基于贝叶斯网络的可控飞行撞地事件量化研究

中国民航大学学报 ›› 2023, Vol. 41 ›› Issue (2): 21-26.

基于贝叶斯网络的可控飞行撞地事件量化研究

刘俊杰，叶英豪，杜尹岚

（中国民航大学安全科学与工程学院，天津 300300）

收稿日期:2021-09-04 修回日期:2021-12-20 出版日期:2023-10-28 发布日期:2023-10-28
作者简介:刘俊杰（1971—），女，天津人，副研究员，硕士，研究方向为民航安全与飞行性能研究.

Quantification of controlled flight into terrain event based on Bayesian network

LIU Junjie, YE Yinghao, DU Yinlan

(College of Safety Science and Engineering, CAUC, Tianjin 300300, China)

Received:2021-09-04 Revised:2021-12-20 Online:2023-10-28 Published:2023-10-28

摘要/Abstract

摘要： 以可控飞行撞地（CFIT，controlledflightintoterrain）事件类型信息为研究对象，依照基元事件分析法分析CFIT事件演化过程，建立了事件后果层—飞机状态层—诱发因素层三层贝叶斯网络结构模型。以2017—2019年中国民航收集的CFIT事件和航空安全网（ASN，AviationSafetyNetwork）近20年（2000—2019年）CFIT事件数据为样本，利用样本统计数据确立网络节点参数，采用GeNIe软件选取贝叶斯网络已知节点与目标节点进行量化分析，得到目标节点可能性排序、最大可能性目标节点及影响强度；最终得出该类事件的关键风险环节，即飞行高度控制、机组丧失情景意识、飞行保障及相应节点的量化结果，为加强此类事件风险控制提供数据支持。

关键词: 航空安全信息, 信息量化, 可控飞行撞地, 贝叶斯网络, 风险控制

Abstract: Choosing the information of controlled flight into terrain(CFIT) as the research object, a three-layer Bayesian network model including event consequence layer, aircraft status layer and inducing layer is established according to the analysis of the CFIT event evolution process based on basic element analysis method. Taking the CFIT event data collected by civil aviation of China from 2017 to 2019 and Aviation Safety Network (ASN) in recent 20 years (2000-2019) as samples, the parameters of network nodes are established. The known nodes and target nodes of Bayesian network are selected by GeNIe for quantitative analysis, to obtain the possibility ranking, most probable target nodes and impact intensity of target nodes. Finally, the key risk processes of the CFIT, namely flight altitude control, crew loss of situational awareness, flight support and corresponding quantitative results, are obtained to provide data support for strengthening the risk control of the CFIT events.

Key words: aviation safety information, information quantification, controlled flight into terrain(CFIT), Bayesian network,
risk control

中图分类号:

V328
X949

刘俊杰, 叶英豪, 杜尹岚. 基于贝叶斯网络的可控飞行撞地事件量化研究[J]. 中国民航大学学报, 2023, 41(2): 21-26.

LIU Junjie, YE Yinghao, DU Yinlan. Quantification of controlled flight into terrain event based on Bayesian network[J]. Journal of Civil Aviation University of China, 2023, 41(2): 21-26.

参考文献 15

[1]	史亚杰, 陈艳秋．航空安全信息管理的问题与对策[J]．中国安全生产科学技术, 2010, 6(3): 116-120．
[2]	韩静茹．以风险管理为导向的航空安全信息管理探讨[J]．民航学报, 2018, 2(5): 50-53．
[3]	LIU Y C． A simulated study on the effects of information volume on traf－ fic signs, viewing strategies and sign familiarity upon driver′s visual search performance[J]． International Journal of Industrial Ergonomics, 2005, 35(12): 1147-1158．
[4]	张伟．基于信息熵的交通标志信息认知计算模型[J]．交通运输研究, 2015, 1(4): 56-65． [5] 张杉, 尹春华, 孙屹飞．商品评论的信息量化方法与计算[J]．北京信息科技大学学报(自然科学版), 2018, 33(5): 50-53．
[6]	周涛, 翟长旭, 高志刚．基于贝叶斯网络的高速公路预警系统研究[J]．公路工程, 2007, 32(4): 163-166．
[7]	张连文, 郭海鹏．贝叶斯网引论[M]．北京: 科学出版社, 2006．
[8]	KELLY D, EFTHYMIOU M． An analysis of human factors in fifty con－ trolled flight into terrain aviation accidents from 2007 to 2017[J]． Journal of Safety Research, 2019, 69: 155-165．
[9]	SMITH A, CASSELL R, YANG Y, et al． Feasibility demonstration of an aircraft performance risk assessment model[C]//19th Digital Avionics Systems Conference(DASC), October 7-13, 2000, Philadelphia, PA, USA. IEEE, 2000: 4D4/1-4D4/8.
[10]	汪磊, 孙瑞山. 可控飞行撞地(CFIT)的事故树分析(FTA)[C]//第六届全国交通运输领域青年学术会议论文集. 北京: 中国交通运输协会, 2005: 1120 -1123.
[11]	杜红兵, 王雪莉．基于贝叶斯网络的可控飞行撞地事故原因分析方法[J]．安全与环境学报, 2009, 9(5): 136-139．
[12]	LEE J． Modeling terrain awareness and warning systems for airspace and procedure design[C]//2012 IEEE/AIAA 31st Digital Avionics Sys－ tems Conference (DASC), October 14-18, 2012, Williamsburg, VA, US－ A． IEEE, 2012: 2B2-1．
[13]	WANG H F, WAN J, MIAO L Y． Research on controlled flight into ter－ rain risk analysis based on bow tie model and WQAR data [J]． DEStech Transactions on Engineering and Technology Research , 2017: 540 544．
[14]	中国民航科学技术研究院. 基于 WQAR 大数据的可控飞行撞地风险量化与预防研究[R]. 北京: 中国民航科学技术研究院, 2019.
[15]	刘汉辉, 孙瑞山, 张秀山．基元事件分析法[J]．中国民航学院学报, 1997, 15(3): 1-9