Fault Detection for Covered Conductors With High-Frequency Voltage Signals: From Local Patterns to Global Features

TL;DR

This paper introduces a novel machine learning approach utilizing high-frequency voltage signals and clustering techniques to detect early-stage faults in covered conductors, achieving state-of-the-art real-time disturbance detection performance.

Contribution

It presents an innovative pulse shape characterization method and a machine learning model that outperforms existing solutions in fault detection for covered conductors.

Findings

Model outperforms Kaggle competition winner

Achieves high accuracy in early fault detection

Provides real-time disturbance detection in the field

Abstract

The detection and characterization of partial discharge (PD) are crucial for the insulation diagnosis of overhead lines with covered conductors. With the release of a large dataset containing thousands of naturally obtained high-frequency voltage signals, data-driven analysis of fault-related PD patterns on an unprecedented scale becomes viable. The high diversity of PD patterns and background noise interferences motivates us to design an innovative pulse shape characterization method based on clustering techniques, which can dynamically identify a set of representative PD-related pulses. Capitalizing on those pulses as referential patterns, we construct insightful features and develop a novel machine learning model with a superior detection performance for early-stage covered conductor faults. The presented model outperforms the winning model in a Kaggle competition and provides the state-of-the-art solution to detect real-time disturbances in the field.