Terabyte-Scale Dataset for Partial Discharge Detection in Covered Conductors via Contact Galvanic Method

The dataset designed for the detection of partial discharges in transmission power lines using covered conductors (CCs) through a contact galvanic method, sourced from real environments across 23 different stations in various locations. Encompassing over a terabyte of data, it documents a wide array of fault scenarios, including contacts with and without ground and conductor breakdowns. Though partially introduced in a Kaggle competition (only 3% of data), its full extent is disclosed here for the first time. The dataset is distinguished by its rich, imbalanced distribution across seven classes, derived from signals processed via a sophisticated voltage-based method, and supplemented with extracted features to aid analysis. Its scale, detailed labeling, and real-world basis offer unparalleled opportunities for developing machine learning algorithms aimed at fault detection. This contribution holds vast potential for reuse in electrical engineering research focused on enhancing power distribution network reliability and safety, particularly in the context of predictive maintenance and understanding partial discharge behaviors.本数据集专为通过接触电化检测法（contact galvanic method）检测包覆导线（covered conductors，CCs）输电线路的局部放电而设计，数据采集自全球23个不同站点的真实运行环境。数据集体量逾1太字节（TB），涵盖接地接触、非接地接触及导线击穿等多种故障场景。尽管该数据集的部分内容曾在Kaggle竞赛中亮相（仅占总数据量的3%），但其完整版本首次在此公开。该数据集包含七大类别，且类别分布不均衡、样本覆盖全面，其原始信号通过先进的电压处理方法生成，并补充了用于辅助分析的特征提取结果。本数据集的大规模体量、精细化标注以及真实场景采集的特性，为开发面向故障检测的机器学习算法提供了得天独厚的研究条件。该数据集可为旨在提升配电网络可靠性与安全性的电气工程研究提供极具价值的复用潜力，尤其在预测性维护以及局部放电机理研究领域应用前景广阔。