Innovative Approach for Detecting Early-Stage Partial Discharges in Instrument Transformers via Ultrasound and Random Forest Analysis

Abstract

This article introduces a novel technique for detecting and classifying Partial Discharges in Instrument Transformers, addressing the gradual breakdown of external insulation in high-voltage electrical equipment through ultrasound measurements. The use of hand-held probe-microphones for ultrasonic sensing gains prominence for its versatility and online diagnostic capabilities. The proposed method combines insights into partial discharge types and the pollution level within the equipment, thereby transforming ultrasonic readings into useful information and facilitating informed decision-making. Laboratory tests simulate real-world conditions to which current and voltage transformers of 145 kV and 245 kV are subjected. These tests result in ultrasonic and apparent charge measurements, also known as Phase-Resolved Partial Discharges (PRPD). A random forest model achieves over 92 % accuracy in classifying ultrasonic signals into eight class: normal, light partial discharge, light corona, corona, light superficial, light saline pollution, moderate saline pollution and heavy saline pollution; enhancing the understanding and predictive maintenance of instrument transformers.