|本期目录/Table of Contents|

[1]周志鹏,诸泽宇.基于事件提取和改进MMHC的航空旅客运输事故征候贝叶斯网络建模*[J].中国安全生产科学技术,2021,17(2):152-158.[doi:10.11731/j.issn.1673-193x.2021.02.024]
　ZHOU Zhipeng,ZHU Zeyu.Bayesian network modeling of aviation passenger transport incident based on event extraction and improved MMHC[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2021,17(2):152-158.[doi:10.11731/j.issn.1673-193x.2021.02.024]
点击复制

基于事件提取和改进MMHC的航空旅客运输事故征候贝叶斯网络建模*
分享到：

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

卷:
17
期数:
2021年2期
页码:
152-158
栏目:
职业安全卫生管理与技术
出版日期:
2021-02-28

文章信息/Info

Title:
Bayesian network modeling of aviation passenger transport incident based on event extraction and improved MMHC
文章编号:
1673-193X(2021)-02-0152-07
作者:
周志鹏; 诸泽宇
(南京航空航天大学 经济与管理学院，江苏 南京 211189)
Author(s):
ZHOU Zhipeng;  ZHU Zeyu
(Department of Economics and Management,Nanjing University of Aeronautics and Astronautics,Nanjing Jiangsu 211189,China)
关键词:
航空安全; 贝叶斯网络; 事故征候; 致因事件; 事件提取
Keywords:
aviation safety;  Bayesian network;  aviation incident;  causal event;  event extraction
分类号:
X949
DOI:
10.11731/j.issn.1673-193x.2021.02.024
文献标志码:
A
摘要:
为表征航空旅客运输事故征候演化机理，提出事故征候贝叶斯网络的建模方法。基于事故征候中致因事件、结果事件及分类标准的定义，以7 265起事故征候案例为样本，利用事件提取算法，识别事故征候叙述文本中的致因事件，利用改进的最大最小爬山算法实现网络建模；依据事件提取的测试集验证与结构学习的交叉验证，检验建模算法的准确性与有效性；基于证据敏感性指标，识别关键致因事件。结果表明：航空旅客运输事故征候贝叶斯网络模型包含94个节点和247条有向弧。空降冲突、严重设备故障、机组成员疾病及火灾烟雾是模型中高风险关联的致因事件，在安全监管过程中消除或减弱关键致因事件的发生能有效控制系统风险。
Abstract:
To characterize the evolution mechanism of aviation passenger transportation incidents,a Bayesian network modeling method for the aviation incidents was proposed.Based on the definition of the causal event,result event and classification criteria in the incident,taking 7265 incident cases as samples,the event extraction algorithm was used to identify the causal event in the incident narrative text,and the improved maximum and minimum hill climbing algorithm was applied to realize the network modeling.According to the test set validation of event extraction and the cross validation of structural learning,the accuracy and effectiveness of the modeling algorithm were verified.The key cause events were identified on the basis of evidence sensitive indexes.The results showed that the Bayesian network model of aviation passenger transportation incidents contained 94 nodes and 247 directed arcs.The airborne conflicts,serious equipment faults,crew member diseases,and fire smoke were the highrisk associated causal events in the model.Eliminating or reducing the occurrence of key causal events in the safety supervision process can effectively control the system risk.

参考文献/References:

