基于XGBoost算法的绝缘子污秽放电在线诊断方法研究  

Research on Online Diagnosis Method of Insulator Pollution Discharge Based on XGBoost Algorithm

作　　者：陈兴新 岳一石 程紫熠 邹妍晖 巢亚锋 CHEN Xingxin;YUE Yishi;CHEN Ziyi;ZOU Yanhui;CHAO Yafeng(Three Gorges University,Yichang 443002,China;State Grid Hunan Electric Power Company Limited Research Institute,Changsha 410007,China)

机构地区：[1]三峡大学,湖北宜昌443002 [2]国网湖南省电力有限公司电力科学研究院,湖南长沙410007

出　　处：《湖南电力》2021年第2期36-40,共5页Hunan Electric Power

基　　金：国网湖南省电力有限公司科技项目(5216A520000T)。

摘　　要：为了准确地监测绝缘子放电状态,提出一种基于XGBoost(极端梯度提升)算法的绝缘子污秽放电在线诊断方法,通过绝缘子在不同污秽程度运行下的放电声音分析判断绝缘子放电状态,实现绝缘子的准确监测。结果表明,该方法可以有效判断绝缘子放电状态。In order to accurately monitor the discharge state of insulators,an on-line diagnosis method of insulator pollution discharge based on XGBoost algorithm is proposed in this paper.By analyzing the discharge sound of insulators under different pollution levels,the discharge status of insulators can be judged,and the accurate monitoring of insulators can be realized.The results show that the method can effectively judge the insulator discharge state.

关 键 词：绝缘子 污秽度 在线诊断 放电状态 XGBoost算法 

分 类 号：TM854[电气工程—高电压与绝缘技术]