Fuzzy and Multilayer Perceptron for Evaluation of HV Bushings

TL;DR

This paper compares fuzzy set theory and neural networks for diagnosing high voltage bushing conditions using dissolved gas analysis, demonstrating both methods achieve around 10% error and aiding maintenance decisions.

Contribution

It introduces the application of fuzzy set theory to bushing diagnosis and compares its performance with neural networks in accuracy and efficiency.

Findings

Both methods diagnose with 10% error

Fuzzy theory helps classify bushing degradation

Neural networks also effective in diagnosis

Abstract

The work proposes the application of fuzzy set theory (FST) to diagnose the condition of high voltage bushings. The diagnosis uses dissolved gas analysis (DGA) data from bushings based on IEC60599 and IEEE C57-104 criteria for oil impregnated paper (OIP) bushings. FST and neural networks are compared in terms of accuracy and computational efficiency. Both FST and NN simulations were able to diagnose the bushings condition with 10% error. By using fuzzy theory, the maintenance department can classify bushings and know the extent of degradation in the component.