［1］AYRA E S,ROSINSUA D,CANO J.Bayesian network for managing runway overruns in aviation safety ［J］.Journal of Aerospace Information Systems,2019,16(12):546-558.
［2］魏志强,吴金栋,刘馨泽,等.空中交通尾流间隔标准的安全性评估分析［J］.中国安全生产科学技术,2018,14(12):180-185. WEI Zhiqiang,WU Jindong,LIU Xinze,et al.Safety assessment and analysis on standard of wake separation for air traffic ［J］.Journal of Safety Science and Technology,2018,14(12):180-185.
［3］王晴昊,胡剑波,姚登凯.STPA在进近着陆飞行安全分析中的研究及应用［J］.系统工程理论与实践,2018,38(10):2703-2712. WANG Qinghao,HU Jianbo,YAO Dengkai.Research and application of STPA to flight safety analysis in approach and landing ［J］.System Engineering Theory & Practice,2018,38(10):2703-2712.
［4］康瑞,杨凯.考虑等待位置的航空器交叉滑行冲突概率模型［J］.中国安全生产科学技术,2019,15(8):64-69. KANG Rui,YANG Kai.Model on conflict probability of aircraft cross-taxiing considering holding position ［J］.Journal of Safety Science and Technology,2019,15(8):64-69.
［5］ZHANG X,MAHADEVAN S.Ensemble machine learning models for aviation incident risk prediction ［J］.Decision Support Systems,2019,116(1):48-63.
［6］DINIS D,TEIXEIRA A P,SOARESC G.Probabilistic approach for characterising the static risk of ships using Bayesian networks ［J］.Reliability Engineering & System Safety,2020,203:107073.
［7］ARNALDO V R,GMEZ C V,PEREZ S,et al.Prediction of aircraft safety incidents using Bayesian inference and hierarchical structures ［J］.Safety Science,2018,104:216-230.
［8］RAO A H,MARAIS K.High risk occurrence chains in helicopter accidents ［J］.Reliability Engineering & System Safety,2018,170:83-98.
［9］覃璇,李仲学,赵怡晴.尾矿库风险演化复杂网络模型及关键隐患分析［J］.系统工程理论与实践,2017,37(6):1648-1653. QIN Xuan,LI Zhongxue,ZHAO Yiqing.A complex network model for analyzing risks and major hazards of tailing impoundments ［J］.System Engineering Theory & Practice,2017,37(6):1648-1653.
［10］RODRIGUEZ S ,COMENDADOR F G,VALDS R A,et al.Assessment of airport arrival congestion and delay:prediction and reliability ［J］.Transportation Research Part C:Emerging Technologies,2019,98:255-283.
［11］ROSTAMABADI A,JAHANGIRI M,ZAREI E,et al.A novel fuzzy Bayesian network-HFACS (FBN-HFACS) model for analyzing Human and Organization Factors (HOFs) in process accidents ［J］.Process Safety and Environmental Protection,2019,132:59-72.
［12］ZOU X,YUE W L.A Bayesian network approach to causation analysis of road accidents using netica ［J］.Journal of Advanced Transportation,2017,2017:1-18.
［13］KABIR S,PAPADOPOULOS Y.Applications of Bayesian networks and Petri nets in safety,reliability,and risk assessments:areview ［J］.Safety Science,2019,115:154-175.
［14］RECASENS M,HOVY E.Blanc:implementing the rand index for coreference evaluation ［J］.Natural Language Engineering,2011,17(4):485-510.
［15］TANG C,YANG X,LV J,et al.Zero-shot learning by mutual information estimation and maximization［J］.Knowledge-Based Systems,2020,194:105490.
［16］TANG D,WEI F,QIN B,et al.Sentiment embeddings with applications to sentiment analysis［J］.IEEE Transactions on Knowledge and Data Engineering,2015,28(2):496-509.
［17］DEVLIN J,CHANG M W,LEE K,et al.BERT:pre-training of deep bidirectional transformers for language understanding［C］// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Stroudsburg:Association for Computational Linguistics,2018:4171-4186.
［18］李硕豪,张军.贝叶斯网络结构学习综述［J］.计算机应用研究,2015,32(3):641-646. LI Shuohao,ZHANG Jun.Review of Bayesian networks structure learning ［J］.Application Research of Computers,2015,32(3):641-646.

相似文献/References:

