高压电缆行波信号智能诊断训练数据

该数据集以高压电缆运行中的行波信号为载体，结合客户在石油、化工、机场、钢铁等关键行业的实际运行环境，通过部署高精度传感器采集电缆在正常运行及潜在故障状态下的行波信号。对原始信号进行去噪、归一化、特征提取、分类标注等预处理后，形成高质量的结构化时序数据集。经训练后的模型可集成至边缘计算平台或云服务系统，实现对高压电缆绝缘劣化、局部放电、接地故障等隐患的自动识别、早期预警与精确测距功能，显著提升电缆运维智能化水平。This dataset takes traveling wave signals generated during the operation of high-voltage cables as the data carrier, and integrates the actual operating environments from customers in key industries such as petroleum, chemical, airport and steel manufacturing. High-precision sensors are deployed to collect traveling wave signals of cables under both normal operation and potential fault conditions. After preprocessing the original signals through denoising, normalization, feature extraction, classification annotation and other steps, a high-quality structured time-series dataset is constructed. The trained model can be integrated into edge computing platforms or cloud service systems to realize automatic identification, early warning and accurate distance measurement for hidden hazards including high-voltage cable insulation degradation, partial discharge and grounding faults, thereby significantly improving the intelligent operation and maintenance level of power cables.

搜集汇总

背景与挑战

背景概述

该数据集是用于高压电缆智能诊断的训练数据，通过采集电缆运行中的行波信号，并经过去噪、特征提取等预处理，形成结构化时序数据，旨在训练模型自动识别绝缘劣化、局部放电等故障隐患，实现早期预警和精确测距。它主要应用于高压电缆的智能运维和故障预测场景，支持实时监控和风险评估，有助于减少人工巡检、降低运维成本，推动电力系统向数字化和预防性维护转型。