Fuzzy logic approach for power transformer asset management based on dissolved gas-in-oil analysis

Abstract

Dissolved gas analysis (DGA) of transformer oil is one of the most effective power transformer condition monitoring tools which can be facilitated to determine transformer criticality ranking and hence identifying a suitable condition-based asset management decision. There are many interpretation techniques for DGA results however all current techniques rely on personnel experience more than analytical formulation. As a result, the current techniques do not necessarily lead to the same conclusion for the same oil sample. A significant number of DGA results fall outside the proposed codes of the current based-ratio methods and cannot be diagnosed by these methods. Moreover, ratio methods fail to diagnose multiple fault conditions due to the mixing up of produced gases. To overcome these limitations, this paper introduces a fuzzy logic approach to aid in standardizing DGA interpretation techniques, identify transformer critical ranking and provide a suitable asset management decision based on DGA analysis. The approach relies on integrating all existing DGA interpretation techniques into one expert prototype model. DGA results of 338 oil samples of pre-known fault condition that are collected from different transformers of different rating and different life span are used to establish the model which is developed based on the consistency of various traditional DGA interpretation techniques that are currently used by various utilities and chemical laboratories worldwide.