中国安全科学学报 ›› 2024, Vol. 34 ›› Issue (3): 84-92.doi: 10.16265/j.cnki.issn1003-3033.2024.03.0679

• 安全工程技术 • 上一篇    下一篇

面向飞行全过程的民航事故致因关联网络分析

刘丹1,2,3(), 罗颜声1,2,3, 李诗轩1,2,3,**(), 许钢焱4, 李墨潇1,2,3   

  1. 1 武汉理工大学 湖北隆中实验室,湖北 襄阳 441022
    2 武汉理工大学 中国应急管理研究中心,湖北 武汉 430070
    3 武汉理工大学 安全科学与应急管理学院,湖北 武汉 430070
    4 香港理工大学 工程学院,香港 999077
  • 收稿日期:2023-09-14 修回日期:2023-12-20 出版日期:2024-03-28
  • 通讯作者:
    ** 李诗轩(1993—),女,湖北十堰人,博士,副教授,主要从事知识组织与情报分析、应急舆情分析与文本挖掘方面的研究。E-mail:
  • 作者简介:

    刘丹 (1985—),男,湖南邵阳人,博士,教授,博士生导师,主要从事公共安全与应急管理、机器学习与智能计算、风险评估与应急决策方面的研究。E-mail:

    许钢焱,助理教授。

    李墨潇,副教授。

  • 基金资助:
    国家社会科学基金一般项目(23BGL280); 国家自然科学基金青年项目(72204194); 国家自然科学基金青年项目(52209146)

Causes and correlation network analysis of civil aviation accidents for whole flight phases

LIU Dan1,2,3(), LUO Yansheng1,2,3, LI Shixuan1,2,3,**(), XU Gangyan4, LI Moxiao1,2,3   

  1. 1 Hubei Longzhong Laboratory, Wuhan University of Technology, Xiangyang Hubei 441022, China
    2 China Research Center for Emergency Management, Wuhan University of Technology, Wuhan Hubei 430070, China
    3 School of Safety Science and Emergency Management, Wuhan University of Technology, Wuhan Hubei 430070, China
    4 Faculty of Engineering, The Hong Kong Polytechnic University, Hong Kong 999077, China
  • Received:2023-09-14 Revised:2023-12-20 Published:2024-03-28

摘要:

为提升我国民航安全水平,面向“滑行—起飞—爬升—巡航—下降—进近与着陆”的飞行全过程,提出一种基于关联规则和社会网络分析(SNA)的致因分析方法。首先,搜集中国民航安全信息系统2010—2022年共1 051起民航事故案例,结合《控制航行服务程序—培训》,建立基于“人—机—环—管”的民航事故致因体系;其次,采用EasyData数据服务平台进行标注,构建面向飞行全过程的民航事故致因数据集,基于FP-Growth算法挖掘以飞行阶段为规则后项的关联规则;最后,考虑关联规则的共现频率,构建民航事故致因关联网络,开展飞行阶段与事故致因的中心性分析。结果表明:进近与着陆阶段是飞行过程中风险最大的阶段,运行失效、跑道安全事故和客舱安全事故是主要事故类型,在挖掘出的10个民航事故关键致因因素中,人为因素4个、设施设备因素 2个、 环境因素3个、 管理因素1个。

关键词: 飞行全过程, 民航事故, 事故致因, 关联网络, 社会网络分析(SNA)

Abstract:

In order to improve the safety level of China Civil Aviation, a cause analysis method, which focused on the whole process of 'taxiing-takeoff-climbing-cruising-falling-approaching and landing', was proposed based on association rules and SNA. Firstly, a total of 1 051 civil aviation accident cases from 2010 to 2022 were collected from Aviation Safety Information System. Then, a civil aviation accident causation index system based on 'human-machine-environment-management' was established in combination with 'control navigation service procedure-training'. Secondly, the EasyData data service platform was used for annotation, followed by constructing the data-set of the cause of civil aviation accidents facing the whole process of flight. Furthermore, the FP-Growth algorithm was employed to mine the association rules with the flight phase as the subsequent term of rules. Finally, this study emphasized the co-occurrence frequency of association rules, and developed the correlation network of civil aviation accident causes by applying the centrality analysis of flight phase and accident causes. The results show that the most dangerous phases of flight are the approach and landing. Operation failures, runway safe accidents and cabin safe accidents are the main types. Among the 10 identified causes of civil aviation accidents, there are 4 human factors, 2 facilities and equipment factors, 3 environmental factors and 1 management factor.

Key words: whole flight process, civil aviation accidents, cause of accident, correlation network, social network analysis(SNA)

中图分类号: