Study On Fault Diagnose Of Eletromotor Based On Neural Network Expert System

In this paper, the classical vibration and stator current faults of the AC electromotor under the practical circumstance are lifted and analyzed, the characters of vibration and stator current faults are studied in detail, the corresponding repository of the AC electromotor is also listed, it is the base of studying the fault diagnose on AC electromotor.On the base of the studying traditional Expert system, a new Expert systemmode on the fault diagnose of AC electromotor ------ the Neural network Expertsystem is put forward, it will conquer the limitation of the traditional Expert system, such as can not self-study, self-adaption.The signals of vibration, current and frequency are deal with to reflect the randomicity and uncertainty of the fault freely. In this system, the BP and Kohonen neural network are selected to capture the information. The modes of the neural network are used to express the knowledge, so the superiority of self-study of Neural network can be used sufficiently. The knowledge in traditional Expert system is expressed by a kind data structure. On contrast to the traditional Expert system, the new method can distribute the information of repository to the value of weight and threshold of the Neural network, the knowledge of expert can be expressed preferably.During the studying Expert system, the very Neural network must be created firstly, then it should be trained, when the reach precision that we need, we can input the signal to diagnose fault. The practical diagnose proved that our method is correct and precede the traditional Expert system.