Fault classification of three phase induction motors using Bi-LSTM networks

Abstract The induction motors are back bone of the modern industry and play very important role in manufacturing transportation sectors. motor faults mainly classified into internal such as inter turn short circuits , broken rotors external over load, voltage asymmetry supply voltage. identification type fault is for safe operation preventing risk machine failures. In this work, a Bidirectional Long Short Term memory networks (Bi-LSTM)-based learning methodology proposed classification Induction Motors. line voltages three phases currents considered inputs to Bi-LSTM network identifying types fault. Line current data sets six different conditions. conditions phase normal output (NO), overload (OL), (OV), under (UV), Voltage unbalance (VUB) single phasing (SP). BI-LSTM trained using Adam optimization algorithm. results obtained with compared LSTM show advantage approach.