| |
Induction Motor Stator Faults Diagnosis using Neural Networks
| [View]
[Download]
|
| Author(s) |
T. Orlowska-Kowalska; C. T. Kowalski |
| Abstract |
The paper deals with the diagnostic problems of the induction motors in the case of stator faults. For diagnostic purposes two kinds of neural networks were proposed: multilayer perceptron networks and self organizing Kohonen networks. Neural networks were trained and tested using measurement data of axial leakage flux and mechanical vibration spectra. The efficiency of developed neural detectors was evaluated. Feedforward NN with very simple internal structure used for the detection of fault kind gave satisfactory results, what is very important in practical realization. Experiments with Kohonen networks indicated that they could be used for initial classification of motor faults, as a introductory step before proper neural detector based on multiplayer perceptron. |
| Download |
| Filename: | EPE-PEMC2002 - T8-072 - Orlowska-Kowalska.pdf |
| Filesize: | 406.8 KB |
|
| Type |
Members Only |
| Date |
Last modified 2004-05-25 by System |
| |
 |