道路交通安全风险辨识与分析方法综述

寇敏; 张萌萌; 赵军学; 谢清民; 李鑫; 张荣林

doi:10.3963/j.jssn.1674-4861.2022.06.003

道路交通安全风险辨识与分析方法综述

doi: 10.3963/j.jssn.1674-4861.2022.06.003

寇敏^1,,
张萌萌^1, ,,
赵军学²,
谢清民²,
李鑫³,
张荣林⁴

1.
山东交通学院交通与物流工程学院济南 250357
2.
山东省公安厅交通管理局济南 250000
3.
山东高速交通建设集团股份有限公司济南 250101
4.
水发技术集团有限公司济南 250100

基金项目:

国家自然科学基金项目 52102412

全国统计科学研究项目 2021LY017

山东省自然科学基金项目 ZR202103040503

山东省自然科学基金项目 ZR2021QF110

济南市科学技术局项目 2019GXRC022

详细信息

作者简介:
寇敏(1994—), 硕士研究生.研究方向: 交通安全.E-mail: 1581839294@qq.com

通讯作者:
张萌萌(1981—), 博士, 教授.研究方向: 智能交通、交通规划等.E-mail: 573275197@qq.com

中图分类号: U491
计量
- 文章访问数: 1525
- HTML全文浏览量: 466
- PDF下载量: 185
- 被引次数: 0
出版历程
- 收稿日期: 2022-04-07
- 网络出版日期: 2023-03-27

A Review of Identification and Analysis Methods for Road Safety Risk

1.
School of Transportation and Logistics Engineering, Shandong Jiaotong University, Jinan 250357, China
2.
Traffic Management Bureau of Shandong Public Security Department, Jinan 250000, China
3.
Shandong High-speed Transportation Construction Group Co., LTD., Jinan 250101, China
4.
SHUIFA Technology Group Co.Ltd., Jinan 250100, China

摘要

摘要: 道路交通安全风险辨识及分析的准确性、全面性, 是实现风险主动防控的基础和关键环节, 直接影响道路交通安全管理的精细化水平。从影响因素和分析方法2个方面对道路交通安全风险相关研究进行综述和评论。针对人的不安全行为、车辆的不安全状态、道路的不安全条件、外界环境刺激等单因素风险, 以及多因素间的关联耦合风险辨识, 梳理了安全风险理论分析法、系统安全分析法、大数据与人工智能分析方法等道路交通安全风险分析方法。研究表明: 安全风险理论分析法、系统安全分析法等以定性分析为主的方法侧重于对道路交通安全风险要素的全面、系统梳理, 具有简单、直观、易操作等优势, 但在多因素交织影响下的道路交通事故定量化剖析和事故成因深度挖掘方面存在较多局限性; 基于多源数据挖掘技术的大数据与人工智能分析方法在海量信息感知、高效计算处理等方面优势明显, 可基于多元数据对交通安全风险进行综合分析、精准挖掘, 刻画多因素耦合下的事故风险特征、探究事故发生规律, 是当前较为主流的研究方向。并提出道路交通安全风险研究领域存在的不足之处及未来研究发展方向, 主要包括多源异构数据的动态采集与融合、智能网联环境下的道路交通安全风险辨识、考虑时空异质性的可移植的道路交通安全风险识别模型研究等。
- 交通安全 /
- 风险辨识 /
- 主动防控 /
- 事故预防
Abstract: The accuracy and comprehensiveness of road traffic safety risk identification and analysis is the basis and key link to achieve active risk prevention and control, and directly affects the refinement level of road traffic safety management. This paper summarizes and comments on the studies related to road traffic safety risk from two aspects of influencing factors and analysis methods. In a view of the single factor risk such as unsafe behavior of drivers, unsafe state of vehicles, unsafe conditions of roads, and external environmental stimulation, as well as the correlation and coupling risk identification among multiple factors, the road traffic safety risk analysis methods such as safety risk theoretical analysis method, system safety analysis method, big data and artificial intelligence analysis method are sorted out. The study shows that the qualitative analysis methods such as the safety risk theoretical analysis method and the system safety analysis method focus on the comprehensive and systematic analysis of the road traffic safety risk factors, and have the advantages of simplicity, directness, and ease of operation, but there are many limitations in the quantitative analysis of road traffic accidents and the deep excavation of accident causes under the influence of multiple factors. Big data and artificial intelligence analysis methods based on multi-source data mining technology have obvious advantages in massive information perception, efficient computing, and processing, and can comprehensively analyze and accurately mine traffic safety risks based on multiple data, depict accident risk characteristics under the coupling of multiple factors, and explore the rules of accident occurrence, which is the current mainstream research direction. It also points out the shortcomings in the field of road traffic safety risk research and the direction of future research and development, mainly including the dynamic collection and fusion of multi-source heterogeneous data, road traffic safety risk identification under the intelligent network environment, and the research of transplantable road traffic safety risk identification model considering space-time heterogeneity.
- traffic safety /
- risk identification /
- proactive prevention and control /
- accident prevention

