基于改进决策树算法的电能计量装置故障自动化诊断系统  

Automatic Fault Diagnosis System of Energy Metering Device Based on Improved Decision Tree Algorithm

作　　者：张驰 王栋 赵书函 ZHANG Chi;WANG Dong;ZHAO Shuhan(Information&Telecommunication Company of State Grid Gansu Electric Power Company,Lanzhou 730000,China)

机构地区：[1]国网甘肃省电力公司信息通信公司,兰州730000

出　　处：《自动化与仪表》2024年第2期1-4,10,共5页Automation & Instrumentation

摘　　要：电网中电能计量装置具有周检工作量大、数量多、巡检成本较高、巡检效率较低以及故障定位用时较长等问题,该文提出以改进决策树算法为依据的电能计量装置故障自动化诊断系统。设计相应的电能计量装置在线监测流程,结合数据挖掘以及决策树算法进行算例模型的搭建。经过实验验证,所提系统能够更高效地进行故障诊断,同时其自动化诊断故障的准确率相比人工判读更高。The power metering device in the power grid has many problems,such as large weekly inspection workload,large quantity,high inspection cost,low inspection efficiency and long fault location time.This paper presents an automatic fault diagnosis system based on improved decision tree algorithm.The corresponding online monitoring flow of energy metering device is designed,and the example model is built by combining data mining and decision tree algorithm.The experimental results show that the proposed system can diagnose faults more efficiently,and the accuracy of automatic diagnosis is higher than that of manual interpretation.

关 键 词：决策树算法 电能计量装置 故障诊断 决策树深度 数据挖掘 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]