Transformer Fault Diagnosis Utilizing Rough Set and Support Vector Machine

Abstract

In this study, we are concerned with fault diagnosis of power transformer. The objective is to explore the use of some advanced techniques such as rough set (RS), support vector machine model (SVM) and quantify their effectiveness when dealing with dissolved gases extracted from power transformers. In order to increase data quality and decrease scalability of input data, we utilize the strong ability of RS theory in processing large data and eliminating redundant information, SVM is performed to separate various fault types of power transformer. As the simulation results to verify the effectiveness, the proposed method showed more improved classification results than artificial neural network (ANN).