Continual on-line training of neural networks with applications to electric machine fault diagnostics
- 13 November 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 4 (02759306) , 2224-2228
- https://doi.org/10.1109/pesc.2001.954450
Abstract
An online training algorithm is proposed for neural network (NN) based electric machine fault detection schemes. The algorithm obviates the need for large data memory and long training time, a limitation of most AI-based diagnostic methods for commercial applications, and in addition, does not require training prior to commissioning. Experimental results are provided for an induction machine stator winding turn-fault detection scheme that uses a feedforward NN to compensate for machine and instrumentation nonidealities, to illustrate the feasibility of the new training algorithm for real-time implementation.Keywords
This publication has 7 references indexed in Scilit:
- Alternatives for assessing the electrical integrity of induction motorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- An integrated, on-line, motor protection systemPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Transient model for induction machines with stator winding turn faultsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Neural network based on-line stator winding turn fault detection for induction motorsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Insulation failure prediction in AC machines using line-neutral voltagesIEEE Transactions on Industry Applications, 1998
- Instantaneous power as a medium for the signature analysis of induction motorsIEEE Transactions on Industry Applications, 1996
- Analysis of Cage Induction Motors with Stator Winding FaultsIEEE Transactions on Power Apparatus and Systems, 1985