基于正则表达式和Jaccard系数的智能变电站录波通道同源匹配OACSTPCD
Homologous matching of recording channels in intelligent substations based on regu-lar expression and Jaccard similarity coefficient
针对220 kV及以上电压等级智能变电站双套录波通道同源匹配问题,提出一种基于正则表达式和Jaccard系数的智能变电站录波通道同源匹配方法.首先,针对录波通道命名不规范的问题,使用正则表达式对通道名称文本进行预处理,统一通道名称的表达形式;同时,使用jieba分词算法和去停用词操作,去除通道名称文本中可能存在的冗余信息.然后,使用Jaccard相似系数匹配算法计算录波通道名称文本之间的相似度,依据相似度大小筛选出同源通道.最后,基于电网实际的录波文件数据进行仿真分析.仿真结果表明:所提方法可有效实现智能变电站录波通道同源匹配.
In addressing the challenge of homologous matching for dual sets of recording channels in intelligent sub-stations of 220 kV and above,this paper presents a novel method employing regular expression and Jaccard index.To overcome the issue of irregular naming of recording channels,regular expressions to preprocess name texts of the channels are employed to ensure a standardized expression format.Furthermore,through Jieba word segmentation algorithm and stopword removal potential redundant information within the name texts of the channels.Subse-quently,the Jaccard similarity coefficient matching algorithm is employed to calculate the similarity between record-ing channel names,screening out homologous channels based on their similarity degrees.To validate the proposed method,simulations are conducted using actual recording file data from the power grid.The results affirm the effec-tiveness of the proposed method in achieving homologous matching of recording channels in intelligent substations.
王冠南;郭丽娟;彭曙蓉;陈慧霞;黄浩宇
国网江西省电力有限公司电力科学研究院,南昌 330096长沙理工大学 电气与信息工程学院,长沙 410114
录波通道同源匹配文本匹配正则表达式Jaccard相似系数
homologous matching of recording channeltext matchingregular expressionJaccard similarity coefficient
《浙江电力》 2024 (001)
20-27 / 8
国网江西省电力有限公司科技项目(52182022000A);湖南省教育厅重点项目(20A021);国家自然科学基金面上项目(52177069)
评论