基于状态向量的危化品事故分析方法及应用
|
摘要
危险化学品行业属于高危险性行业,各类爆炸、火灾、泄漏和中毒事故时有发生.传统的基于因果关系的事故链分析方法受限于传统安全工程所依赖的技术基础和假定无法适应于今天所建造的复杂系统.本文以事故致因理论为基础,分析危化品事故形成的主要影响因素,构建了危化品事故状态向量,全面描述导致危化品事故发生的因素,并基于构建的状态向量进行危化品事故分析预测应用.利用高维向量对事故状态进行了定义,尽最大可能考虑了造成事故发生的众多因素,并利用支持向量机学习算法,建立事故预测模型.对已掌握的危化品事故进行的样本实验表明,本文提出的危化品事故预测方法,可有效快速的甄别事故状态,对危化品行业事故的预测预防具有积极意义.
Hazardous chemicals industry is a high risk industry. Explosion, fire, leakage, and poisoning accidents occur frequently. Traditional causality-based accident chain analysis method is limited by the technical basis and assumptions that traditional safety engineering relies on, and cannot adapt to today's complex systems. Based on the accident causation theory, this study analyses the main factors affecting the formation of dangerous chemicals accidents, constructs a state vector of dangerous chemicals accidents, describes the factors leading to dangerous chemicals accidents comprehensively,and uses the state vector to analyze and forecast dangerous chemicals accidents. The high dimension vector is used to define the accident state, and the most possible factors are considered. Using support vector machine learning algorithm,an accident prediction model is established by accident state vector. A sample test of the hazardous chemical accident shows that the method can differentiate accident state accurately and efficiently, and demonstrate a positive significance on accident prediction of hazardous chemicals.
Hazardous chemicals industry is a high risk industry. Explosion, fire, leakage, and poisoning accidents occur frequently. Traditional causality-based accident chain analysis method is limited by the technical basis and assumptions that traditional safety engineering relies on, and cannot adapt to today's complex systems. Based on the accident causation theory, this study analyses the main factors affecting the formation of dangerous chemicals accidents, constructs a state vector of dangerous chemicals accidents, describes the factors leading to dangerous chemicals accidents comprehensively,and uses the state vector to analyze and forecast dangerous chemicals accidents. The high dimension vector is used to define the accident state, and the most possible factors are considered. Using support vector machine learning algorithm,an accident prediction model is established by accident state vector. A sample test of the hazardous chemical accident shows that the method can differentiate accident state accurately and efficiently, and demonstrate a positive significance on accident prediction of hazardous chemicals.
引文
1任继勤,穆咏雪.危化品事故的统计分析与管理启示.化工管理,2015,(16):28-31.[doi:10.3969/j.issn. 1008-4800.2015.16.012]
2国家安监总局化学品登记中心.中国化学品安全网.http://accident.nrcc.com.cn, 2019.
3安世宁.安全生产“十三五”规划八大要点.中国安全生产,2017,(2):13-14.
4肖兴志,郭启光.中国危化品安全事故频发之谜一基于佩尔兹曼效应视角.财经问题研究,2012,(11):31-38.[doi:10.3969/j.issn.1000-176X.2012.11.005]
5陈宝智,吴敏.事故致因理论与安全理念.中国安全生产科学技术,2008, 4(1):42-46.
6 Leveson N. Engineering a Safer World:SystemsThinking Applied to Safety. Cambridge:MIT Press, 2011.
7 Abdulkhaleq A, Wagner S. A software safety verificationmethod based on system-theoretic process analysis.Bondavalli A, Ceccarelli A, Ortmeier F. Computer Safety,Reliability, and Security. Cham:Springer, 2014.[doi:10.1007/978-3-319-10557-4_44]
8郑小平,刘梦婷,李伟.事故预测方法研究述评.安全与环境学报,2008,8(3):162-169.[doi:10.3969/j.issn.1009-6094.2008.03.039]
9崔维,刘士竹.事故灾难类突发事件风险管理研究——以“11·22”中石化东黄输油管道泄漏爆炸特大事故为例.中国应急管理,2014,(6):16-21.
10陈悦,刘则渊,陈劲,等.科学知识图谱的发展历程.科学学研究,2008, 26(3):449-460.
