The Research Of Bayesian Network Fault Diagnosis Fusion Method For Transformer

Power transformers are among the key equipment in electrical power transmission/distribution systems, and to detect early incipient faults in transformers timely and accurately is of great significance for enabling reliable operations of power systems. On the basis of the analysis of the dissolved gas analysis of power transformers, Bayesian network, Gray system theory and evidence theory has been studied and applied to fault diagnosis of power transformer in this thesis.Bayesian network is currently one of the most effective theoretical models in the field of uncertain knowledge representation and reasoning. Bayesian classifier which can be trained and concluded from the input sample can be used to classify the data of unknown model. This paper purposes a basic probability assignment function of the modified Bayesian classifier for solving the invariance problems of basic probability assignment function in a single area. The simulation results show that the method is accurate and effective.By generating, developing and extracting the valuable information from the "part" known information, Grey system theory is a method referring to small sample, poor information uncertainty system. The basic probability assignment function of the whitenization weight function is applied into transformer fault diagnosis and some improvements are put forward in this thesis. Experiments have verified the accuracy of this method.Since the relation between characteristic gases and transformer fault are complicated and fuzzy, the results of different diagnosis techniques might be inconsistent. A fault diagnosis for power transformer based on evidence theory is proposed to combine the diagnosis results of the improved three-ratio method, Bayesian network and Grey system theory by using combination rule for conflicting evidence, and it could effectively integrate multiple diagnosis techniques. Experimental results show that the proposed fusion method could improve the reliability of transformer fault diagnosis.