基于模糊贝叶斯网络的低空无人机运行风险评估

doi:10.16265/j.cnki.issn1003-3033.2024.08.1295

摘要/Abstract

摘要：

为解决目前城市低空环境下的无人机(UAV)运行安全风险问题,利用模糊贝叶斯网络(FBN)识别和评估低空无人机运行的关键风险因素。首先,在分析低空无人机运行流程基础上,从人-机-环-管角度分析低空无人机运行过程的风险因素。随后,利用GeNIe软件构建低空无人机运行风险评估贝叶斯网络(BN),利用专家先验知识和模糊集量化分析底事件的先验概率。最后,开展单因素分析、双因素分析以及敏感性分析,并以实例验证网络可行性。研究结果表明:低空无人机运行的关键风险因素为无人机电池故障、运行航线的环境障碍物以及无人机运行监管技术;FBN反向推理分析结果显示,环境相关风险(79%)、无人机设备风险(60%)是无人机运行过程主要风险因素。

关键词: 模糊贝叶斯网络(FBN), 低空无人机(UAV), 风险评估, 运行安全, GeNIe软件

Abstract:

To solve the current safety risk issues of UAV operations in low-altitude urban environments, a FBN was used to identify and analyze the key risk factors of low-altitude UAV operations. Firstly, risk factors were analyzed from the perspective of human-machine-environment-management based on operation process of low-altitude UAVs. GeNIe software was used to develop a Bayesian network(BN) for risk assessment of low-altitude UAV operations, and the prior probabilities of the underlying events were analyzed using expert prior knowledge and fuzzy sets. Finally, univariate, bivariate, and sensitivity analyses were performed, and the network feasibility was validated. The results indicated that the key risk factors for low-altitude UAV operation were UAV battery failure, environmental obstacles on the operation route, and UAV operation supervision technology. FBN reverse inference showed that environment-related risk (79%) and UAV equipment risk (60%) were the main risk factors in the UAV operation process.

Key words: fuzzy Bayesian network(FBN), low-altitude unmanned aerial vehicle(UAV), risk assessment, operation safety, GeNIe software

中图分类号:

X913.4安全系统工程

耿增显, 陈俊宇. 基于模糊贝叶斯网络的低空无人机运行风险评估[J]. 中国安全科学学报, 2024, 34(8): 53-60.

GENG Zengxian, CHEN Junyu. Risk assessment of low-altitude unmanned aerial vehicle operation based on fuzzy Bayesian network[J]. China Safety Science Journal, 2024, 34(8): 53-60.