[1]魏〓麟,周长春,谢〓果.一种基于贝叶斯网络的机务维修差错调查模型算法[J].中国安全生产科学技术,2012,8(8):102.
　WEI Lin,ZHOU Chang chun,XIE Guo.Method on investigation model of aircraft maintenance human error based on bayesian network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(2):102.
[2]陈艳秋,史亚杰,张元.航空安全科技支撑体系建设的问题和对策[J].中国安全生产科学技术,2010,6(3):152.
　CHEN Yan-qiu,SHI Ya-jie,ZHANG Yuan.Problems and countermeasures on the construction of science and technology supporting system of civil Aviation safety in China[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(2):152.
[3]高扬,葛培荣,李阳.基于贝叶斯网络的航空器看错落错跑道事件研究[J].中国安全生产科学技术,2010,6(2):66.
　GAO Yang,GE Pei-rong,LI Yang.Analysis of take-off or landing wrong runway in civil airport based on bayesian network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(2):66.
[4]宋程成,孙瑞山,刘俊杰.自愿报告信息分析模型（CRIAM）研究[J].中国安全生产科学技术,2013,9(9):43.[doi:10.11731/j.issn.1673-193x.2013.09.008]
　SONG Cheng cheng,SUN Rui shan,LIU Jun jie.Research on confidential report information analysis model[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2013,9(2):43.[doi:10.11731/j.issn.1673-193x.2013.09.008]
[5]李盼,樊建春,刘书杰.基于故障树与贝叶斯网络的钻井井塌事故的定量分析[J].中国安全生产科学技术,2014,10(1):143.[doi:10.11731/j.issn.1673-193x.2014.01.024]
　LI Pan,FAN Jian chun,LIU Shu jie.Quantitative analysis of borehole collapse in drilling base on fault tree analysis and Bayesian networks[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(2):143.[doi:10.11731/j.issn.1673-193x.2014.01.024]
[6]姚锡文,许开立,王贝贝,等.石化装置火灾爆炸贝叶斯网络与防护层集成分析[J].中国安全生产科学技术,2014,10(3):95.[doi:10.11731/j.issn.1673-193x.2014.03.016]
　YAO Xi wen,XU Kai li,WANG Bei bei,et al.Integrative analysis of Bayesian networks and LOPA for fire and explosion in petrochemical plant[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(2):95.[doi:10.11731/j.issn.1673-193x.2014.03.016]
[7]陈华群,余 娟.基于改进贝叶斯的飞行签派安全评估研究[J].中国安全生产科学技术,2014,10(5):109.[doi:10.11731/j.issn.1673-193x.2014.05.019]
　CHEN Huaqun,YU Juan.Research on safety assessment of flight dispatch based on improved Bayesian[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(2):109.[doi:10.11731/j.issn.1673-193x.2014.05.019]
[8]马庆春,张继旺,张来斌.基于改进贝叶斯网络的加油站火灾爆炸分析[J].中国安全生产科学技术,2014,10(6):176.[doi:10.11731/j.issn.1673-193x.2014.06.029]
　MA Qing chun,ZHANG Ji wang,ZHANG Lai bin.Accident analysis of fire and explosion in gas station based on improved Bayesian Network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(2):176.[doi:10.11731/j.issn.1673-193x.2014.06.029]
[9]陈兆波,阴东玲,曾建潮,等.基于贝叶斯网络的煤矿事故人因推理[J].中国安全生产科学技术,2014,10(11):145.[doi:10.11731/j.issn.1673-193x.2014.11.025]
　CHEN Zhao-bo,YIN Dong-ling,ZENG Jian-chao,et al.Human factors inference of safety accidents in coal mine based on Bayesian network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(2):145.[doi:10.11731/j.issn.1673-193x.2014.11.025]
[10]施志坚,王华伟,徐璇.基于CREAM和贝叶斯网络的航空维修人为差错概率预测[J].中国安全生产科学技术,2015,11(4):185.[doi:10.11731/j.issn.1673-193X.2015.04.030]
　SHI Zhi-jian,WANG Hua-wei,XU Xuan.Prediction of human error probability in aviation maintenance based on CREAM and Bayesian network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(2):185.[doi:10.11731/j.issn.1673-193X.2015.04.030]

备注/Memo

备注/Memo:
收稿日期： 2020-12-13
* 基金项目： 国家自然科学基金项目(71871116)；中央高校基本科研业务费专项资金项目（NR2019006）；南京航空航天大学研究生创新基地开放基金项目（kfjj20190910）
作者简介： 周志鹏，博士，副教授，主要研究方向为工程安全事故网络建模、航空安全风险评估、事故预测理论与方法、险兆事件管理。
通信作者： 诸泽宇，硕士研究生，主要研究方向为航空安全管理、事故建模与分析。
更新日期/Last Update: 2021-03-11