ANN Based Age Estimation of In-Service Transformer Oil Samples

Abstract

The mineral oil or the transformer oil, the main ingredient of power transformer acts as an insulating and cooling agent. Some of the important oil characteristics like viscosity, specific gravity, flash point, oxidation stability, total acid number, breakdown voltage, dissipation factor, volume resistivity and dielectric constant are indicative of its insulating property that deteriorates during in- service period with respect to time. Some of the properties show correlation with service aging of the oil. Six properties such as moisture content, resistivity, tan delta, interfacial tension and flash point have been considered. The data for the six properties with respect to age, in days, has been taken from literature, whereby samples of ten working power transformers of 16 to 20 MVA installed at different substations in Punjab, India have been considered. This paper aims at developing an ANN (Artificial Neural Network) model for estimating the age of in service transformer oil samples. The model uses the six properties as inputs and age as target. The most popular ANN architecture for such non linear problem is a multi layer feedforward network employing back propagation algorithm which is simulated for estimating the age of unknown samples of transformer oil.