基于QAR的民机异常飞行模式识别及风险评价模型

doi:10.16265/j.cnki.issn1003-3033.2025.02.0779

摘要/Abstract

摘要：

为实时评估与监测飞行风险,利用聚类分析方法挖掘快速存取记录器(QAR)数据蕴含的异常模式,分析民机异常飞行模式的影响因素;以欧氏距离表征QAR参数样本之间的相似性,建立基于K-means的异常飞行模式识别模型,定义异常模式偏离程度;基于全球商用喷气式飞机致命事故起数和死亡人数占比,结合异常模式偏离程度、异常模式持续时间、飞行阶段、安全不期望事件发生的可能性和安全不期望事件发生后果严重程度,提出一种基于QAR数据的民机飞行风险量化评价方法;使用某航空公司实际飞行QAR数据,通过实例验证民机异常飞行模式识别和风险量化模型的可行性。结果表明:异常模式多出现在巡航阶段及各飞行阶段交替临界时刻,不同航班不同飞行阶段异常飞行模式及风险分布差异明显,航班总风险值均值为166.94,但异常值高于386.97,滑跑起飞阶段的异常飞行风险相对偏低,均值为5.95;巡航阶段的异常飞行风险相对偏高,均值为93.46。

关键词: 快速存取记录器(QAR), 民机异常飞行, 模式识别, 风险评价, 聚类分析

Abstract:

In order to assess and monitor flight risks in real-time, clustering analysis was utilized to explore the abnormal patterns embedded in QAR data, and the influencing factors of abnormal flight patterns of civil aircraft were analyzed. The Euclidean distance was employed to characterize the similarity between samples of QAR parameters, establishing an abnormal flight pattern recognition model based on K-means to define the deviation degree of abnormal patterns. By considering the number of fatal accidents and the proportion of deaths in global commercial jet accidents, in conjunction with the deviation degree of abnormal patterns, the duration of abnormal patterns, flight phases, the likelihood of unexpected safety events, and the severity of consequences following unexpected safety events, a quantified assessment method for civil aviation flight risks based on QAR data was proposed. The feasibility of abnormal flight pattern recognition and risk quantification models for civil aircraft was validated through the practical QAR data of a certain airline. The results indicate that abnormal patterns are more prevalent during the cruising phase and critical moments at the transitions between flight phases. Significant differences are observed in the distribution of abnormal flight patterns and risks across different flights and flight phases. The average total risk value for flights is 166.94, with outliers exceeding 386.97. The abnormal flight risk during the takeoff roll phase is relatively low, with an average of 5.95, while the risk during the cruising phase is relatively high, with an average of 93.46.

Key words: quick access recorder(QAR), abnormal flight of civil aircraft, pattern recognition, risk assessment, cluster analysis

中图分类号:

X949

王菲茵, 袁锦彤, 刘笑辰, 谭维, 汪磊. 基于QAR的民机异常飞行模式识别及风险评价模型[J]. 中国安全科学学报, 2025, 35(2): 160-167.

WANG Feiyin, YUAN Jintong, LIU Xiaochen, TAN Wei, WANG Lei. Pattern identification and risk assessment model of civil aircraft abnormal flight based on QAR[J]. China Safety Science Journal, 2025, 35(2): 160-167.

