Predicting transformers oil parameters

Abstract

In this paper different configurations of artificial neural networks are applied to predict various transformers oil parameters. The prediction is performed through modeling the relationship between the transformer insulation resistance extracted from the Megger test and the breakdown strength, interfacial tension, acidity and the water content of the transformers oil. The process of predicting these oil parameters statuses is carried out using two different configurations of neural networks. First, a multilayer feed forward neural network with a back-propagation learning algorithm is implemented. Subsequently, a cascade of these neural networks is deemed to be more promising. Both configurations are evaluated using real-world training and testing data and the accuracy is calculated across a variety of hidden layer and hidden node combinations. The results indicate that even with a lack of sufficient data to train the network, accuracy levels of 83.9% for breakdown voltage, 94.6% for interfacial tension, 56.4% for water content, and 75.4% for oil acidity predictions were obtained by the cascade of neural networks