A Study Of The Fault Diagnosis Expert System Based Fuzzy Neural Networks On Hydroelectric Generating Units

With the development of socialization manufacture, the capacity of hydroelectric generating units becomes larger, the automatic level of the equipments becomes higher, the structure becomes more complex, the causes resulting in the fault of hydroelectric generating units increase, and at the same time the users' demand for the quality of electric power energy becomes higher. So, it is more important to diagnose the fault of hydroelectric generating units.This paper introduces important significance of the fault diagnosis of the hydroelectric generating units, current status and tendency of the fault diagnosis of hydroelectric generating units all over the world. It also analyses the content and the method of condition monitoring and fault diagnostic system as well as its development situation. Discusses about the principal fault and fault's reason of the vibration of the hydroelectric generating units.The fault diagnosis strategies of the hydroelectric generating units are presented. Object oriented knowledge representation method is put forward to deal with the multi-hierarchy fault diagnosis structure of the hydroelectric generating units. Furthermore, fuzzy expert system is employed to representing the uncertainty knowledge of the hydroelectric generating units. Based on discussing the advantages and disadvantages of fuzzy logic system and neural network, this paper tries to integrate fuzzy logic system and neural network in the fault diagnosis of the hydroelectric generating units. The simulation results demonstrated the novelty and feasibility of this idea.