Prediction of Power Transformer Fault Based on Auto Regression Model

Abstract

Dissolved gases analysis is the essence to diagnose and forecast power transformer fault. This paper utilized an Auto Regression model to predict contents of gases dissolved in power transformer oil, and adopted Akaike's Information Criterion to determine model order. Then, the prediction results of AR model are compared with results of Gray model. Finally, gray artificial immune algorithm diagnosed power transformer fault types through gases contents predicted by Auto Regression model. Experiments demonstrates that Auto Regression model has a higher accuracy than Gray Model, and the fault prediction results of the proposed algorithm are in accord with the results using real gases contents, thus , the power transformer fault prediction algorithm present in the paper is effective and reliable.