图/表 6

图1

图2

图3

图4

图5

表1

参考文献 24

[1]	LYU Hao, YUJianjun, ZHU Tongyu. A novel method of overrun risk measurement and assessment using large scale QAR data[C]. IEEE Fourth International Conference on Big Data Computing Service and Applications, 2018: 213-220.
[2]	REY M, ALOISE D, SOUMIS F, et al. A data-driven model for safety risk identification from flight data analysis[J]. Transportation Engineering, 2021, 5: DOI: 10.1016/J.TRENG.2021.100087.
[3]	BARRY D J. Estimating runway veer-off risk using a Bayesian network with flight data[J]. Transportation Research Part C: Emerging Technologies, 2021, 128: DOl:10.1016/J.TRC.2021.103180.
[4]	CHANG Yuhern, YANG Huihua, HSIAO Y J. Human risk factors associated with pilots in runway excursions[J]. Accident Analysis & Prevention, 2016, 94: 227-237.
[5]	DISTEFANO N, LEONARDI S. Aircraft runway excursion features: a multiple correspondence analysis[J]. Aircraft Engineering and Aerospace Technology, 2019, 91(1):197-203. doi: 10.1108/AEAT-11-2017-0244
[6]	ALLAN J. A heuristic risk assessment technique for birdstrike management at airports[J]. Risk Analysis, 2010, 26(3): 723-729.
[7]	WANG Lei, WU Changxu, SUN Ruishan. An analysis of flight Quick Access Recorder (QAR) data and its applications in preventing landing incidents[J]. Reliability Engineering & System Safety, 2014, 127: 86-96.
[8]	WANG Lei, ZHANG Jingyi, DONG Chuanting, et al. A method of applying flight data to evaluate landing operation performance[J]. Ergonomics, 2019, 62(2):171-180. doi: 10.1080/00140139.2018.1502806 pmid: 30022708
[9]	孙瑞山, 刘胤甫. 基于QAR数据的飞行员飞行操作风格研究[J]. 中国安全科学学报, 2022, 32(12): 63-69. doi: 10.16265/j.cnki.issn1003-3033.2022.12.1169
	SUN Ruishan, LIU Yinfu. Research on pilots' flight operation style based on QAR data[J]. China Safety Science Journal, 2022, 32(12): 63-69. doi: 10.16265/j.cnki.issn1003-3033.2022.12.1169
[10]	孙瑞山, 陈雄, 梁妍. 基于高斯混合模型的飞机进近着陆阶段运行异常检测[J]. 安全与环境学报, 2022, 22(3): 1371-1376.
	SUN Ruishan, CHEN Xiong, LIANG Yan. Abnormal operation detection for approach and landing phase based on Gaussian mixture model[J]. Journal of Safety and Environment, 2022, 22(3): 1371-1376.
[11]	陈农田, 满永政, 李俊辉. 基于QAR数据的民机高高原进近着陆风险评估方法[J]. 北京航空航天大学学报, 2024, 50(1): 77-85.
	CHEN Nongtian, MAN Yongzheng, LI Junbui. Risk assessment method for civil aircraft approach and landing at high plateau based on QAR data[J]. Journal of Beijing University of Aeronautics and Astronautics, 2024, 50(1):77-85.
[12]	高扬, 王向章. 基于SPA-Markov的飞行安全态势评估与预测研究[J]. 中国安全生产科学技术, 2016, 12(8): 87-91.
	GAO Yang, WANG Xiangzhang. Research on assessment and prediction of flight safety situation based on SPA-Markov[J]. Journal of Safety Science and Technology, 2016, 12(8): 87-91.
[13]	王剑辉, 邓伟, 夏正洪, 等. 运输航空飞行安全风险评价方法[J]. 中国安全科学学报, 2019, 29(12): 110-116. doi: 10.16265/j.cnki.issn1003-3033.2019.12.018
	WANG Jianhui, DENG Wei, XIA Zhenghong, et al. Flight risk assessment method of transport aviation[J]. China Safety Science Journal, 2019, 29(12): 110-116. doi: 10.16265/j.cnki.issn1003-3033.2019.12.018
