Application of SVM and KNN to Duval Pentagon 1 for Transformer Oil Diagnosis

The carried out investigations deal with the application of machine learning algorithms to Duval Pentagon 1 graphical method for the diagnosis of transformer oil. In fact, combined to graphical methods, pattern recognition aims to may complement. For this purpose, we have used the Support Vector Machine (SVM) and the K-Nearest Neighbor (KNN) algorithms combined to the Duval method. The SVM parameters have been optimized with the Particle Swarm Optimization (PSO). Inspired from IEC and IEEE, five classes namely PD, D1, D2, T1&T2, and T3 have been adopted. The combined algorithms were verified using 155 samples from IEC TC 10 and related databases. We found that KNN, SVM may complement the Duval Pentagon 1 diagnosis method.