Comparison of Mamdani and Sugeno Fuzzy Inference Systems to Assess the Health Condition of Power Transformer

Dissolved gas analysis is an effective method for diagnosis of power transformer incipient faults. In this work, the health status of the transformer is evaluated using fuzzy logic approach. Fuzzy inference systems namely Mamdani type-1 and Sugeno type-1 available in MATLAB environment are taken to perform the task. The gases in ppm and fault levels are given as inputs to fuzzy inference system and health status of transformer is predicted. The results infer that Sugeno systems offer better prediction capability and good accuracy even for varying conditions of gas concentrations and fault levels.