Identification of three phase induction motor incipient faults using neural network

The induction motors are most widely used motors in industrial, commercial and residential sectors because of enormous merits of these over other types of available electrical motors. These motors work under various operating stresses, which deteriorate their motor conditions giving rise to faults. The early detection of these deteriorating conditions in incipient phase and its removal/correction is very necessary for the prevention of any external faults/failure of induction motors reducing repair costs and motor outage time. Fault detection using analytical methods is not always possible because it requires a perfect knowledge of the motor model. The artificial neural network techniques are rather easy to develop and to perform. These networks can be applied when the information about the system is obtained from measurements, which later can be used in the training procedures of the neural networks. Neural detectors can be designed from simulation or experimental tests. In the present paper the applicability/feasibility of artificial neural network (ANN) technique for the detection and identification of incipient faults in an induction motor has been explored. Radial basis function (exact fit) approach has been used for ANN training and test. The applicability of the graphical user interface (GUI) of neural network tool box under Matlab environment has been explored in this paper. The various types of faults have been considered. Three phase instantaneous voltages and currents are utilized in proposed approach. Simulated fault current and voltage data have been used for testing of trained network.