Estimation of Degree of Polymerisation and Residual Age of Transformers Based on Furfural Levels in Insulating Oil Through Generalized Regression Neural Networks

摘要

Furfural Analysis and Degree of Polymerisation measurements give a measure of the degradation of paper insulation in transformers. These in turn relate to the ageing of transformers. Independent analysis of each of these chemical parameters gives an idea of the residual age of a transformer. But there have been no specific standards established to determine the ageing in transformers. In this paper, there is an attempt to estimate/predict the Degree of Polymerisation and the residual age of a transformer using Artificial Neural Networks given the Furfural component in oil.