Application Of Fault Forecast Of Turbo-generator Unit Based On Wavelet Neural Network

In recent years, research on Wavelet neural networks (WNN) has made great progress and research on the application of WNN has been conducted in almost every field. This dissertation makes an intensive study on the application of networks to steam turbine.In chapter one the history, status and development of the fault predicting for turbo generator units are described. It also deals with the contents of the research work of the project.In chapter two the theory of Wavelet Transform and Artificial neural networks are introduced in brief. And the theory of WNN is also introduced. Because of the insufficiency of WNN, an improved algorithm is proposed. At the same time the theory of the fault diagnosis means based upon vibration spectrum and fuzzy fault diagnosis are introduced.The chapter three is my paper emphasis. WNN's established process and how to select its relevant parameter are introduced. Finally, by means of using simulated data of the faults of steam turbines, the predictive performance of WNN is checked. At the same time the fuzzy diagnose is applied into the fault forecast.In chapter four the function, structure and concrete realization course of the software for predicting system are introduced.In the last chapter of this dissertation, the conclusion and outlook of the research work are given. Some problems which need further research are pointed out.