Assessment of the technical condition of a transformer based on the operational parameters of its oil using the fuzzy logic method

Abstract

In this article, a mathematical model and decision-making algorithm based on the theory of fuzzy logic were developed to assess the technical condition of a transformer based on the operational indicators of its oil. In the study, the water content, acid number, amount of mechanical impurities, kinematic viscosity, density, flash point, electrical strength and dielectric loss of transformer oil were selected as the main diagnostic parameters characterizing the technical condition of the transformer. Membership functions were formed for each parameter, a fuzzy rule base was created based on expert knowledge and regulatory documents, and an integral technical condition indicator was calculated using the Mamdani inference algorithm and the centroid method. The results of the study showed that the developed model allows for a comprehensive analysis of the relationship between the diagnostic indicators of transformer oil, determining the degree of degradation of the transformer insulation system, and dividing its technical condition into the categories of "very bad", "bad", "average", "good" and "excellent". The proposed approach serves to increase the operational reliability of transformers, prevent accidents, introduce condition-based maintenance systems, and extend the service life of transformers.