基于随机森林的避雷器绝缘状态评估方法  

A Method for Arrester Insulation State Assessment based on Random Forest

作　　者：刘志伟[1] 宁克[1] 刘星廷 侯滨[1] 王海旗 Liu Zhi-wei;Ning Ke;Liu Xing-ting;Hou Bin;Wang Hai-qi

机构地区：[1]国网山西省电力公司物资分公司,山西太原030021 [2]国网山西省电力公司电力科学研究院,山西太原030021

出　　处：《电力系统装备》2023年第1期10-12,共3页Electric Power System Equipment

基　　金：国网山西省电力公司科技项目(B9QD-300009601-00001)。

摘　　要：在温度、湿度及表面污秽等多种因素同时作用时,避雷器在线监测的特征量的变化比较复杂,实测数据的准确性会大幅降低,仅根据监测得到的特征量无法准确、直接地判断避雷器的绝缘状态。因此,基于大量的历史记录数据,采用随机森林算法构建避雷器绝缘状态评估模型,对避雷器的绝缘状态进行准确评估,及时发现避雷器内部绝缘缺陷。利用某电力公司的实际测试数据,结果显示随机森林的评价准确率为89.12%,与决策树和支持向量机相比,该方法有更优的泛化能力,为避雷器运维提供有效支撑。Temperature,humidity,surface pollution and other factors effect the measurements of arrester on-line monitoring,and the accuracy of measured data will be greatly reduced.It is impossible to accurately and directly judge the insulation state of Arrester based on the measured data obtained by monitoring.This paper proproses an assessment model for the insulation state of arresters based on random forest algorithm and a large number of historical data.It can accurately assess the insulation state of arresters.The example shows that the assessment accuracy of the proposed model is 89.12%,and it has better generalization ability than the decision tree and the support vector machine.

关 键 词：随机森林 避雷器 绝缘状态评估 

分 类 号：TM862[电气工程—高电压与绝缘技术]