大数据条件下现场运行电能表计量误差估计方法  

Measurement Error Estimation Method of Field Service Electricity Energy Meters under the Condition of Big Data

作　　者：代燕杰 董贤光 刘亚骑 梁雅洁 刘潇 齐佳 孙永全[4] DAI Yan-jie;DONG Xian-guang;LIU Ya-qi;LIANG Ya-jie;LIU Xiao;QI Jia;SUN Yong-quan(State Grid Shandong Electric Power Company Marketing Service Center(Metering Center),Jinan 250000,China;Jinan Power Supply Company of State Grid Shandong Electric Power Company,Jinan 250000,China;Shandong Zhongshi Yitong Group Co.,Ltd,250000,China;The Higher Educational Key Laboratory for Measuring&Control Technology and Instrumentation of Heilongjiang Province,Harbin University of Science and Technology,Harbin 150080,China)

机构地区：[1]国网山东省电力公司营销服务中心(计量中心),济南250000 [2]国网山东省电力公司济南供电公司,济南250000 [3]山东中实易通集团有限公司,济南250000 [4]哈尔滨理工大学测控技术与仪器黑龙江省高校重点实验室,哈尔滨150080

出　　处：《哈尔滨理工大学学报》2022年第5期97-105,共9页Journal of Harbin University of Science and Technology

基　　金：国家自然科学基金(61179024);国网山东省电力公司科技项目(520626200022).

摘　　要：为了探究现场多维影响工况下在网电能表的计量性能,并映射其在标准实验室条件下的计量误差,提出一种基于大数据分析技术的现场服役电能表计量误差估计方法,结合现场运行的环境数据和电因素数据实现在线计量误差估计。首先,通过优化聚类评价指标实现K-Means聚类算法的改进,并对现场环境数据进行聚类分析;然后,采用LM算法优化基于BP神经网络的数据训练方法,结合负载电流、功率因数等数据,构建电能表电能误差与环境温度、湿度和负载电流、功率因数四种应力的映射关系;最后,在获取电能表现场电能误差数据的基础上,开展工程应用实例计算。结果表明,利用所提方法可对电能表的计量误差进行划分,验证了所提方法的准确性。In order to better explore the measurement performance of field service electricity energy meters under multi-dimensional influence conditions,and infer measurement error under standard laboratory conditions,a measurement error estimation method of field service electricity energy meters is proposed based on big data analysis technology,which realizes on-line measurement error estimation by combining environmental data and electric factor data of field operation.Firstly,the K-Means clustering algorithm is improved by optimizing the clustering evaluation index,and the field environmental data is analyzed by clustering.Then,LM algorithm is used to optimize the data training method BP neural network,and modeling relationship between electric energy error and the four factors of environmental temperature,humidity,load current and power factor is constructed.Finally,on the basis of field electric energy error data of electric energy meter,the calculation of engineering application example is carried out.The results show that the proposed method can be used to divide the measurement energy error of electric energy meter,and the accuracy of the proposed method is verified.

关 键 词：智能电能表 电能误差 温度 功率因数 BP神经网络 

分 类 号：TM933.4[电气工程—电力电子与电力传动] TB971[一般工业技术—计量学]