Abstract
Power transformer is the key apparatus at the transformer substation, its working safe and reliability relate to the safety and stabilization of power system directly. Therefore, it has practical significance to effective inspect the running condition of transformer, diagnose and predict the transformer fault.
This paper is based on a lot of references, system overview the fault processing of the power transformer, the principle of gerneration characteristic gas, corresponding relationship between the different kinds of fault and different kinds of characteristic.
Base on analysis the relationship between the dissolving gas content in oil and different kinds of faults, making use of the technology of gas phase color spectrum sample data of the characteristic gas content in oil. Then these data samples become to the learning and training characteristic vecter matrix of the artifial neural network .Making the most of the paralleling processing, learing,memorization,nonlinearity mapping,adaptation ability and robustness etc of the artifial neural network,constructing the fault characteristic gas diagnosis system of the power transformer based on the artifial neural network. Selecting and training the BP neural network .
According to the transformer fault gases and the fault types, a type of 5-12-5 BP Neural Network model for transformer fault diagnosis is established. After training and fault diagnosing, the model's fault diagnosis accuracy is above 90%,which shows that the model is proper, feasible and correct for the transformer fault diagnosis.
Key words: Power Transformer; Artificial Neural Network; Fault Diagnosis; Network Convergence Speed