|本期目录/Table of Contents|

[1]牛毅,樊运晓,高远.基于数据挖掘的化工生产事故致因主题抽取[J].中国安全生产科学技术,2019,15(10):165-170.[doi:10.11731/j.issn.1673-193x.2019.10.026]
 NIU Yi,FAN Yunxiao,GAO Yuan.Topic extraction on causes of chemical production accidents based on data mining[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(10):165-170.[doi:10.11731/j.issn.1673-193x.2019.10.026]
点击复制

基于数据挖掘的化工生产事故致因主题抽取
分享到:

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
15
期数:
2019年10期
页码:
165-170
栏目:
职业安全卫生管理与技术
出版日期:
2019-10-31

文章信息/Info

Title:
Topic extraction on causes of chemical production accidents based on data mining
文章编号:
1673-193X(2019)-10-0165-06
作者:
牛毅樊运晓高远
(中国地质大学(北京) 工程技术学院,北京 100083)
Author(s):
NIU Yi FAN Yunxiao GAO Yuan
(School of Engineering & Technology,China University of Geosciences Beijing,Beijing 100083,China)
关键词:
化工事故文本数据数据挖掘潜在狄利克雷分配(LDA)事故致因
Keywords:
chemical accidents text data data mining Latent Dirichlet Allocation (LDA) accident cause
分类号:
X928.0
DOI:
10.11731/j.issn.1673-193x.2019.10.026
文献标志码:
A
摘要:
为充分挖掘化工生产事故数据中的有效信息和潜在规律,提高对化工事故认知水平,针对某化工集团2010—2016年共1 578起事故数据,利用社会网络分析等方法揭示事故要素间的关联关系;运用潜在狄利克雷分配(LDA)模型进行事故聚类,并抽取到5个事故致因主题。研究结果表明:LDA主题模型等数据挖掘技术能有效挖掘大量事故数据中的潜在信息;5个事故致因主题中,4个涉及到人因或组织层面的缺陷;员工注意力不集中和现场风险管理不足这2个致因主题间具有较强相关性;员工注意力不集中、现场风险管理不足以及设备问题是导致事故发生的主要原因。
Abstract:
In order to fully exploit the effective information and potential laws in the data of chemical production accidents,and improve the cognitive level of chemical accidents,according to the data of 1 578 accidents in a chemical industry group from 2010 to 2016,the association relationship between the accident elements was revealed by means of social network analysis.The Latent Dirichlet Allocation (LDA) model was applied to conduct the accident clustering,and five topics of accident causes were extracted.The results showed that the data mining techniques such as LDA topic model could effectively mine the potential information in a large amount of accident data.Among the five topics of accident causes,four topics involved the human factors or organizational defects.Two topics of accident causes including the lack of concentration of employees and the inadequate onsite risk management had a strong correlation.The lack of concentration of employees,the inadequate onsite risk management,and the equipment problems were the main causes of accidents.

参考文献/References:

