The Application Of Fuzzy Neural Network Based On Genetic Algorithm To The Fault Detection And Diagnosis

FDD(Fault Detection and Diagnosis) is an important part of control system. It relates to many techniques close, such as FTC(fault tolerant control), robust control, adaptive control, intelligent control, etc. In the previous decade, FDD has greatly developed. While some new theories and techniques have been applied to it successfully, such as PCA(principle component analysis), GA(genetic algorithm),wavelet theory, -ANN (artificial neural network), fuzzy system, pattern classification, adaptive control theory, nonlinear system theory, etc.This paper applies Fuzzy Neural Network based on Genetic Algorithm to the FDD(Fault Detection and Diagnosis)of power electronic circuits. Because ANN can be used without the specific model of object, and it stores useful information as distributed manner, we usually make use of the topological structure and weights of neural network to realize nonlinear mapping, which make those weights full of meaning, also reserve the training algorithm of ANN. As it is known, we hope to get the universal best answer, so in the processing of weight training, we adopt GA to avoid the defect of BP algorithm, which is very easy to get into the local best answer. A new FDD system has been given in this dissertation. The results show that it is good to the FDD. Both the rate of lost detection and the rate of error detection get to what we want.