11任利强,郭强,王海鹏,等.基于CiteSpace的人工智能文献大数据可视化分析.计算机系统应用,2018, 27(6):18-26.
12姬源,谢冬,周思明,等.电力领域语义搜索系统的构建方法.计算机系统应用,2016, 25(4):91-96.
13 Vapnik V. The Nature of Statistical Learning Theory. New York:Springer, 1995.
14 Cristianini N, Taylor JS. An Introduction to Support Vector Machines and other Kerner-based Learning Methods.Cambridge:University Press, 2004.
15萧嵘,王继成,孙正兴,等.一种SVM增量学习算法.南京大学学报(自然科学版),2002, 38(2):152-157.[doi:10.3321/j.issn:0469-5097.2002.02.004]
16张灿淋,姚明海,童小龙,等.一种新的基于KKT条件的错误驱动SVM增量学习算法.计算机系统应用,2014, 23(1):144-148.[doi:10.3969/j.issn.1003-3254.2014.01.028]
17 Burges CJC. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery,1998, 2(2):121-167.[doi:10.1023/A:1009715923555]
18周伟达,张莉,焦李成.支撑矢量机推广能力分析.电子学报,2001,29(5):590-594.[doi:10.3321/j.issn:0372-2112.2001.05.004]
19 Chang CC, Lin C J. LIBSVM:A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):27.
2国家安监总局化学品登记中心.中国化学品安全网.http://accident.nrcc.com.cn, 2019.
3安世宁.安全生产“十三五”规划八大要点.中国安全生产,2017,(2):13-14.
4肖兴志,郭启光.中国危化品安全事故频发之谜一基于佩尔兹曼效应视角.财经问题研究,2012,(11):31-38.[doi:10.3969/j.issn.1000-176X.2012.11.005]
5陈宝智,吴敏.事故致因理论与安全理念.中国安全生产科学技术,2008, 4(1):42-46.
6 Leveson N. Engineering a Safer World:SystemsThinking Applied to Safety. Cambridge:MIT Press, 2011.
7 Abdulkhaleq A, Wagner S. A software safety verificationmethod based on system-theoretic process analysis.Bondavalli A, Ceccarelli A, Ortmeier F. Computer Safety,Reliability, and Security. Cham:Springer, 2014.[doi:10.1007/978-3-319-10557-4_44]
8郑小平,刘梦婷,李伟.事故预测方法研究述评.安全与环境学报,2008,8(3):162-169.[doi:10.3969/j.issn.1009-6094.2008.03.039]
9崔维,刘士竹.事故灾难类突发事件风险管理研究——以“11·22”中石化东黄输油管道泄漏爆炸特大事故为例.中国应急管理,2014,(6):16-21.
10陈悦,刘则渊,陈劲,等.科学知识图谱的发展历程.科学学研究,2008, 26(3):449-460.
11任利强,郭强,王海鹏,等.基于CiteSpace的人工智能文献大数据可视化分析.计算机系统应用,2018, 27(6):18-26.
12姬源,谢冬,周思明,等.电力领域语义搜索系统的构建方法.计算机系统应用,2016, 25(4):91-96.
13 Vapnik V. The Nature of Statistical Learning Theory. New York:Springer, 1995.
14 Cristianini N, Taylor JS. An Introduction to Support Vector Machines and other Kerner-based Learning Methods.Cambridge:University Press, 2004.
15萧嵘,王继成,孙正兴,等.一种SVM增量学习算法.南京大学学报(自然科学版),2002, 38(2):152-157.[doi:10.3321/j.issn:0469-5097.2002.02.004]
16张灿淋,姚明海,童小龙,等.一种新的基于KKT条件的错误驱动SVM增量学习算法.计算机系统应用,2014, 23(1):144-148.[doi:10.3969/j.issn.1003-3254.2014.01.028]
17 Burges CJC. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery,1998, 2(2):121-167.[doi:10.1023/A:1009715923555]
18周伟达,张莉,焦李成.支撑矢量机推广能力分析.电子学报,2001,29(5):590-594.[doi:10.3321/j.issn:0372-2112.2001.05.004]
19 Chang CC, Lin C J. LIBSVM:A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2011, 2(3):27.