HTML全文

图 1 道路交通安全风险影响因素及辨识分析方法框架

Figure 1. Influencing factors of road traffic safety risk and identification analysis method framework

下载: 全尺寸图片幻灯片

参考文献(45)

[1]	张树林, 凤鹏飞, 余皖生, 等. 基于风险管理的道路交通安全风险防控工程设计及应用[J]. 人类工效学, 2021, 27(1): 68-73. doi: 10.13837/j.issn.1006-8309.2021.01.0011 ZHANG S L, FENG P F, YU W S, et al. Design and application of road traffic safety risk prevention and control engineering based on risk management[J]. Chinese Journal of Ergonomics, 2021, 27(1): 68-73. (in Chinese) doi: 10.13837/j.issn.1006-8309.2021.01.0011
[2]	JONES C M, JONSSON I. Detecting emotions in conversations between driver and in-car information systems[C]. The1stInternational Conference on Affective Computing and Intelligent Interaction, Beijing: ACII, 2005.
[3]	张名芳, 马艳华, 吴初娜, 等. 公交驾驶员心理状况影响因素分析与疾病判别模型[J]. 交通运输系统工程与信息, 2021, 21(6): 96-104. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202106011.htm ZHANG M F, MA Y H, WU C N, et al. Analysis of influencing factors and disease discrimination model of bus drivers'psychological status[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(6): 96-104. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202106011.htm
[4]	黄晶, 彭扬, 黄烨, 等. 考虑噪声标签影响的驾驶员精神负荷状态评价[J]. 汽车工程, 2022, 44(5): 771-777. https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC202205013.htm HUNG J, PENG Y, HUANG Y, et al. State evaluation of driver mental load considering the influence of noise label[J]. Automotive Engineering, 2022, 44(5): 771-777. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-QCGC202205013.htm
[5]	马玉珍, 朱海燕, 朱琳, 等. 基于眼动特征及ECG的轨道交通驾驶员疲劳分析与识别[J]. 人类工效学, 2020, 26(3): 1-5+12. doi: 10.13837/j.issn.1006-8309.2020.03.0001 MA Y Z, ZHU H Y, ZHU L, et al. Analysis and identification of rail transit driver fatigue based on eye movement feature and ECG[J]. Chinese Journal of Ergonomics, 2020, 26(3): 1-5+12. (in Chinese) doi: 10.13837/j.issn.1006-8309.2020.03.0001
[6]	裴玉龙, 周侃, 张诚. 酒精作用下驾驶人心理生理及眼动特性分析[J]. 哈尔滨工业大学学报, 2011, 13(5): 80-86. doi: 10.3969/j.issn.1009-1971.2011.05.015 PEI Y L, ZHOU K, ZHANG C. Analysis of psychophysiological and eye movement characteristics of drivers under the influence of alcohol[J]. Journal of Harbin Institute of Technology, 2011, 13(5): 80-86. (in Chinese) doi: 10.3969/j.issn.1009-1971.2011.05.015
[7]	郭凤香, 熊昌安, 万华森, 等. 风险情境下老年驾驶人行为特性研究[J]. 中国公路学报, 2021, 34(9): 309-321. doi: 10.3969/j.issn.1001-7372.2021.09.026 GUO F X, XIONG C A, WAN H S, et al. Research on behavior characteristics of elderly drivers under risk situation[J]. China Journal of Highway and Transport, 2021, 34(9): 309-321. (in Chinese) doi: 10.3969/j.issn.1001-7372.2021.09.026
[8]	DOZZA M, GONZALEZ N P. Recognising safety critical events: Can automatic video processing improve naturalistic data analyses?[J]. Accident Analysis & Prevention, 2013, 60(11): 298-304.
[9]	SUN R, HAN K, HU J, et al. Integrated solution for anomalous driving detection based on BeiDou/GPS/IMU measurements[J]. Transportation Research Part C: Emerging Technologies, 2016, 69(8): 193-207.
