Fault Diagnosing Of An Induction Motor Based On Signal Fusion Using One-Dimensional Convolutional Neural Network

Abstract

The detection and classification of induction motor faults using a one-dimensional convolutional neural network is discussed in this paper. A one-dimensional deep neural network is learned utilizing three-phase current and voltage signals from an induction motor system. The results of experiments show that the one-dimensional deep convolutional neural network method effectively diagnoses the induction motor conditions (Bearing fault, Rotor bar broken, short circuit stator winding 8% and 12.5 %).