| 引用本文: | 李 彬,傅 哲,肖 羽,等.基于优化模态分解与时空图卷积网络的光伏配电网高阻抗故障诊断与定位方法研究[J].电力系统保护与控制,2026,54(03):121-131.[点击复制] |
| LI Bin,FU Zhe,XIAO Yu,et al.Research on high-impedance fault diagnosis and location in photovoltaic distribution networks based on optimized modal decomposition and spatiotemporal graph convolutional networks[J].Power System Protection and Control,2026,54(03):121-131[点击复制] |
|
| 摘要: |
| 高比例光伏接入使配电网络暂态特性复杂化，导致传统方法在高阻抗故障诊断与定位时存在特征提取不充分、拓扑关联性不强的问题，进而影响准确性。鉴于此，提出一种基于斑马优化(zebra optimization algorithm, ZOA)多元变分模态分解(multivariate variational mode decomposition, MVMD)结合Teager-Kaiser能量算子(teager-kaiser energy operator, TKEO)多特征融合时空图卷积神经网络(spatio-temporal graph convolutional network, STGCN)的光伏配电网高阻抗故障诊断与定位方法。首先利用MVMD处理多变量信号，以有效融合多维数据并充分挖掘故障特征，此外采用ZOA对MVMD参数优化，进一步提升特征提取效果。其次通过TKEO增强MVMD最高频本征模态分量，捕捉瞬时能量变化。最后构建多特征融合向量输入STGCN，通过长短期记忆层提取时序动态特征，结合图卷积神经网络挖掘节点间空间拓扑关系，实现时空特征联合建模。在IEEE33节点系统上进行了仿真测试，结果表明相较于传统方法，所提方法在光伏配电网高阻抗故障诊断与定位方面具有更高精度。 |
| 关键词: 配电网 高阻抗 故障诊断与定位 斑马优化多元变分模态分解 时空图卷积神经网络 |
| DOI：10.19783/j.cnki.pspc.250522 |
| 投稿时间：2025-05-16修订日期：2025-11-15 |
| 基金项目:智能电网重大专项(2030)(2025ZD0805200)；中国科学院青年创新促进会项目资助(2023000018)；国网北京市电力公司科技项目资助(520202230006) |
|
| Research on high-impedance fault diagnosis and location in photovoltaic distribution networks based on optimized modal decomposition and spatiotemporal graph convolutional networks |
| LI Bin1,FU Zhe2,XIAO Yu2,ZHANG Qi2,ZHANG Xiangyi2,ZHANG Yi2,LUO Zhongge2,SUN Yushu3 |
| (1. State Grid Beijing Daxing Electric Power Supply Company, Beijing 102600, China; 2. State Grid Beijing Urban District Power
Supply Company, Beijing 100034, China; 3. Institute of Electrical Engineering, Chinese Academy of Sciences, Beijing 100190, China) |
| Abstract: |
| The high penetration of photovoltaic (PV) generation complicates the transient characteristics of distribution networks, leading to insufficient feature extraction and weak topological correlation in traditional high-impedance fault (HIF) diagnosis and location methods, thereby degrading accuracy. To address these challenges, a novel HIF diagnosis and location method for PV-integrated distribution networks is proposed based on multi-feature fusion via zebra optimization algorithm (ZOA)-optimized multivariate variational mode decomposition (MVMD), combined with Teager-Kaiser energy operator (TKEO), and a spatiotemporal graph convolutional network (STGCN). First, MVMD processes multivariate signals to effectively fuse multi-dimensional data and fully extract fault features. Meanwhile, ZOA is used to optimize the MVMD parameters, further enhancing feature extraction performance. Second, TKEO is utilized to enhance the highest-frequency intrinsic mode function decomposed by MVMD, enabling the capture of transient energy variations. Finally, a multi-feature fusion vector set is constructed and fed into the STGCN, which employs long short-term memory layers to extract temporal dynamic features and integrates graph convolutional networks to explore spatial topological relationships among nodes, achieving joint spatiotemporal feature modeling. Simulation tests conducted on the IEEE 33-node system demonstrate that, compared to traditional methods, the proposed approach achieves higher accuracy in HIF diagnosis and location for PV distribution networks. |
| Key words: distribution network high impedance fault diagnosis and location zebra optimization algorithm-optimized multivariate variational mode decomposition spatiotemporal graph convolutional network |
