Analysis of emergency response to cabin turbulence based on dynamic Bayesian network

doi:10.16265/j.cnki.issn1003-3033.2024.12.0411

Abstract

Abstract:

In order to effectively reduce the casualties and property losses caused by cabin turbulence, a decision analysis method based on a dynamic Bayesian network is proposed for cabin turbulence emergency response. Firstly, according to the relevant laws and regulations at domestic and international, combined with the emergency duties of key personnel on the ground and in the air, the turbulence emergency disposal process is analysed from pre-flight, in-flight and post-flight, and 24 key events are selected to construct a structured BT model. Secondly, the mapping conditions and transformation rules are established to form a DBN model. Then, the objective direct node a priori probability and the supplementary node fuzzy probability obtained by the triangular fuzzy probabilities of supplementary nodes obtained by the fuzzy number expert judgement method to obtain the a priori probabilities of all nodes. Finally, the time slice intervals of 1 and 2 min are selected to focus on the simulation inference of moderate and heavy turbulence, and to study the characteristics of the influence of each dynamic element on the failure of cabin turbulence event disposal. The results show that: the emergency response nodes are significantly affected by the degree of turbulence and time changes, and the optimal time for emergency response is within 5 min. Among them, the probability of failure for the failure of the crew fixation measures in place increases with the increase of the degree of turbulence, human factors such as the failure of the crew to fasten the seat belts and the over-servicing by the cabin crew are the key reasons for the failure of the response.

Key words: dynamic Bayesian network(DBN), turbulence event, emergency response, bow-tie(BT)model, triangular fuzzy number

CLC Number:

X928.03事故预防与预测

WU Yu, WU Xinyi, XIE Jiang. Analysis of emergency response to cabin turbulence based on dynamic Bayesian network[J]. China Safety Science Journal, 2024, 34(12): 203-212.

Figures/Tables 8

Fig.1

Table 1

Fig.2

Fig.3

Fig.4

Table 2

Node prior probability table

节点	直接节点先验概率 $P (C b)$		三角模糊数 $G = (k, l, u)$		补充节点模糊概率 $P g$		先验概率 $P A = 0.7 P (C b) + 0.3 P g$
节点	中度	重度	中度	重度	中度	重度	中度	重度
A₁₁₁	—	—	(0.012,0.010,0.005)	(0.100,0.150,0.050)	0.009	0.100	0.009	0.100
A₁₁₂	0.120	0.260	(0.100,0.020,0.039)	(0.400,0.450,0.320)	0.053	0.390	0.100	0.300
A₁₁₃	0.070	0.100	(0.210,0.100,0.107)	(0.150,0.100,0.050)	0.136	0.100	0.090	0.100
A₁₁₄	—	—	(0.011,0.100,0.107)	(0.110,0.130,0.060)	0.009	0.010	0.009	0.010
A₁₁₅	—	—	(0.120,0.800,0.055)	(0.050,0.150,0.100)	0.085	0.010	0.085	0.010
A₁₂₁	—	—	(0.120,0.050,0.100)	(0.120,0.120,0.060)	0.090	0.100	0.090	0.010
A₁₂₂	0.090	0.120	(0.100,0.120,0.149)	(0.180,0.240,0.240)	0.123	0.220	0.100	0.150
A₁₂₃	0.150	0.360	(0.350,0.354,0.244)	(0.400,0.450,0.620)	0.316	0.490	0.200	0.400
A₁₂₅	0.100	0.200	(0.120,0.100,0.060)	(0.520,0.490,0.580)	0.100	0.530	0.100	0.300
A₁₂₄₁	0.200	0.420	(0.280,0.310,0.310)	(0.500,0.530,0.530)	0.200	0.520	0.200	0.450
A₁₂₄₂	0.160	0.260	(0.300,0.340,0.330)	(0.420,0.380,0.370)	0.290	0.390	0.200	0.300
A₁₃₁	0.100	0.200	(0.100,0.120,0.080)	(0.180,0.250,0.170)	0.100	0.200	0.100	0.200
A₁₃₂₁	0.100	0.250	(0.120,0.120,0.060)	(0.400,0.380,0.468)	0.100	0.416	0.100	0.300
A₁₃₂₂	0.140	0.350	(0.210,0.208,0.100)	(0.350,0.320,0.479)	0.173	0.383	0.150	0.360
A₁₃₃	0.160	0.420	(0.310,0.320,0.486)	(0.400,0.390,0.490	0.293	0.353	0.200	0.400
A₂₁₁	—	—	(0.100,0.100,0.100)	(0.100,0.100,0.100)	0.100	0.100	0.100	0.100
A₂₁₂	0.27	0.460	(0.310,0.320,0.486)	(0.400,0.390,0.490)	0.372	0.426	0.300	0.450
A₂₁₃	—	—	(0.100,0.100.0.100)	(0.150,0.210,0.240)	0.100	0.200	0.100	0.200
A₂₂₁	0.010	0.010	(0.010,0.010,0.010)	(0.001,0.001,0.001)	0.010	0.010	0.010	0.010
A₂₂₂	—	—	(0.030,0.040,0.080)	(0.030,0.040,0.080)	0.050	0.050	0.050	0.050
A₃₁	0.100	0.300	(0.100,0.150,0.050)	(0.250,0.300,0.350)	0.100	0.300	0.100	0.300
A₃₂	0.060	0.080	(0.020,0.032,0.029)	(0.042,0.030,0.066)	0.027	0.046	0.050	0.070
A₄₁	0.100	0.100	(0.120,0.100,0.080)	(0.120,0.100,0.080)	0.100	0.100	0.100	0.100
A₄₂	0.010	0.010	(0.010,0.010,0.010)	(0.010,0.010,0.010)	0.010	0.010	0.010	0.010

