摘要
通过知识图谱构建电网故障处置模型,将庞大而分散的终端设备数据信息和故障案例数据转化为专业的领域知识图谱,可以有效降低故障处置压力,辅助相关人员进行故障处置决策,提高处置效率和智能化水平。针对知识图谱在配电网故障处置过程中的重要推动作用,文章对知识图谱构建方法及关键技术,如知识抽取、知识融合、知识加工、知识更新等进行了阐述,尤其根据配电网故障处置数据的特点,分析对比构建配电网领域知识图谱过程中各阶段的技术,最后结合知识图谱的发展趋势,提出了配电网故障处置知识图谱面临的挑战和机遇。
Building a power grid fault disposal model through the knowledge graph and transforming the huge and scattered terminal equipment information and fault case data into a professional domain knowledge graph can effectively reduce the pressure of fault disposal,assist relevant personnel in making fault disposal decisions,and improve the efficiency of disposal and the level of intelligence.In view of the important role of knowledge graph in the process of distribution network fault disposal,this paper describes the construction methods and key technologies of knowledge graph,such as knowledge extraction,knowledge fusion,knowledge processing,knowledge updating,etc.Especially according to the characteristics of distribution network fault disposal data,this paper analyzes and compares the technologies at various stages in the process of building the distribution network domain knowledge graph.Finally,combines the development trend of the knowledge graph,the challenges and opportunities faced by the knowledge graph of distribution network fault handling are presented.
作者
刘丽
闫晓梅
李刚
LIU Li;YAN Xiaomei;LI Gang(Department of Computer,North China Electric Power University,Baoding 071003,Hebei Province,China;Engineering Research Center of Intelligent Computing for Complex Energy Systems,Ministry of Education,Baoding 071003,Hebei Province,China)
出处
《电力信息与通信技术》
2023年第7期19-26,共8页
Electric Power Information and Communication Technology
基金
国家重点研发计划资助(2020YFB0906000,2020YFB0906005)
中央高校基本科研业务费专项资金资助(2020MS119)。
关键词
配电网
知识图谱
故障处置
命名实体识别
深度学习
distribution network
knowledge graph
grid fault handling
named entity recognition
deep learning
作者简介
刘丽(1978),女,博士,研究生导师,从事人工智能原理与应用、泛逻辑学、智能控制等研究工作;通信作者:闫晓梅(1995),女,硕士研究生,从事知识图谱技术研究,709119217@qq.com;李刚(1980),男,博士,副教授,硕士生导师,从事智能电网与大数据、信息物理能源系统、故障预测与健康管理工作。
