基于融合K-近邻算法的电压互感器在线监测方法  

Online Monitoring Method for Voltage Transformers Based on Fusion K-nearest Neighbor Algorithm

作　　者：李振华[1,2] 崔九喜 杨信强 吴海荣 杨诗豪 薛田良[1,2] LI Zhenhua;CUI Jiuxi;YANG Xinqiang;WU Hairong;YANG Shihao;XUE Tianliang(Hubei Provincial Key Laboratory for Operation and Control of Cascaded Hydropower Station(China Three Gorges University),Yichang 443002,Hubei Province,China;College of Electrical Engineering&New Energy,China Three Gorges University,Yichang 443002,Hubei Province,China)

机构地区：[1]梯级水电站运行与控制湖北省重点实验室(三峡大学),湖北省宜昌市443002 [2]三峡大学电气与新能源学院,湖北省宜昌市443002

出　　处：《电网技术》2024年第9期3938-3947,I0100,共11页Power System Technology

基　　金：国家自然科学基金项目(52277012);强电磁工程与新技术国家重点实验室开放课题(2022KF005)。

摘　　要：由于受工作时长和环境因素的影响,电容式电压互感器(capacitor voltage transformer,CVT)在运行过程中误差稳定性不高,易出现电能计量失准现象。为此,该文提出了一种基于融合K-近邻算法(fusion K-nearest neighbor algorithm,FKNN)的电压互感器在线评估方法。该方法利用互感器的历史运行数据构建虚拟标准器,通过改进K-近邻算法对互感器实时状态进行监测,实现对异常情况的报警。同时,提出了一种加权移动时间窗的方法,自适应更新异常阈值,有效削弱电网不平衡波动的影响。实验结果表明,该文方法能够准确监测互感器的0.2级误差漂移。Due to the influence of working hours and environmental factors,capacitor voltage transformer(CVT)error stability during operation is low,and it is prone to inaccurate energy measurement.Therefore,this paper proposes an online evaluation method for voltage transformers based on the fusion K-nearest neighbor algorithm(FKNN).The method uses the historical operation data of the transformer to construct a virtual standard instrument.It monitors the real-time operation status of the transformer through an improved K-nearest neighbor algorithm to achieve abnormal condition alarms.At the same time,a weighted moving time window method is proposed to adaptive update the abnormal threshold value,effectively weakening the influence of unbalanced fluctuations in the power grid.Experimental results show that the proposed method can accurately monitor the 0.2-level error drift of the transformer.

关 键 词：电压互感器 虚拟标准器 K-近邻算法 自适应更新 

分 类 号：TM721[电气工程—电力系统及自动化]