Fuzzy Controller vs. Classical Methods for Determining the Degree of Polymerization

Abstract

This paper shows a fuzzy logic-based method for determining the degree of polymerization of the solid insulation of a transformer, taking into account the 2-FAL (2-furfuraldehyde) content. The proposed method generates information on the “health” condition of the transformer, with a high precision degree. The proposed system is based on two fuzzy-type controllers, and for each input/output of them it is defined a type of membership functions, triangle and trapezoid for a better response of analysis. The obtained results were compared to the results got by classical methods applied for the same 2-FAL content. For verifying the precision and accuracy, the proposed method was applied on more than a hundred of samples subjected to verification.