智能电能表综合性能评级方法研究  

Research on comprehensive performance rating method for smart meters

作　　者：姜洪浪[1] 赵婷[1] 段晓萌 左嘉 王晓东[1] 王爽[1] Jiang Honglang;Zhao Ting;Duan Xiaomeng;Zuo Jia;Wang Xiaodong;Wang Shuang(China Electric Power Research Institute,Beijing 100192,China)

机构地区：[1]中国电力科学研究院,北京100192

出　　处：《电测与仪表》2018年第6期105-109,115,共6页Electrical Measurement & Instrumentation

基　　金：中国电力科学研究院青年科研基金资助项目(JL84-17-001)

摘　　要：针对目前国内智能电能表综合性能评价缺失的情况,提出一种基于数据挖掘方法的智能电能表综合性能评级方法。基于大量智能电能表样本的全性能试验数据,选取代表性试验项目数据作为性能评级指标,利用主成分法分析某一评级指标下不同试验点的影响程度,给出不同试验点的权重值,通过加权处理获得各评级指标数据,得到评级指标矩阵。采用k均值聚类分析法构建智能电能表综合性能评级模型,对所选各样表性能给出评级结果。最后随机选取三个不同电能表厂家的样表,结合电能表现场故障率统计情况等分析其评级结果分布,验证了该评级方法对电能表综合性能评级的合理性及可靠性。In this paper,a new method of smart meter performance rating based on data mining method is proposed considering the lack of comprehensive performance evaluation of smart meters now.On the basis of the performance test data of a large number of smart meter samples,the representative test data is selected as the performance rating index.Then,the principal component method is used to analyze the influence degree of different test points under a certain rating index,and the weight value of different test points is given,so the data matrix of each rating index is obtained.The k-means clustering analysis method is used to construct the comprehensive performance rating model of the smart meter,and the rating results are given for samples.Finally,smart meter samples are selected from three different manufacturers randomly and their distribution of rating results analyzed considering failure rate in the field.The rating results of the samples verify the proposed method of comprehensive performance for smart meters is reasonable and reliable.

关 键 词：智能电能表 综合性能评级 主成分分析 K均值聚类 

分 类 号：TM933[电气工程—电力电子与电力传动]