基于文本挖掘的物探作业事故分析方法  被引量:4

Analysis Method of Accidents in Geophysical Prospecting Operation Based on Text Mining

在线阅读下载全文

作  者:王明达[1] 陈泼[1] 陈子新 韦永健 徐宗辉 WANG Mingda;CHEN Po;CHEN Zixin;WEI Yongjian;XU Zonghui(College of Mechanical and Electronic Engineering,China University of Petroleum (East China),Qingdao 266580,Shandong,China;Petroleum Engineering Geophysical Co.,Ltd.,Sinopec,Beijing 100000,China)

机构地区:[1]中国石油大学(华东)机电学院,山东青岛266580 [2]中石化石油工程地球物理有限公司,北京100000

出  处:《西安石油大学学报(自然科学版)》2019年第4期119-126,共8页Journal of Xi’an Shiyou University(Natural Science Edition)

基  金:国家自然科学基金(51204203;51875579);山东省自然科学基金青年项目(ZR2016EEQ2b)

摘  要:针对物探作业事故提出了一种基于文本挖掘(TM)的分析方法。首先,从人、机、环境、管理四方面分别对事故文本数据进行文本分析,通过筛选得到事故影响因素,并利用k-means聚类识别事故类型;以事故影响因素为前项,事故类型为后项构建多维物探作业事故数据模型,运用多维Apriori技术进行物探作业事故关联分析,得到事故影响因素与事故类型的强关联规则,并通过分析这些规则发掘各类事故的发生规律;最后,应用该方法对某物探公司野外作业事故数据进行分析及验证。研究结果表明,该方法能够加深对事故的认识,为物探作业安全管理提供科学的决策依据,在物探行业事故分析领域有着良好的应用前景。A analysis method of geophysical exploration operation accident based on text mining (TM) is proposed.Firstly,the text data of accidents are analyzed from four aspects:human,machine,environment and management.The influence factors of accidents are screened and the types of accidents are identified by K-means clustering.Then,the data model of multi-dimensional geophysical exploration operation accidents is established with the influence factors of accidents as the preceding item and the types of accidents as the latter item.The strong association rules between accident influencing factors and accident types are obtained by using multi-dimensional Apriori technology,and the occurrence rules of various accidents are discovered by analyzing these rules.Finally,the field operation accident data of a geophysical exploration company is analyzed and verified using this method.The results show that this method has good application prospects in the accident analysis of geophysical exploration industry.It can deepen the understanding of accidents and provide scientific decision-making basis for safety management of geophysical exploration operations.

关 键 词:物探作业 事故分析 文本数据 文本挖掘 多维Apriori 

分 类 号:TE19[石油与天然气工程—油气勘探] TP391[自动化与计算机技术—计算机应用技术]

 

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