A Fault Diagnosis of Oil-Filled Power Transformers Using Dissolved Gas Analysis

유중 가스 분석법을 이용한 전력용 유입 변압기의 고장 진단

This paper presents an artificial neural network approach to diagnose and detect faults in oil-filled power transformers based on dissolved gas analysis. The proposed algorithm is used to detect faults with or without cellulose involved. Several neural network topologies have been considered. Good diagnosis accuracy is obtained with the proposed approach.