Title :
Fuzzy ART neural network approach for incipient fault detection and isolation in rotating machines
Author :
Roehl, N.M. ; Pedreira, C.E. ; De Azevedo, H. R Teles
Author_Institution :
CEPEL, Electr. Power Res. Center, Rio de Janeiro, Brazil
Abstract :
A neural network approach for online detection and isolation of faults in rotating machines is proposed. The methodology is based on clustering of shaft vibration monitoring data by using fuzzy ART neural networks. Fault isolation is obtained by retrieving stored associations among known physical faults and clusters. The proposed scheme is implemented to detect and isolate different operation modes in an hydro generator
Keywords :
ART neural nets; electric machines; fault diagnosis; fault location; fuzzy neural nets; hydroelectric generators; monitoring; pattern recognition; fault isolation; fuzzy ART neural network; hydrogenerator; incipient fault detection; operation modes; rotating machines; shaft vibration monitoring data clustering; Artificial neural networks; Clustering algorithms; Electrical fault detection; Fault detection; Fuzzy neural networks; Intelligent networks; Monitoring; Neural networks; Rotating machines; Shafts; Subspace constraints; Vibrations;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.488235
