电力系统及其自动化学报2024，Vol.36Issue(4)：9-18,10.DOI:10.19635/j.cnki.csu-epsa.001214
基于VMD和改进聚类算法的配电网故障选线方法
Fault Line Selection Method for Distribution Network Based on VMD and Improved Clustering Algorithm
摘要
Abstract
To improve the accuracy of fault line selection for a small current grounding system under single-phase grounding fault,a fault line selection scheme based on the combination of variational mode decomposition(VMD)of amplitude modulation and frequency modulation functions and the K-means++ clustering algorithm is designed in this paper.The zero-sequence current signal of each line after the fault is decomposed by VMD,and the intrinsic mode func-tions of multiple adaptive frequency band characteristics are obtained.A two-dimensional plane with the waveform corre-lation coefficient of the low-frequency component as its abscissa and the initial polarity of the high-frequency component as its ordinate is constructed,and a distribution diagram of scattered points representing each line is drawn on the two-dimensional plane.Finally,the K-means++ clustering algorithm is used to cluster the constructed scattered point set,and the fault line is selected according to the characteristic that the scattered point representing the fault line belongs to an outlier point.Simulation verification is carried out using the Pscad software,and results show that the proposed fault line selection method is not affected by changes in conditions and can realize an accurate identification of the fault line,indicating a good anti-noise capability.关键词
故障选线/变分模态分解/聚类算法/小电流接地系统/离群点Key words
fault line selection/variational mode decomposition(VMD)/clustering algorithm/small current ground-ing system/outlier point分类
信息技术与安全科学引用本文复制引用
王远川,李泽文,夏翊翔,毛紫玲,郭欣玉..基于VMD和改进聚类算法的配电网故障选线方法[J].电力系统及其自动化学报,2024,36(4):9-18,10.基金项目
国家自然科学基金资助项目(51877012) （51877012）
湖南省科技创新人才计划科技创新团队资助项目(2021RC4061) （2021RC4061）
