Neuro-fuzzy algorithms for power transformers diagnostics

Abstract

There are a number of parameters and methods available for condition monitoring and diagnostic of a power transformer insulation. In this paper we concentrate on a few of them. One of the parameters, which becomes more and more vital for diagnostics of the integrity of a power transformer, is the moisture content of insulation system. Migration of moisture from oil to paper insulation is a very complex, nonlinear with many uncertainties process. The adaptive neuro-fuzzy system identification is applied to predict moisture characteristics of oil. The comparison of the measured and predicted values of average moisture content in paper-oil insulation system is presented. The accurate evaluation of moisture content is extremely important when it is necessary to determine the dryness of the solid insulation during both the factory drying process and refurbishment of the transformer in field. The dry-out termination criteria based on the measurement of dielectric characteristics and classification of the dryness state by using the neuro-fuzzy pattern clustering is suggested for this purpose.