图/表 17

图1

表1

图2

表2

图3

表3

表4

表5

表6

图4

图5

表7

图6

表8

图7

图8

图9

参考文献 16

[1]	HAN Peng, YANG Xinyue, ZHAO Yifei, et al. Quantitative ground risk assessment for urban logistical unmanned aerial vehicle (UAV) based on bayesian network[J]. Sustainability, 2022, 14(9):DOI:10.3390/2022/14095733.
[2]	ALLOUCH A, KOUBAA A, KHALGUI M, et al. Qualitative and quantitative risk analysis and safety assessment of unmanned aerial vehicles missions over the internet[J]. IEEE Access, 2019, 7:53 392-53 410.
[3]	耿增显, 杜星奇, 赵嶷飞, 等. 基于SORA方法城市物流无人机航路运行风险评估[C]. 第九届中国指挥控制大会论文集, 2021:468-473.
[4]	周忠宝. 基于贝叶斯网络的概率安全评估方法及应用研究[D]. 长沙: 国防科学技术大学, 2006.
	ZHOU Zhongbao. Research on methods and application of probabilistic safety assessment based on Bayesian networks[D]. Changsha: National University of Defense Technology, 2006.
[5]	马港, 徐晓楠, 郭小芳, 等. 基于贝叶斯网络的电镀企业火灾事故情景推演[J]. 中国安全科学学报, 2023, 33(2):202-208. doi: 10.16265/j.cnki.issn1003-3033.2023.02.0420
	MA Gang, XU Xiaonan, GUO Xiaofang, et al. Scenario deduction of fire accidents in electroplating enterprises based on Bayesian network[J]. China Safety Science Journal, 2023, 33(2):202-208. doi: 10.16265/j.cnki.issn1003-3033.2023.02.0420
[6]	贾晓惠, 王化姗, 崔用梅. 基于贝叶斯网络的公交车事故外因分析[J]. 科学技术与工程, 2021, 21(21):9 116-9 122.
	JIA Xiaohui, WANG Huashan, CUI Yongmei. Bayesian network-based bus accidents external causation analysis[J]. Science Technology and Engineering, 2021, 21(21): 9 116-9 122.
[7]	屈静, 张建彬, 李旭芳, 等. 基于贝叶斯网络的输油管道泄漏事故情景推演[J]. 中国安全科学学报, 2021, 31(1):192-198. doi: 10.16265/j.cnki.issn1003-3033.2021.01.028
	QU Jing, ZHANG Jianbin, LI Xufang, et al. Deduction of leakage accident scenarios of oil pipelines based on Bayesian network[J]. China Safety Science Journal, 2021, 31(1): 192-198. doi: 10.16265/j.cnki.issn1003-3033.2021.01.028
[8]	鲁义, 伍江乐, 邵淑珍, 等. 基于贝叶斯网络的危化品道路运输事故推理模型[J]. 中国安全科学学报, 2022, 32(3): 174-182. doi: 10.16265/j.cnki.issn1003-3033.2022.03.024
	LU Yi, WU Jiangle, SHAO Shuzhen, et al. Prediction model for road transport accidents of hazardous chemicals based on Bayesian network[J]. China Safety Science Journal, 2022, 32(3):174-182. doi: 10.16265/j.cnki.issn1003-3033.2022.03.024
[9]	陈雍君, 吴光晔, 张宇, 等. 基于模糊贝叶斯网络的城市地下综合管廊运维风险分析[J]. 安全与环境工程, 2021, 28(4):64-70.
	CHEN Yongjun, WU Guangye, ZHANG Yu, et al. Operation and maintenance of urban underground utility tunnels based on fuzzy Bayesian network[J]. Safety and Environmal Engineering, 2021, 28(4):64-70.
[10]	成连华, 魏凯, 曹东强. 基于模糊贝叶斯网络的高层建筑火灾风险评估方法[J]. 科学技术与工程, 2023, 23(13):5 707-5 714.
	CHENG Lianhua, WEI Kai, CAO Dongqiang. Fire risk assessment method of high-rise building based on fuzzy Bayesian network[J]. Science Technology and Engineering, 2023, 23(13):5 707-5 714.
[11]	郑来, 顾鹏, 卢健. 基于T-S模糊故障树和贝叶斯网络的重特大交通事故成因分析[J]. 交通信息与安全, 2021, 39(4):43-51,59.
	ZHENG Lai, GU Peng, LU Jian. A cause analysis of extraordinarily severe traffic crashes based on T-S fuzzy fault tree and Bayesian network[J]. Journal of Transport Information and Safety, 2021, 39(4): 43-51.
[12]	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.
[13]	蒋骏贤. 基于贝叶斯理论的危险源评估和分析方法研究[J]. 民航学报, 2023, 7(2):73-78.
	JIANG Junxian. Research on assessment and analysis methods of hazard sources based on Bayesian theory[J]. Journal of Civil Aviation, 2023, 7(2):73-78.
[14]	岳仁田, 韩蒙, 杨果果. 民用多旋翼无人机运行风险控制网络模型[J]. 中国安全生产科学技术, 2023, 19(5):209-214.
	YUE Rentian, HAN Meng, YANG Guoguo. Network model of operation risk control on civil multirotor UAV[J]. Journal of Safety Science and Technology, 2023, 19(5):209-214.
[15]	韩鹏, 王梦琦, 赵嶷飞. 基于贝叶斯网络的物流无人机失效风险评估[J]. 中国安全生产科学技术, 2020, 16(11):178-183.
	HAN Peng, WANG Mengqi, ZHAO Yifei. Failure risk assessment of logistics UAV based on Bayesian network[J]. Journal of Safety Science and Technology, 2020, 16(11):178-183.
[16]	李航, 聂芳艺. 基于贝叶斯网络的物流无人机碰撞风险评估[J]. 科学技术与工程, 2023, 23(15):6 700-6 706.
	LI Hang, NIE Fangyi. Collision risk assessment of logistics UAV based on bayesian network[J]. Science Technology and Engineering, 2023, 23(15):6 700-6 706.

无人机飞行事故报告	风险因素
起飞后爬升过程掉落,砸中围栏	机-环
油门异常,爬升姿态不稳定,操作员遥控着陆	人-机-管
下降发生抖动,降落时撞到围栏	机-环
监控到降落姿态不稳定,螺旋桨打到围栏	机-环-管
降落重试,爬升过程油门增大,无人机失控	机
监视到状态异常,启用应急程序后安全着陆	机-管
降落时发生转向,无人机失控侧翻碰撞到围栏	机-环
降落过程中姿态角过大,无人机紧急停浆	机
无人机航线监视异常,采取应急程序降落	机-管
降落重试时无人机姿态不稳定,执行应急降落	机-管
在终点未获得降落许可,应急降落撞到围栏	机-环-管
航路中无人机离线,应急程序降落碰到障碍物	机-环-管
无人机离线,未获得降落许可,采取应急程序	机-管
监视到飞行过程GPS更新频率低,应急备降	机-管
机载摄像头传图异常,操作员操作无人机迫降	人-机

序号	模糊语言	三角模糊数(l,m,n)
1	轻度影响	(0.0,0.1,0.3)
2	一般影响	(0.1,0.3,0.5)
3	中度影响	(0.3,0.5,0.7)
4	较大影响	(0.5,0.7,0.9)
5	重度影响	(0.7,0.9,1.0)

专家权重矩阵	E₁	E₂	E₃	E₄	相对权重e_j
E₁	1	2	4	5	0.445 6
E₂	1/2	1	3	4	0.333 5
E₃	1/4	1/3	1	2	0.136 1
E₄	1/5	1/4	1/2	1	0.084 7

点	三角模糊加权均值	点	三角模糊加权均值
X₁₁	(0.35,0.53,0.73)	X₃₁	(0.40,0.60,0.77)
X₁₂	(0.24,0.43,0.63)	X₃₂	(0.24,0.41,0.61)
X₂₁	(0.32,0.52,0.70)	X₃₃	(0.42,0.62,0.79)
X₂₂	(0.24,0.43,0.63)	X₃₄	(0.25,0.42,0.62)
X₂₃	(0.17,0.34,0.54)	X₄₁	(0.25,0.44,0.64)
X₂₄	(0.12,0.29,0.49)	X₄₂	(0.26,0.43,0.63)

节点因素	先验概率	节点因素	先验概率
X₁₁	0.54	X₃₁	0.59
X₁₂	0.43	X₃₂	0.42
X₂₁	0.52	X₃₃	0.61
X₂₂	0.43	X₃₄	0.43
X₂₃	0.35	X₄₁	0.44
X₂₄	0.30	X₄₂	0.44