Power Transformer Fault Diagnosis by Using the Artificial Immune Support Vector Machines

Dissolved gas analysis is an effective and important method for power transformer fault diagnosis. In order to improve the diagnostic accuracy of power transformer fault, the paper presents a method of hybrid intelligent algorithm of immune support vector machines. Considering the compactness characteristics of dissolved gas analysis data the achieved samples are pre-selected with the immune clustering analysis speed up the of the model parameters determination, the Support Vector Machine is used for Transformer Fault Diagnosis, and the grid search method based on cross-validation is chosen to determine model parameters. Comparison results show that the precision of fault diagnosis can be evidently improved.