海上风电场集电海缆故障区段定位方法  

Fault section location method for collector submarine cable in offshore wind farm

作　　者：白通 王慧芳[1] 杨林刚 高玉青 周才全 BAI Tong;WANG Huifang;YANG Lingang;GAO Yuqing;ZHOU Caiquan(College of Electrical Engineering,Zhejiang University,Hangzhou 310027,China;POWERCHINA Huadong Engineering Corporation Limited,Hangzhou 311122,China)

机构地区：[1]浙江大学电气工程学院,浙江杭州310027 [2]中国电建集团华东勘测设计研究院有限公司,浙江杭州311122

出　　处：《电力自动化设备》2025年第5期93-100,共8页Electric Power Automation Equipment

摘　　要：准确定位集电线路故障区段是海上风电场集电海缆故障快速恢复的关键。针对现有海上风电场量测信息无法实现集电海缆故障区段定位问题,提出在集电线路各区段增设容易配置的电流互感器,可满足基于数据驱动建模的故障区段定位方法。以集电线路测点电流幅值变化量构建特征集,通过搭建永磁直驱风电场仿真模型,获取正常运行和故障工况的仿真样本,然后采用轻量级梯度提升机(LightGBM)算法离线训练故障区段分类模型,并应用于海上风电场监控系统实现在线快速定位故障区段。MATLAB/Simulink实验证明了所提方法能满足多分支集电海缆的故障区段定位需求,在不同过渡电阻、故障类型、故障位置条件下,具有较高的定位准确率。Accurate locating the fault section of collector cable is the key to rapidly recover the faults of collector submarine cable in offshore wind farm.To solve the problem that the existing measurement information of offshore wind farm is insufficient to achieve fault section location in collecting submarine cables,it is proposed to add easily configurable current transformers in each section of the collector lines,which can meet the requirements of fault section location method based on data-driven modeling.The feature set is constructed based on the variation of the current amplitude at the measurement point of the collector line,and the simulation model of a permanent magnet direct drive wind farm is built to obtain the simulation samples of normal operation and fault conditions.Then the LightGBM(light gradient boosting machine)algorithm is used to train the fault section classification model offline,and it is applied to the offshore wind farm monitoring system to realize online rapid location of the fault section.MATLAB/Simulink experiments show that the proposed method can meet the fault section location requirements of multi-branch collector submarine cables,and has high positioning accuracy under different transition resistances,fault types and fault locations.

关 键 词：故障区段定位 海上风电场 数据驱动建模 机器学习算法 集电线路 

分 类 号：TM81[电气工程—高电压与绝缘技术] TM713