Transformer Failure Diagnosis System Of The Neural Network Based On The Feature Gases Method

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 gas content and detection method and fault attribute chassification technology.Combining the actual work, 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 and RBP neural network which suitable to the power transformer running condition and fault on-line detection, diagnosis and forecasting. We have discussed the network construction, optimization and algorithmic, and we have done the simulation experiment by the NNTOOL in the Matlab.Simulation results indicate that the dissolve gas in oil analysis approach is convenient feasible technology in order to inspect the filling oil power apparatus running condition, diagnose and forecast the fault. It maybe realizes running condition detection on-line, fault diagnosis and forecast of the power transformer.