摘要
针对配电网小电流接地系统发生单相接地故障时选线过程易受噪声干扰、选线精度较低的问题,提出了一种多判据融合的选线方法。该方法结合快速傅里叶变换(FFT)与变分模态分解(VMD)技术,提取各线路零序电流的三种特征分量,构建多维度输入特征;在此基础上,引入粒子群算法优化的随机森林分类器(PSO-RF),以故障线路为输出标签对模型进行训练,实现对新故障数据的准确线路判别。利用MATLAB/Simulink软件建立单相接地故障仿真模型进行仿真实验,验证所提方法的有效性,并与现有算法进行对比。结果表明,所提方法在选线准确率方面具有显著优越性,展现出良好的工程应用潜力。
In response to the issues of susceptibility to noise interference and relatively low line selection accuracy during single-phase grounding faults in the low-current grounding systems of distribution networks,this paper proposes a multi-criteria fusion-based fault line selection method.This approach integrates fast fourier transform(FFT)and variational mode decomposition(VMD)techniques to extract three characteristic components of the zero-sequence current from each line,thereby constructing multi-dimensional input features.On this basis,the random forest classifier optimized by the particle swarm optimization algorithm(PSO-RF)is proposed in this study.The model is trained using the faulty line as the output label,enabling accurate identification of fault lines in new fault data.A single-phase grounding fault simulation model was established,using MATLAB/Simulink software for simulation experiments to validate the effectiveness of the proposed method,and comparisons are made with existing algorithms.The results demonstrate that the proposed method exhibits significant superiority in fault line selection accuracy,showing promising potential for engineering applications.
作者
钟灵毓秀
郑吴筱添
靳玉洁
吴梦宇
钟建伟
廖红华
ZHONG Ling-yuxiu;ZHENG Wu-xiaotian;JIN Yu-jie;WU Meng-yu;ZHONG Jian-wei;LIAO Hong-hua(College of Intelligent Systems Science and Engineering,Hubei Minzu University,Enshi 445000,China)
出处
《电工电气》
2026年第1期45-50,60,共7页
Electrotechnics Electric
基金
国家自然科学基金项目(62341305)
湖北民族大学研究生科研创新项目(MYK2025080)。
关键词
故障选线
小电流接地
粒子群算法
随机森林分类器
多判据融合
fault line selection
low-current grounding
particle swarm optimization
random forest classifier
multi-criteria fusion
