Application Research of Immune Neural Network on Motor Fault Diagnosis

Motor fault diagnosis methods are crucial in acquiring safe and reliable operation in motor drive systems. In this paper, we propose a hybrid algorithm for motor fault diagnosis based on the combination of artificial immune system (AIS) and artificial neural network (ANN). The artificial immune algorithm (AIA) for data clustering is employed to adaptively choose the amount and location of the hidden layer centers of the radial basis function (RBF) neural network. The simulation experiment results show that the proposed algorithm for determining RBF neural network structure is more effective than random initialization and k-means center selection algorithms. It is implemented into an application of motor fault diagnosis; the speed and accuracy of diagnosis are significantly improved.