煤矿机电设备事故知识图谱构建及应用

针对难以从煤矿机电设备事故表象和部分监控数据判断设备事故根本原因,以及缺少能够利用历史数据、经验知识的有效手段来提高设备事故处理效率等问题,构建了煤矿机电设备事故知识图谱。首先设计四组元本体模型的数据关系,确定本体及本体之间的关系类型;然后根据设计的数据关系,采用机器学习和规则模板相结合的方法从数据库、文本中抽取实体、关系和属性;最后基于Python语言,通过py2neo库用Cypher语句对实体、关系和属性进行创建并存入Neo4j图数据库,实现知识图谱的构建和更新。煤矿机电设备事故知识图谱在煤矿机电设备事故诊断、风险管理和智能问答等方面的应用可使用户高效利用煤矿机电设备事故相关知识,帮助设备维护人员快速查找事故链条、定位事故原因并提出维修方案,达到降低事故率、减少事故处理时间的目的。

Construction and application of mine electromechanical equipment accident knowledge graph

It is difficult to judge the root cause of equipment accident from the appearance of coal mine electromechanical equipment accident and part of monitoring data,and there is a lack of effective methods to improve the efficiency of equipment accident treatment by using historical data and experience knowledge.In order to solve the above problems,the mine electromechanical equipment accident knowledge graph is constructed.Firstly,the data relationships of the four-group ontology model are designed,and the ontology and the relationship types between the ontologies are determined.Secondly,according to the designed data relationships,a combination method of machine learning and rule templates is used to extract entities,relationships and attributes from databases and texts.Finally,based on the Python language,through the py2neo library,the entities,relationships and attributes are created and stored in the Neo4j graph database with Cypher statements,so as to realize the construction and update of the knowledge graph.The application of mine electromechanical equipment accident knowledge graph in mine electromechanical equipment accident diagnosis,risk management and intelligent question and answer can enable users to effectively use related knowledge of mine electromechanical equipment accident,help equipment maintenance personnel to quickly find the accident chain,locate the cause of the accident and put forward maintenance schemes,so as to achieve the purpose of reducing the accident rate and the accident handling time.