基于网络结构优化的检修计划编制数据源多目标合并方法  

Multi-objective Consolidation Method of Maintenance Plan Data Source Based on Network Structure Optimization

作　　者：董耀 张小龙 曹春莲 郑立国 马永超 DONG Yao;ZHANG Xiaolong;CAO Chunlian;ZHENG Liguo;MA Yongchao(Haixi Electric Power Corporation,Geermu 816099,China;State Grid Qinghai Electric Power Company,Xining 810000,China)

机构地区：[1]国网青海省电力公司海西供电公司,青海格尔木816099 [2]国网青海省电力公司,青海西宁810000

出　　处：《微型电脑应用》2023年第5期43-46,共4页Microcomputer Applications

基　　金：国网青海省电力公司海西供电公司项(52280620008C)。

摘　　要：由于传统多目标数据合并方法缺少数据校验与格式转换,导致数据合并后存在误差,影响电网设备故障识别准确率,因此设计一种基于网络结构优化的检修计划编制数据源多目标合并方法。融合来源于各传感器的多源数据,通过数据级、特征级和决策级等3层校验,得到抗干扰能力强的数据源;转换多目标数据格式,分别提取不同类型数据的相应特征,将数据的黑度-坡度进行归一化处理并以矩阵形式实现数据合并。实例分析结果证明,所设计的数据合并方法识别电网设备3种故障状态准确率分别为97.36%、93.80%、94.50%。该方法提高了电网设备故障识别的准确率,可以为检修计划编制提供可靠依据。The traditional multi-target data consolidation method lacks data verification and format conversion,which leads to errors after data merger and affects the fault identification accuracy of power grid equipment.Therefore,a multi-target merger method for compiling data sources based on network structure optimization is designed.It integrates multi-source data from each sensor,obtains data sources with strong anti-interference ability through data level,feature level and decision level verification,converts multi-target data formats,extracts the corresponding characteristics of different types of data,normalizes the blackness-slope of data and realizes data merging in matrix form.Example analysis results prove that the data consolidation method identifies the three fault states of power grid equipment,with the accuracy of 97.36%,93.80%and 94.50%,respectively.The method improves the accuracy of fault identification and can provide reliable basis for maintenance plan.

关 键 词：数据校验 网络结构优化 数据格式转换 检修计划编制 多目标合并 特征提取 

分 类 号：O29[理学—应用数学]