[1]戚萌,朱常龙.2013—2017年中国石化及化工行业安全生产现状及展望[J].现代化工,2019,39(2):1-8. QI Meng,ZHU Changlong.2013—2017 Sinopec and chemical industry safety production status and prospects[J].Modern Chemical Industry,2019,39(2):1-8.
[2]HOLLNAGEL E.Safety-I and safety-II:the past and future of safety management [M].Farnham:Ashgate,2014:35-36.
[3]BELLAMY LINDA J.Exploring the relationship between major hazard,fatal and non-fatal accidents through outcomes and causes[J].Safety Science,2015(71):93-103.
[4]李健,白晓昀,任正中,等.2011~2013年我国危险化学品事故统计分析及对策研究[J].中国安全生产科学技术,2014(6):142-147. LI Jian,BAI Xiaojun,REN Zhengzhong,et al.Statistical analysis and countermeasures of dangerous chemicals accidentsin China from 2011 to 2013[J].Journal of Safety Science and Technology,2014(6):142-147.
[5]LORENZO,MICAELA,GABRIELE.A combined approach for the analysis of large occupational accident databases to support accident-prevention decision making[J].Safety Science,2018(106):191-202.
[6]RIVAST,PAZ M,MARTINJE,et al.Explaining and predicting workplace accidents using data-mining techniques[J].Reliability Engineering and System Safety,2011(96):739-747.
[7]ZHANG Z,HE Q,GAO J,et al.A deep learning approach for detecting traffic accidents from social media data[J].Transportation Research Part C,2018(86):580-596.
[8]ALIKHANI M,NEDAIE A,AHMADVAND A.Presentation of clustering-classification heuristic method for improvement accuracy in classification of severity of road accidents in Iran[J].Safety Science,2013(60):142-150.
[9]YANG MIANG GOH,UBEYNARAYANACU.Construction accident narrative classification:An evaluation of text mining techniques[J].Accident Analysis and Prevention,2017(108):122-130.
[10]BLEI D M,NG AY,JORDAN M J.Latent dirichlet allocation[J].Journal of Machine Learning Research,2003(3):993-1022.
[11]李静.基于LDA的微博灾害信息聚合——以台风为例[D].武汉:武汉大学,2018.
[12]RAMESH N,WILLIAM C,JOHN L.Parallelized variational EM for Latent Dirichlet Allocation:an experimental evaluation of speed and scalability[J].IEEE International Conference on Data Mining,2007:349-354.
[13]唐明,朱磊,邹显春.基于Word2Vec的一种文档向量表示[J].计算机科学,2016,43(6):214-217. TANG Ming,ZHU Lei,ZOU Xianchun.A document vector representation based on Word2Vec[J].Computer Science,2016,43(6):214-217.
[14]朱庆华,李亮.社会网络分析法及其在情报学中的应用[J].情报理论与实践,2008,31(2):179-183. ZHU Qinghua,LI Liang.Social network analysis and its application in information science[J].Information Theory andPractice,2008,31(2):179-183.
[15]AU ASUNCION,P SMYTH,M WELLING.Asynchronous distributed learning of topic models[J].Conference on Neural Information Processing System,2011:81-88.

相似文献/References:

[1]王陈玉书,张园园,张巨伟,等.化工事故模糊系统FTA模型的研究与应用[J].中国安全生产科学技术,2013,9(2):117.
 WANG CHEN Yu shu,ZHANG Yuan yuan,ZHANG Ju wei,et al.Research and application on FTA model of chemical accident fuzzy system[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(10):117.
[2]陈伟,温晋锋,钱城江.化工企业事故决策者风险感知模拟预测研究[J].中国安全生产科学技术,2016,12(8):92.[doi:10.11731/j.issn.1673-193x.2016.08.015]
 CHEN Wei,WEN Jinfeng,QIAN Chengjiang.Study on simulation and prediction of risk perception for enterprise decision-maker in chemical accident[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2016,12(10):92.[doi:10.11731/j.issn.1673-193x.2016.08.015]
[3]魏利军,王向阳,罗艾民,等.基于贝叶斯网络的化工园区地震次生灾害情景分析[J].中国安全生产科学技术,2017,13(12):73.[doi:10.11731/j.issn.1673-193x.2017.12.011]
 WEI Lijun,WANG Xiangyang,LUO Aimin,et al.Scenario analysis on secondary disasters of earthquake in chemical industry park based on Bayesian network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2017,13(10):73.[doi:10.11731/j.issn.1673-193x.2017.12.011]

备注/Memo

备注/Memo:
收稿日期: 2019-05-10;数字出版日期: 2019-10-26
* 基金项目: 国家自然科学基金项目(51474193)
作者简介: 牛毅,硕士研究生,主要研究方向为工业安全管理、事故致因分析。
通信作者: 樊运晓,博士,教授,主要研究方向为事故预防、系统安全工程、风险管理。
更新日期/Last Update: 2019-11-05