Fault Diagnosis Of Power Transformer Based On Information Fusion

In order to solve problems encountered in the application of artificial intelligence in fault diagnosis of power transformer, some improved methods are presented, the main reserch work of this dissertation consists of the following parts:As Back propagation neural network is easily stacked into the minimal valve locally and causes strict demands of initial valve an EA-BPNN algorithm to optimize the initial valve of BPNN structure is presented in this dissertation. It is powerful to diagnoses the faults of power transformer in terms of the following test result.The basic ideas of information fusion are introduced and the power transformer diagnostic model based on information fusion is built, Within this diagnostic model, the dissolved gas-in-oil analysis(DGA) is combined tightly with the results of conventional electrical test of power transformers. It has shown that the model posses satisfactory capability of knowledge representation and strong solving ability to deal with uncertain facts.