A learning pattern recognition system using neural network for diagnosis and monitoring of aging of electrical motor

The authors propose a fault detector for an induction motor using an artificial neural network (ANN). It is a learning pattern recognition system which can diagnose faults as well as aging conditions. For the diagnosis, this system uses a frequency spectrum analysis method based on vibration conditions of the rotating machine. In the ANN, the inputs are several vibration frequencies. Outputs of artificial neural networks provide the information on the fault condition of the motor. The PDP model, which is a multilayer perceptron model with an error backpropagation learning algorithm, is used as the ANN for this diagnostic system