Neural Networks based fault diagnosis of ac motors
This paper presents an Artificial Neural Network (ANN) technique to recognize the incipient faults of an AC motor such as a synchronous motor. The proposed ANN-based fault detector is developed using the Resilient Error Back Propagation (RPROP) training algorithm. The fast and reliable method f...
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2008
|
| Subjects: | |
| Online Access: | http://scholars.utp.edu.my/id/eprint/2639/ http://scholars.utp.edu.my/id/eprint/2639/1/NN_-_ac_motors_-_IEEE_ITSIM2008_-_Aug_2008.pdf |
| Summary: | This paper presents an Artificial Neural Network
(ANN) technique to recognize the incipient faults of an
AC motor such as a synchronous motor. The proposed
ANN-based fault detector is developed using the
Resilient Error Back Propagation (RPROP) training
algorithm. The fast and reliable method for multilayer
neural networks converges much faster than the
conventional back propagation algorithm. The main
causes to diagnose three major faults are investigated
and validated by adopting feed-forward back
propagation neural networks. |
|---|