An Expert System for Power Transformer Fault Diagnosis Using Advanced Generalized Stochastic Petri Net

Abstract

Power transformers are considered as one of the essential elements in electrical networks. Power transformer fault diagnosis and repair is a complex task that includes many possible types of faults and demands special trained personnel. Any failure in these equipments directly reduces network reliability and increases maintenance costs. The paper mainly investigates fault diagnosis of power transformer by using Advanced Generalized Stochastic Petri Net (AGSPN) technology. AGSPN is used for accurately fault diagnosis in power transformer when some incomplete and uncertain alarm information of protective relays. After reviewing the AGSPN theory, the models of fault diagnosis for power transformer are built. Simulation results for the most common types of transformer faults (short circuit, insulation failure, oil leakage and overloading) are presented. The obtained results are ultimately interesting and applicable for maintenance and fault diagnosis engineers to quickly fault diagnosis on the scene. Finally, the proposed method can easily be adapted to different power system elements.