Table 2

Fig.5

Fig.6

References 26

[1]	DESKOS G, CARRE A D, PALACIOS R. Assessment of low-altitude atmospheric turbulence models for aircraft aeroelasticity[J]. Journal of Fluids and Structures, 2020, 95: DOI: 10.1016/j.jfluidstructs.2020.102981.
[2]	Aviation safety network (2017-2022)[DB/OL]. [2023-11-21].
[3]	HU Boyan, HUI Pinghong, DING Jinfeng, et al. Spatiotemporal characteristics of clear-air turbulence (CAT) potential in China during 1979-2020[J]. Climate Dynamics, 2023, 61: DOI: 10.1007/s00382-023-06684-z.
[4]	FAA-H-8083-25C, Pilot's handbook of aeronautical knowledge[S], 2023.
[5]	李朝潞, 吴俊杰, 万连成. 基于支持向量机的飞机颠簸预测方法研究[J]. 西安航空学院学报, 2022, 40(3):24-28.
	LI Chaolu, WU Junjie, WAN Liancheng. Research on aircraft turbulence prediction method based on support vector machine[J]. Journal of Xi'an Aeronautics University, 2022, 40 (3):24-28.
[6]	曾兵, 肖子龙, 董理, 等. 基于G-sensor实报的空中颠簸管理系统设计[J]. 民航学报, 2022, 6(4):77-81.
	ZENG Bing, XIAO Zilong, DONG Li, et al. Design of turbulence management system based on G-sensor actual report[J]. Journal of Civil Aviation, 2022, 6(4): 77-81.
[7]	WANG Qing, ZHENG Fengqi, QIAN Weiqi, et al. A practical filter error method for aerodynamic parameter estimation of aircraft in turbulence[J]. Chinese Journal of Aeronautics, 2023, 36 (2):17-18.
[8]	杜红兵, 张世博, 李弘毅, 等. 火灾场景下民机客舱人员疏散仿真及优化[J]. 中国安全生产科学技术, 2023, 19(2):187-194.
	DU Hongbing, ZHANG Shibo, LI Hongyi, et al. Simulation and optimization of personnel evacuation in civil aircraft cabin under fire scenario[J]. Journal of Safety Science and Technology, 2023, 19(2): 187-194.
[9]	张青松, 魏祥宇, 吴煜. 智能化民航安保的研究热点与发展趋势[J]. 交通信息与安全, 2023, 41(5):1-11.
	ZHANG Qingsong, WEI Xiangyu, WU Yu. A review of focus and development trends in intelligent civil aviation security[J]. Traffic Information and Security, 2023, 41 (5):1-11.
[10]	CANKAYA B, TOPUZ K, DELEN D, et al. Evidence-based managerial decision-making with machine learning: the case of Bayesian inference in aviation incidents[J]. Omega, 2023, 120: DOI: 10.1016/j.jfluidstructs.2020.102906.
[11]	MUECKLICH N, SIKORA I, PARAKEVAS A, et al. The role of human factors in aviation ground operation-related accidents/incidents: a human error analysis approach[J]. Transportation Engineering, 2023, 13: DOI:10.1016/j.treng.2023.100184.
[12]	MA Yaping, YUAN Jinfeng, TAN Lingling, et al. A model for aircraft cabin evacuation considering passenger type[J]. Journal of Safety Science and Resilience, 2024, 5(1): 83-90.
[13]	AC-121-FS—2009-35,关于制定空中颠簸管理程序防止人员伤害的要求[S].
[14]	CCAR-91-R4,一般运行和飞行规则[S]. 2022.
[15]	AC-121-FS-2011-004R1,航空承运人运行中心(AOC)政策与标准[S].
[16]	AC-121-FS-27-R3,客舱乘务员的资格和训练[S]. 2020.
[17]	余稼洋, 郭建胜, 周楚涵, 等. 基于Bow-tie-DT-FTA的航空安全事故预防措施决策分析[J]. 火力与指挥控制, 2022, 47(8):158-164.
	YU Jiayang, GUO Jiansheng, ZHOU Chuhan, et al. Decision-making analysis of preventive measures for aviation safety accidents based on Bow-tie-DT-FTA[J]. Fire Control &Command Control, 2022, 47(8): 158-164.
[18]	刘保占, 靳卫卫, 安伟, 等. 基于模糊Bow-tie模型的深水钻井平台井喷溢油风险评价[J]. 船海工程, 2020, 49(2):1-5.
	LIU Baozhan, JIN Weiwei, AN Wei, et al. Oil spill risk assessment for blowout of deepwater drilling platform based on fuzzy Bow--tie model[J]. Ship & Ocean Engineering, 2020, 49(2):1-5.
[19]	杨文安, 李佳欣. 基于动态贝叶斯网络的装配式建筑吊装施工安全风险分析[J]. 安全与环境学报, 2024, 24(4):1328-1336.
	YANG Wenan, LI Jiaxin. Safety risk analysis of hoisting construction of prefabricated buildings based on dynamic Bayesian network[J]. Journal of Safety and Environment, 2023, 24(4):1328-1336.
[20]	陈志煌, 刘国恒, 王莹莹, 等. 基于动态贝叶斯网络的水下连接器故障诊断[J]. 中国安全科学学报, 2020, 30(5):81-87. doi: 10.16265/j.cnki.issn1003-3033.2020.05.013
	CHEN Zhihuang, LIU Guoheng, WANG Yingying, et al. Fault diagnosis of subsea collet connector based on dynamic Bayesian network[J]. China Safety Science Journal, 2020, 30(5):81-87. doi: 10.16265/j.cnki.issn1003-3033.2020.05.013
[21]	张健, 罗鑫悦, 黎宗孝, 等. 基于动态贝叶斯网络的无人机航迹模型研究[J]. 中国安全生产科学技术, 2023, 19(11):188-193.
	ZHANG Jian, LUO Xinyue, LI Zongxiao, et al. Research on UAV trajectory modeling based on dynamic Bayesian network[J]. China Safety Production Science and Technology, 2023, 19(11):188-193.
[22]	岳文静, 杜丽敬, 陈先锋, 等. 基于DBN的气体泄漏事故情景推演与节点分析[J]. 中国安全科学学报, 2022, 32(增1):165-170.
	YUE Wenjing, DU Lijing, CHEN Xianfeng, et al. Scenario deduction and node analysis of gas leakage accidents based on DBN[J]. China Safety Science Journal, 2022, 32(S1):165-170. doi: 10.16265/j.cnki.issn1003-3033.2022.S1.0893
[23]	GUO Yunlong, JIN Yongxing, HU Shenping, et al. Risk evolution analysis of ship pilotage operation by an integrated model of FRAM and DBN[J]. Reliability Engineering & System Safety, 2023, 229:1-18.
[24]	KIZIELEWICZ B, DOBRYAKOVA L. Stochastic triangular fuzzy number (S-TFN) normalization: a new approach for nonmonotonic normalization[J]. Procedia Computer Science, 2023, 225:4901-4911.
[25]	张健健, 郭继坤, 费青竹. 基于主成分分析和三角模糊数的应急物资供应能力指标体系[J]. 兵工自动化, 2023, 42(11):68-72.
	ZHANG Jianjian, GUO Jikun, FEI Qingzhu. Index system of emergency material supply capacity based on principal component analysis and triangular fuzzy number[J]. Ordnance Industry Automation, 2023, 42(11):68-72.
[26]	GHAFFARI A, SAADAT R, MESIAR R. Fuzzy number-valued triangular norm-based decomposable time-stamped fuzzy measure and integration[J]. Fuzzy Sets and Systems, 2022, 430(28):144-173.

