导线触树故障明火分布估计的多维零序电流特征有效性分析  

Effectiveness analysis of multidimensional zero-sequence current characteristics for flame distribution estimation of tree faults

作　　者：刘家铭 梁栋[1] 赵伟同 王鹏玮 徐丙垠[1] 黄超艺 朱毅勇 LIU Jiaming;LIANG Dong;ZHAO Weitong;WANG Pengwei;XU Bingyin;HUANG Chaoyi;ZHU Yiyong(School of Electrical and Electronic Engineering,Shandong University of Technology,Zibo 255000,China;State Grid Quanzhou Power Supply Company,Quanzhou 362101,China)

机构地区：[1]山东理工大学电气与电子工程学院,山东淄博255000 [2]国网福建省电力有限公司泉州供电公司,福建泉州362101

出　　处：《供用电》2024年第11期43-50,共8页Distribution & Utilization

基　　金：国家电网有限公司总部科技项目(5500-202221138A-1-1-ZN)。

摘　　要：针对10 kV导线触树故障(tree fault,TF)火灾风险难以量化评估的问题,分析和验证了多维零序电流特征在估计TF明火分布中的有效性。利用真实故障试验数据,构建包括1 s内50个工频周期零序电流有效值、基波及各次谐波的平均值和方差等12个特征的特征向量,建立基于神经网络的TF明火分布估计模型。模型训练采用8170个样本,其中80%用于训练,20%用于测试,并通过均方误差和相关系数对模型性能进行评价。结果显示,神经网络模型能够以较高的准确性估计明火分布,估计绝对误差在±0.05、±0.1范围内的占比分别达到79.99%、93.27%。通过对特征进行逐一排除试验,验证了所选特征对模型的正向贡献和整体特征集的鲁棒性。研究成果为架空导线触树故障明火时空分布的量化估计提供了新的研究思路。To address the challenge of quantifying the fire risk associated with 10kV tree faults(TF),the paper analyzes and validates the effectiveness of multidimensional zero-sequence current characteristics in estimating the distribution of flames in TF.Utilizing real-world fault experiment data,a feature vector of zero-sequence current characteristics,including the effective value,mean value,fundamental wave,and the mean values and variances of each harmonic,is constructed to develop a neural network-based model for TF flame distribution estimation.The model is trained on a dataset of 8,170 samples,of which 80% are used for training and 20% for testing,and evaluated through mean squared error and correlation coefficient.The results demonstrate that the neural network model can estimate the flame distribution with high accuracy,with absolute estimation errors within±0.05 and±0.1 reaching 79.99% and 93.27% respectively.Experiments that systematically exclude each feature confirm the positive contribution of the selected features and the robustness of the overall feature set.The findings provide a new research approach for the quantitative estimation of the spatiotemporal distribution of flames in overhead power line TF.

关 键 词：树木故障 零序电流 炭化路径 神经网络 明火分布估计 

分 类 号：TM71[电气工程—电力系统及自动化]