A fault prediction approach for power transformer based on support vector machine

Power transformer is one of the most expensive component of electrical power plants and the failures of such transformer can result in serious power system issues, so fault forecasting for power transformer is very important to insure the whole power system runs normally. In this paper, a novel fault prediction approach for power transformer based on Support Vector Machine (SVM) is presented using data of Dissolved Gas Analysis (DGA). Moreover, by comparing with the traditional method's like the grey prediction algorithm, the prediction precision for power transformer is improved using our scheme and the proposed SVM approach works well especially for the case of limited data set.