代号	事件	代号	事件	代号	事件	代号	事件
A	颠簸事件发生	A₁₁₁	判断颠簸等级失误	A₁₂₄₁	没有固定餐车	A₂₁₂	乘务人员过度服务
A₁	人为因素	A₁₁₂	机长没做好固定措施	A₁₂₄₂	乘务人员没有固定自己	A₂₁₃	机组人员心理问题
A₂	管理因素	A₁₁₃	没有对颠簸进行广播	A₁₃₁	没有遵守安全防护	A₂₂₁	法规制订缺漏
A₃	环境因素	A₁₁₄	没有进行三方会议	A₁₃₂	不在座椅上	A₂₂₂	监管力度不够
A₄	机载设备因素	A₁₁₅	机长疲劳飞行	A₁₃₂₁	没有抓紧扶手	A₃₁	天气环境恶劣
A₁₁	机长应急处置失效	A₁₂₁	乘务人员疲劳飞行	A₁₃₂₂	旅客没有固定自己	A₃₂	飞机无法绕开
A₁₂	乘务人员应急处置失效	A₁₂₂	没检查飞机物品固定	A₁₃₃	旅客没有系好安全带	A₄₁	固定装置故障
A₁₃	旅客应急失效	A₁₂₃	没有做好自身防护	A₂₁	内部原因	A₄₂	天气雷达故障
A₅	航前阶段	A₁₂₄	服务中处置失效	A₂₂	外部原因
A₆	航中阶段	A₁₂₅	乘务人员没有系好安全带	A₂₁₁	机组成员训练不合格