Interpretable Detection of Partial Discharge in Power Lines with Deep Learning

TL;DR

This paper introduces an end-to-end convolutional neural network framework for detecting partial discharges in power lines, offering robustness against noise and interpretability through pulse activation maps, improving over traditional feature-based methods.

Contribution

It presents a novel CNN-based approach that eliminates the need for feature extraction and introduces pulse activation maps for interpretability in PD detection.

Findings

Robust PD detection without feature engineering

Pulse activation maps enhance interpretability for domain experts

Framework outperforms traditional methods on public dataset

Abstract

Partial discharge (PD) is a common indication of faults in power systems, such as generators, and cables. These PD can eventually result in costly repairs and substantial power outages. PD detection traditionally relies on hand-crafted features and domain expertise to identify very specific pulses in the electrical current, and the performance declines in the presence of noise or of superposed pulses. In this paper, we propose a novel end-to-end framework based on convolutional neural networks. The framework has two contributions. First, it does not require any feature extraction and enables robust PD detection. Second, we devise the pulse activation map. It provides interpretability of the results for the domain experts with the identification of the pulses that led to the detection of the PDs. The performance is evaluated on a public dataset for the detection of damaged power lines. An ablation study demonstrates the benefits of each part of the proposed framework.