industry Applications, 1995
- Application of the recurrent multilayer perceptron in modeling complex process dynamicsIEEE Transactions on Neural Networks, 1994