A New Approach to Identify Power Transformer Criticality and Asset Management Decision 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. There are many interpretation techniques for DGA results. However, all of these techniques rely on personnel experience more than standard mathematical formulation and significant number of DGA results fall outside the proposed codes of the current methods and cannot be diagnosed by these methods. To overcome these limitations, this paper introduces a novel approach using Gene Expression Programming (GEP) to help in standardizing DGA interpretation techniques, identify transformer critical ranking based on DGA results and propose a proper maintenance action. DGA has been performed on 338 oil samples that have been collected from different transformers of different rating and different life span. Traditional DGA interpretation techniques are used in analyzing the results to measure its consistency. These data are then used to develop the new GEP model. Results show that all current traditional techniques do not necessarily lead to the same conclusion for the same oil sample. The new approach using GEP is easy to implement and it does not call for any expert personnel to interpret the DGA results and to provide a proper asset management decision on the transformer based on DGA analysis.