[10]	翟俊达, 鲁光泉, 陈发城, 等. 城市交叉口车路网联信息对青年驾驶人驾驶行为的影响分析[J]. 交通信息与安全, 2022, 40(1): 126-134. doi: 10.3963/j.jssn.1674-4861.2022.01.015 ZHAI J D, LU G Q, CHEN F C, et al. Influence of vehicle network information on driving behavior of young drivers at urban intersections[J]. Journal of Transport Information and Safety, 2022, 40(1): 126-134. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2022.01.015
[11]	周洪亮, 贾凤娇, 刘志远, 等. 四轮独立驱动汽车驱动系统故障诊断与容错控制[J]. 机械工程学报, 2019, 55(22): 174-182. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201922018.htm ZHOU H L, JIA F J, LIU Z Y, et al. Fault diagnosis and fault tolerance control of four-wheel independent drive vehicle drive system[J]. Journal of Mechanical Engineering, 2019, 55(22): 174-182. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201922018.htm
[12]	彭能岭, 聂红朋, 王乾乾, 等. 自动驾驶车辆故障诊断系统研究与应用[J]. 轻工学报, 2020, 35(5): 87-95. https://www.cnki.com.cn/Article/CJFDTOTAL-ZZQB202005014.htm PENG N L, NIE H P, WANG G Q, etal. Research and application of fault diagnosis system for autonomous vehicle[J]. Journal of Light Industry, 2020, 35(5): 87-95. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZZQB202005014.htm
[13]	KLUGER R, SMITH B L, PARK H, et al. Identification of safety-critical events using kinematic vehicle data and the discrete fourier transform[J]. Accident Analysis & Prevention, 2016, 96(11): 162-168.
[14]	王雪松, 徐晓妍. 基于自然驾驶数据的危险事件识别方法[J]. 同济大学学报, 2020, 48(1): 51-59. https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ202001007.htm WANG X S, XU X Y. Hazardous event identification method based on natural driving data[J]. Journal of Tongji University, 2020, 48(1): 51-59. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-TJDZ202001007.htm
[15]	ZOU Y, TARKO A P. An insight into the performance of road barriers redistribution of barrier-relevant crashes[J]. Accident Analysis & Prevention, 2016, 96(11): 152-161.
[16]	RUSLI R, HAQUE M M, KING M, et al. Single-vehicle crashes along rural mountainous highways in Malaysia: An application of random parameters negative binomial model[J]. Accident Analysis & Prevention, 2017(102): 153-164.
[17]	陈昭明, 徐文远. 基于负二项分布的高速公路交通事故影响因素分析[J]. 交通信息与安全, 2022, 40(1): 28-35. doi: 10.3963/j.jssn.1674-4861.2022.01.004 CHEN Z M, XU W Y. Analysis of influencing factors of expressway traffic accidents based on negative binomial distribution[J]. Journal of Transport Information and Safety, 2022, 40(1): 28-35. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2022.01.004
[18]	宁航, 赵祥模, 南春丽, 等. 基于道路线形的智能汽车事故多发路段预判模型[J]. 中国公路学报, 2021, 34(3): 183-192. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202103013.htm NING H, ZHAO X M, NAN C L, et al. Predictive model of intelligent vehicle accident-prone road segment based on road alignment[J]. China Journal of Highway and Transport, 2021, 34(3): 183-192. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL202103013.htm
[19]	YUAN J, ABDEL-ATY M, WANG L, et al. Real-time crash risk analysis of urban arterials incorporating bluetooth, weather, and adaptive signal control data[C]. Transportation Research Board 97thAnnual Meeting, Washington, D. C. : TRB, 2018.
