Research On Fault Diagnosis Of Expert System For Turbine Generator Unit Based On Neural Network

With the online monitoring and fault diagnosis of turbine generator unit vibration as the research object as well as fault diagnosis of expert system in neural network for turbine generator unit vibration as the development object, and in combination with the real machine test in YanGuoXia hydropower plant, this paper analyses and diagnoses these experimental data whereby obtaining the conclusionwhich is of important significance for hydropower plant practice.To begin with, this paper deals with the importance of turbine generator unit fault diagnosis, and analyses the existing research states and developing trend of fault diagnosis as well as the application prospect of fault diagnosis in details. Accordingly, the vibration theory, vibration sources and the part vibration fault features of turbine generator units are analysed, sorted out and finalized so as to lay a solid foundation for the establishment of fault diagnosis expert knowledge bank. Secondly, through the analysis of the purposes and tasks of fault diagnosis expert system, this paper combines the theory and method of Neural Network with the expert system used in vibration faultIIdiagnosis of turbine generator units whereby the fault diagnosis expert system model is established. Also, this paper discusses the method to use neural network to resolve the problems of the knowledge obtaining, knowledge expression, knowledge bank maintenance and inaccurate inference in the fault diagnosis expert system. Whereby suggesting the blocking technology of neural network realized in the concrete research object梩urbine generator units. On the basis of which the open knowledge bank of turbine generator unit vibration fault diagnosis expert system is established. The pre-fabrication prototype method is used to interpret the diagnosis result by the system. At the same time, the hardware structure and realization process of system is analysed; the analysis method gearing to the subject is used to analyse the design of the fault diagnosis expert system realized with the software. And hence, Via the real machine tests of turbine generator units, the fault diagnosis expert system studied in this paper is used to diagnose and analyse testing data whereby obtaining the fault of turbine generator units in the state of rotator imbalance and suggesting that the hydropower plant should conduct dynamic balance tests after the turbine generator units matched with weight. Finally, the summary is made of the complete paper; the weak points in the system are analysed; and the follow-up work on further research is also dealt with.