Transformer Incipient fault prediction using Support Vector Machine (SVM)

Abstract

The power transformer is an important link in the power system. Utilities will face a huge loss if a fault occurs transformer. The outage can cause loss to the industry sector. Transformer incipient fault can be predicted using Dissolved Gas Analysis (DGA) based on gas ratios. The current work is an effort to use SVM to predict transformer incipient fault more precisely. DGA data of various transformer oil samples were collected and analyzed to select the best SVM kernel function and kernel factor to be used and to observe the prediction accuracy.