[20]	徐铖铖, 刘攀, 王炜, 等. 恶劣天气下高速公路实时事故风险预测模型[J]. 吉林大学学报, 2013, 43(1): 68-73. https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201301012.htm Xu C C, LIU P, WANG W, et al. Real-time accident risk prediction model for freeway under severe weather[J]. Journal of Jilin University, 2013, 43(1): 68-73. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JLGY201301012.htm
[21]	胡立伟, 杨锦青, 何越人, 等. 基于改进BP神经网络的城市交通拥塞环境下车辆运行风险识别研究[J]. 公路交通科技, 2019, 36(10): 105-113. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201910014.htm HU L W, YANG J Q, HE Y R, et al. Research on vehicle operation risk identification in urban traffic congestion based on improved BP neural network[J]. Journal of Highway and Transportation Research and Development, 2019, 36(10): 105-113. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201910014.htm
[22]	方雪洋. 混合交通环境下车速离散对交通安全的影响机理研究[D]. 南京: 东南大学, 2015. FANG X Y. Study on the influence mechanism of speed dispersion on traffic safety in mixed traffic environment[D]. Nanjing: Southeast University, 2015. (in Chinese)
[23]	姜宁. 基于我国现状的交通安全风险耦合分析[J]. 理论月刊, 2011(6): 102-106. https://www.cnki.com.cn/Article/CJFDTOTAL-LLYK201106028.htm JIANG N. Coupling analysis of traffic safety risk based on the current situation of china[J]. Theory Monthly, 2011(6): 102-106. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-LLYK201106028.htm
[24]	ABDEL-ATY M, RADWAN A. Modeling traffic accident occurrence and involvement[J]. Accident Analysis & Prevention, 2000, 32(5): 633-642.
[25]	张树林, 金会庆, 曾涛, 等. 重特大道路交通事故风险耦合模型的构建[J]. 人类工效学, 2019, 25(6): 40-43. https://www.cnki.com.cn/Article/CJFDTOTAL-XIAO201906008.htm ZHANG S L, JIN H Q, ZENG T, et al. Construction of coupled risk model for heavy and heavy road traffic accidents[J]. Chinese Journal of Ergonomics, 2019, 25(6): 40-43. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XIAO201906008.htm
[26]	WU W, JIANG S Y, LIU R H, et al. Economic development, demographic characteristics, road network and traffic accidents in Zhongshan, China: gradient boosting decision tree model[J]. Transportmetrica A: Transport Science, 2020, 16(3), 359-387.
[27]	王健宇, 陆化普, 孙智源, 等. 基于MNL模型的车车碰撞事故严重程度影响因素辨识方法[J]. 公路交通科技, 2021, 38(10): 107-113. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK202110014.htm WANG J Y, LU H P, SUN Z Y, et al. Identification method of influencing factors of vehicle-vehicle collision severity based on MNL model[J]. Journal of Highway and Transportation Technology, 2021, 38(10): 107-113. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK202110014.htm
[28]	郭璘, 周继彪, 董升, 等. 基于改进K-means算法的城市道路交通事故分析[J]. 中国公路学报, 2018, 31(4): 270-279. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201804032.htm GUO L, ZHOU J B, DONG S, et al. Analysis of urban road traffic accidents based on improved k-means algorithm[J]. China Journal of Highway and Transport, 2018, 31(4): 270-279. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGL201804032.htm
[29]	袁振洲, 郭曼泽, 彭泳鑫, 等. 基于梯度关联规则的老年行人交通事故风险识别[J]. 交通运输系统工程与信息, 2022, 22(1): 195-208. https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202201021.htm YUAN Z Z, GUO M Z, PENG Y X, et al. Traffic accident risk identification of elderly pedestrians based on gradient association rules[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(1): 195-208. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-YSXT202201021.htm
