现代电子技术2025，Vol.48Issue(10)：118-126,9.DOI:10.16652/j.issn.1004-373x.2025.10.019
一种直流配电网电能质量扰动识别方法
Method of power quality disturbance identification based on DC distribution network
摘要
Abstract
With the increase of power electronic devices connected to the power grid,direct-current(DC)distribution networks are superior to traditional distribution networks in terms of strong transmission performance,reduced line losses,and new energy consumption,gradually becoming a new trend in future distribution development.To ensure the stable operation of the DC distribution network and ensure power quality,an improved sparrow search algorithm-support vector machine(ISSA-SVM)power quality disturbance identification method based on kernel principal component analysis(KPCA)feature dimensionality reduction is proposed.The formation mechanisms of various power quality issues were thoroughly explored,and six features were extracted based on waveform analysis.The DBSCAN clustering method is used to detect the presence of outliers and determine whether to use KPCA to reduce the dimensionality of features,enabling them to achieve good clustering in different data situations;The ISSA is used to optimize the parameters of SVM,and the SVM model is retrained using the optimization results.The experimental results show that the proposed method has high accuracy and can effectively identify power quality disturbance signals.关键词
直流配电网/电能质量/扰动识别/DBSCAN聚类/功率谱密度/核主成分分析/麻雀搜索算法/支持向量机Key words
DC distribution grid/power quality/disturance identification/DBSCAN clustering/power spectral density/kernel principal component analysis/sparrow search algorithm/support vector machine分类
信息技术与安全科学引用本文复制引用
李语帆,张怡,康健..一种直流配电网电能质量扰动识别方法[J].现代电子技术,2025,48(10):118-126,9.基金项目
国家重点研发计划项目(国际合作专项)(2021YFE0190900) （国际合作专项）
唐山市科学计划项目(22130210H) （22130210H）
