Intelligence Maintenance of Electromotor with Self Organize Map network (SOM)

The technical meaning of maintenance involves functionalchecks, servicing, repairing or replacing of necessarydevices, equipment, machinery, building infrastructure,and supporting utilities in industrial, business,governmental, and residential installations. A selforganizingmap (SOM) or self-organizing featuremap (SOFM) is a type of artificial neural network (ANN)that is trained using unsupervised learning to produce alow-dimensional (typically two-dimensional), discretizedrepresentation of the input space of the training samples,called a map, and is therefore a method todo dimensionality reduction. In this study, self-organizingMaps neural network is used to classify faultsElectromotor and the SOM could accurately the faultclassify. The classification accuracy with SOM network is92.5%.

Keywords:

Maintenance , Electromotor , FFT spectrum , Self-Organize Map Neural Network