Prediction of Transformer Furan Levels

Abstract

In this letter, the ranges of furan content in oil in power transformers are predicted using measurements of oil tests, such as breakdown voltage, acidity, water content, and dissolved gas analysis. Predictive models based on machine-learning techniques are trained and tested to estimate the furan level. A prediction accuracy of 90% is achieved when using k-nearest neighbors as the classification model with a wrapper method as the feature selection technique.