[14]	陈芳, 崔庆敏, 向千秋. 基于动态贝叶斯网络的民航空中停车事件安全风险评估[J]. 中国安全科学学报, 2023, 33(7):16-23. doi: 10.16265/j.cnki.issn1003-3033.2023.07.1884
	CHEN Fang, CUI Qingmin, XIANG Qianqiu. Safety risk assessment of civil aviation air parking events based on DBN[J]. China Safety Science Journal, 2023, 33(7): 16-23. doi: 10.16265/j.cnki.issn1003-3033.2023.07.1884
[15]	张兆宁, 陈子辰, 卢飞. 配对进近侧向位置误差QAR参数关联性分析[J]. 中国安全科学学报, 2021, 31(8): 47-52. doi: 10.16265/j.cnki.issn1003-3033.2021.08.007
	ZHANG Zhaoning, CHEN Zichen, LU Fei. Correlation analysis of QAR parameters for paired approach lateral position error[J]. China Safety Science Journal, 2021, 31(8): 47-52. doi: 10.16265/j.cnki.issn1003-3033.2021.08.007
[16]	RONG Chuitian, OUYANG Shuxin, SUN Huabo. Anomaly detection in QAR data using VAE-LSTM with multihead self-attention mechanism[J]. Mobile Information Systems, 2022, 1: DOI: 10.1155/2022/8378187.
[17]	JIA Bo, WEI Chuanfeng, MAO Jianfeng, et al. Identification of flight state under different simulator modes using improved diffusion maps[J]. Optik-International Journal for Light and Electron Optics, 2016, 127(9): 3905-3911.
[18]	NASERI A, NEOGI N, RANTANEN E. Stockastic hybrid models with applications to air traffic management[C]. Aiaa Guidance, Navigation & Control Conference & Exhibit, 2007: DOI: 10.2514/6.2007-6696.
[19]	吴奇, 储银雪. 基于深度学习的航空器异常飞行状态识别[J]. 民用飞机设计与研究, 2017(3): 68-78.
	WU Qi, CHU Yinxue. Abnormal flight states of aircraft ldentification based on deep learning[J]. Civil Aircraft Design & Research, 2017(3): 68-78.
[20]	郑磊, 池宏, 邵雪焱. 基于QAR数据的飞行操作模式及其风险分析[J]. 中国管理科学, 2017, 25(10): 109-118.
	ZHENG Lei, CHI Hong, SHAO Xueyan. Pattern recognition and risk analysis for flight operations[J]. Chinese Journal of Management Science, 2017, 25(10): 109-118.
[21]	彭宇, 何永福, 王少军, 等. 飞行数据异常检测技术综述[J]. 仪器仪表学报, 2019, 40(3): 1-13.
	PENG Yu, HE Yongfu, WANG Shaojun, et al. Flight data anomaly detection: a survey[J]. Chinese Journal of Scientific Instrument, 2019, 40(3): 1-13.
[22]	王洁宁, 孙禾, 赵元棣. 面向终端区航空器飞行状态识别的HMM方法[J]. 航空计算技术, 2013, 43(2): 1-5.
	WANG Jiening, SUN He, ZHAO Yuandi. ldentification of aircraft flight mode in terminal area based on hidden markov mode[J]. Aeronautical Computing Technique, 2013, 43(2): 1-5.
[23]	李军亮, 胡国才, 韩维, 等. 基于Elman网络的某型直升机飞行状态识别[J]. 火力与指挥控制, 2015 (12): 57-60.
	LI Junliang, HU Guocai, HAN Wei, et al. Helicopter flight condition recognition based on Elman neural network[J]. Fire Control & Command Control, 2015 (12): 57-60.
[24]	熊邦书, 刘雨, 莫燕, 等. 基于SVM的直升机飞行状态识别[J]. 应用科学学报, 2016, 34(4): 469-474.
	XIONG Bangshu, LIU Yu, MO Yan, et al. Recognition of helicopter flight condition based on support vector machine[J]. Journal of Applied Sciences, 2016, 34(4): 469-474.

航班	采样点	标准气压高度/ft	面板俯仰姿态/(°)	空/地时前轮状态	1号协调N1指数/ (r·min^-1)	襟翼把手位置/(°)	综合无线电高度/ft	空地开关状态
A	10 853	-171	11.95	0	96	5	9	1
A	110 737	30 101	2.11	1	83	0	4 040	1
A	143 529	-352	2.46	0	30	30	0	1
B	15 969	-287	17.05	0	91	5	56	1
B	61 841	36 100	2.64	1	86	0	5 500	1
B	151 457	6 989	-0.88	0	73	30	-4	0
C	12 850	-334	11.43	0	86	5	11	1
C	28 805	33 108	2.46	1	83	0	5 500	1
C	98 609	33	0.88	0	67	30	-3	0