Neural network based method for the automatic detection of the stator faults of the induction motor

This paper proposes a neural network based method to achieve an automatic detection of different stator faults of the induction motor. The concerned stator faults are the inter turns short circuit, phase to phase and phase to ground faults. The inputs of the feedforward multi-layer neural network are the indicators of the stator faults while its outputs are the corresponding faults. Therefore, the used indicators of faults are extracted from the symmetrical components of the stator currents which are the magnitude and the angle phase of the negative and zero sequence current. The neural network is trained by the back-propagation algorithm. A faulty simplified multiple coupled circuit model of a 1.1 kW induction motor is used to simulate the different operating conditions of the machine useful to built the data base for the training and the test procedures. The good training and test results show the efficiency of the proposed method.