A review of intelligent diagnostic methods for condition assessment of insulation system in power transformers

Incipient fault diagnosis of a power transformer is greatly influenced by the condition assessment of its insulation system specifically oil/paper insulation. In recent times, a number of intelligent methods based on AI techniques, Artificial Neural Network and Fuzzy Logic have been used to predict incipient faults in a power transformer based on its insulation studies under various kinds of stresses. This paper focuses on the different intelligent methods which have led to the development of an expert system based on Dissolved Gas Analysis (DGA) for on-line condition monitoring of power transformers.