Artificial Neural Network and Rough Set for HV Bushings Condition Monitoring

TL;DR

This paper develops and compares neural network and rough set models for monitoring transformer bushing conditions, demonstrating that combined models improve accuracy and training speed over individual methods.

Contribution

It introduces a hybrid approach combining MLP, RBF, and RS models with majority voting for enhanced bushing condition monitoring.

Findings

MLP outperforms RBF and RS in accuracy

RBF trains the fastest among the models

Committee model surpasses individual models in performance

Abstract

Most transformer failures are attributed to bushings failures. Hence it is necessary to monitor the condition of bushings. In this paper three methods are developed to monitor the condition of oil filled bushing. Multi-layer perceptron (MLP), Radial basis function (RBF) and Rough Set (RS) models are developed and combined through majority voting to form a committee. The MLP performs better that the RBF and the RS is terms of classification accuracy. The RBF is the fasted to train. The committee performs better than the individual models. The diversity of models is measured to evaluate their similarity when used in the committee.