智能电表故障辨识模型研究  

Study on Smart Meters Fault Identification Model

作　　者：杨金成[1] 蒋平[2] 陈广宇[3] 袁铁江[2,4] 薛飞[1] 

机构地区：[1]国网新疆电力公司电力科学研究院,新疆乌鲁木齐830000 [2]新疆大学电气工程学院,新疆乌鲁木齐830047 [3]国网冀北电力有限公司承德供电公司,河北承德067000 [4]清华大学电机系电力系统国家重点实验室,北京100084

出　　处：《电器与能效管理技术》2017年第6期30-36,共7页Electrical & Energy Management Technology

基　　金：国家自然科学基金(51367018);国家电网科学技术项目(SGXTDKOOTLTS1600154)

摘　　要：针对智能电表故障辨识问题,基于电表计量数据并考虑影响智能电表故障的各个因素,提出一种智能电表故障辨识模型(智能电表计量异常分析模型和基于C5.0智能电表故障预测模型)。首先用智能电表计量异常分析模型筛选出计量异常的智能电表,然后采用基于C5.0智能电表故障预测模型预测智能电表是否发生非计量故障或无故障。实例验证结果表明,智能电表故障辨识模型可以较为准确、真实地辨识智能电表故障,可为智能电表故障辨识的进一步研究提供一定参考。Aiming at the smart meters failure identification problem,based on the measurement data of smart meter and considering various factors which affect the fault of smart meter,a smart meter fault identification model was proposed.It consists of two parts：the abnormal analysis model of smart meters and the fault prediction model based on C5.0.The idea is that,first of all,the measuring abnormal smart meter is selected by the abnormal analysis model of smart meters,then the fault prediction model based on C5.0 is used to predict whether the metering has a non-measurement fault or not.The results of examples show that the smart meter fault identification model can more accurately and truthfully identify smart meter fault,and this method can provide some reference for the further research of fault identification of smart meters.

关 键 词：智能电表 故障辨识 C5.0 数据挖掘 

分 类 号：TM933[电气工程—电力电子与电力传动]