Standardization of DGA interpretation techniques using fuzzy logic approach

Abstract

Dissolved gas analysis (DGA) of transformer oil is one of the most effective power transformer condition monitoring tools. There are many interpretation techniques for DGA results. However, all of these techniques rely on personnel experience more than standard mathematical formulation. As a result, various DGA interpretation techniques do not necessarily lead to the same conclusion for the same oil sample. DGA interpretation is yet a challenge in the power transformer condition monitoring research area. To alleviate this issue, this paper introduces a fuzzy logic approach to help in standardizing DGA results quantification and classification using various interpretation techniques such as key gas, Rogers ratio, IEC ratio, Doernenburg and Duval triangle methods. In this context, DGA results for 2000 oil samples have been collected from different transformers of different ratings, life span and operating conditions. Traditional DGA interpretation techniques are used to analyze the results which are then compared with the results of the fuzzy logic models. Results show that the fuzzy logic models enhance the consistency among all current interpretation techniques and can eliminate the need for expert personal to interpret DGA results.