NEURAL NETWORK AIDED ON-LINE DIAGNOSTICS OF INDUCTION MACHINE STATOR FAULTS

A Multy Layer Perceptron Neural Network able to recognize inter-turn short-circuits in the stator of induction machines is presented. The network is inserted in an on-line diagnostic system which utilizes the machine voltages and currents as input signals. The current computed by a faulted machine models are analyzed with the aim to evidence the variables more suitable to characterize the short circuit's effects. These variables, properly normalized, are the input data sets for the learning process of the network, which is therefore applicable to a class of induction machines.