基于文本挖掘的煤矿顶板事故致因网络分析  被引量:11

Network Analysis of Coal Mine Roof Accident Causation Based on Text Mining

在线阅读下载全文

作  者:田水承 周鹏辉[1,2] TIAN Shuicheng;ZHOU Penghui(College of Safety Science and Engineering,Xi'an University of Science and Technology,Xi'an 710054,China;Institute of Safety and Emergency Management,Xi'an University of Science and Technology,Xi'an 710054,China)

机构地区:[1]西安科技大学安全科学与工程学院,西安710054 [2]西安科技大学安全与应急管理研究所,西安710054

出  处:《煤炭技术》2023年第2期117-121,共5页Coal Technology

基  金:国家自然科学基金面上项目(51874237);国家自然科学基金重点支持项目(U1904210)。

摘  要:针对我国煤矿顶板事故现状,需明确顶板事故致因因素,有针对性地科学管控应对。运用文本挖掘、R语言及关联规则技术,选取2008—2020年国内116例煤矿顶板事故调查报告进行归并分词、特征项降维及可视化处理后,构建关联规则及复杂社会网络中心性分析及核心边缘结构分析。结果表明,顶板事故各致因间存在紧密联系,安全管理混乱、安全教育培训不足、安全监督检查不到位、技术措施不完善、安全意识淡薄、违章操作等6项致因对事故的发生起主要作用,同时在复杂社会网络分析中也处于核心地位,应对其高度重视和管控,从而减少煤矿顶板事故的发生。In view of the current situation of coal mine roof accidents in China,it is necessary to clarify the causal factors of roof accidents,and target scientific control and response.Using text mining,R language and association rule technology,116 domestic coal mine roof accident investigation reports from 2008 to 2020 were selected for subsumption of words,feature item dimensionality reduction and visualization,and then association rules and complex social network centrality analysis and core edge structure analysis were constructed.The results show that the causes of roof accidents are closely related to each other,and the six causes of accidents,such as chaotic safety management,insufficient safety education and training,inadequate safety supervision and inspection,imperfect technical measures,poor safety awareness and illegal operation,play a major role in the occurrence of accidents,and are also in the core position in the analysis of complex social networks,so that they should be highly valued and controlled to reduce the occurrence of coal mine roof accidents.

关 键 词:煤矿顶板事故 文本挖掘 R语言 Apriori算法 网络分析 

分 类 号:TD327.2[矿业工程—矿井建设]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象