| 引用本文: | 柯 亮,李 波,廖 凯,等.基于XGBoost的配电网高阻接地故障检测方法[J].电力系统保护与控制,2024,52(6):88-98.[点击复制] |
| KE Liang,LI Bo,LIAO Kai,et al.High impedance fault detection method in a distribution network based on XGBoost[J].Power System Protection and Control,2024,52(6):88-98[点击复制] |
|
| 摘要: |
| 配电网高阻接地故障具有电气量微弱、与正常运行工况相似等特点，因此难以检测。针对传统指标阈值法常由经验整定，在复杂环境下适应性较差、灵敏性不足等问题，提出一种基于极端梯度提升(extreme gradient boosting, XGBoost)的配电网高阻接地故障检测方法，以避免复杂的阈值整定。首先，通过建立10 kV中压配电系统高阻接地故障的等效模型，获取高阻接地故障和正常运行工况的零序电流数据。然后，在对数据进行归一化处理的基础上，利用XGBoost直接从原始量测信息中学习其与高阻接地故障的映射关系，构建高阻接地故障检测模型，以降低因特征提取产生的误差。最后，大量仿真结果表明，所提方法对高阻接地故障检测具有较好的灵敏性和速动性，并且在噪声和数据缺失等情况下表现出较强的泛化能力。 |
| 关键词: 配电网 高阻接地故障 故障检测 零序电流 XGBoost |
| DOI：10.19783/j.cnki.pspc.231322 |
| 投稿时间：2023-10-11修订日期：2023-12-25 |
| 基金项目:国家电网有限公司总部管理科技项目资助(5400- 202255150A-1-1-ZN) |
|
| High impedance fault detection method in a distribution network based on XGBoost |
| KE Liang1,LI Bo1,LIAO Kai1,TAN Yunyao1,JIA Yizhen1,DUAN Qing2,SHA Guanglin2 |
| (1. School of Electrical Engineering, Southwest Jiaotong University, Chengdu 611756, China;
2. China Electric Power Research Institute, Beijing 100192, China) |
| Abstract: |
| In distribution networks, a high impedance fault (HIF) exhibits weak characteristics, often indistinguishable from normal disturbances, making their detection challenging. Traditional indicator threshold methods, which are empirically calibrated, suffer from poor adaptability and lack sensitivity when confronted with complex environments. To address these limitations, a novel method for detecting HIF in distribution networks based on extreme gradient boosting (XGBoost) is proposed. This method avoids the complex threshold tuning. First, an equivalent model of a 10 kV medium-voltage distribution system with HIF is established to obtain zero-sequence current data for both HIF and normal disturbances. On the basis of data normalization, XGBoost is employed to directly learn the mapping relationship between the raw measurement information and the HIF from the original data, thereby constructing an HIF detection model to minimize errors caused by feature extraction. Finally, extensive simulation results demonstrate that the proposed detection method exhibits superior sensitivity and rapidity in identifying HIFs while demonstrating strong generalization capabilities in scenarios involving noise and data incompleteness. |
| Key words: distribution network high impedance fault fault detection zero-sequence current XGBoost |