[30]	张亚东. 高速铁路列车运行控制系统安全风险辨识及分析研究[D]. 成都: 西南交通大学, 2013. ZHANG Y D. Study on safety risk identification and analysis of high-speed railway train operation control system[D]. Chengdu: Southwest Jiaotong University, 2013. (in Chinese)
[31]	陈赓, 刘茂, 李丽芬. 天津市道路交通风险分析及其应用[J]. 中国安全科学学报, 2006年, 16(5): 52-55. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK200605012.htm CHEN G, LIU M, LI L F. Risk analysis and application of tianjin road traffic[J]. China Safety Science Journal, 2006, 16(5): 52-55. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK200605012.htm
[32]	赵学刚. 城市道路交通安全综合风险预警控制研究[J]. 中国安全科学学报, 2016, 26(2): 158-163. https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK201602031.htm ZHAO X G. Study on comprehensive risk early warning and control of urban road traffic safety[J]. China Safety Science Journal, 2016, 26(2): 158-163. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-ZAQK201602031.htm
[33]	燕飞, 唐涛, 郜春海. 城市轨道交通安全评价体系研究[J]. 都市快轨交通, 2010, 23(3): 34-35. https://www.cnki.com.cn/Article/CJFDTOTAL-DSKG201802033.htm YAN F, TANG T, GAO C H. Research on safety evaluation system of urban rail transit[J]. Urban Rapid Rail Transit, 2010, 23(3): 34-35. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DSKG201802033.htm
[34]	徐志胜, 姜学鹏. 安全系统工程[M]. 北京: 机械工业出版社, 2012年. XU Z S, JIANG X P. Safety system engineering[M]. Beijing: China Machine Press, 2012.
[35]	李丽芬. 城市道路交通风险分析及其应用[D]. 天津: 南开大学, 2005. LI L F. Urban road traffic risk analysis and its application[D]. Tianjin: Nankai University, 2005. (in Chinese)
[36]	许海华. 因果分析图和AHP法在翻车事故成因分析中的应用[J]. 南昌大学学报, 2012, 36(1): 97-102. https://www.cnki.com.cn/Article/CJFDTOTAL-NCDL201201021.htm XU H H. Application of causal analysis graph and AHP method in cause analysis of rollover accident[J]. Journal of Nanchang University, 2012, 36(1): 97-102. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-NCDL201201021.htm
[37]	孟祥海, 柳昕汝. 山区高速公路伤亡事故故障树模型及事故成因分析[J]. 公路交通技术, 2018, 34(5): 118-125+131. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJT201805023.htm MENG X H, LIU X R. Failure tree model and cause analysis of casualty accident on mountain highway[J]. Technology of HighwayandTransport, 2018, 34(5): 118-125+131. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJT201805023.htm
[38]	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. doi: 10.3963/j.jssn.1674-4861.2021.04.006 ZHENG L, GU P, LU J. Cause analysis of heavy and heavy traffic accidents based on T-S fuzzy fault tree and bayesian network[J]. Journal of Transport Information and Safety, 2021, 39(4): 43-51+59. (in Chinese) doi: 10.3963/j.jssn.1674-4861.2021.04.006
[39]	罗文慧, 蔡凤田, 吴初娜, 等. 基于文本挖掘的道路运输安全风险源辨识模型[J]. 西南交通大学学报, 2020, 56(1): 147-152. https://www.cnki.com.cn/Article/CJFDTOTAL-XNJT202101019.htm LUO W H, CAI F T, WU C N, et al. Road transportation safety risk source identification model based on text mining[J]. Journal of Southwest Jiaotong University, 2020, 56(1): 147-152. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-XNJT202101019.htm
[40]	程宇航, 张健钦, 李江川, 等. 交通行业事故文本数据的可视化挖掘分析方法[J]. 计算机工程与应用, 2021, 57(21): 116-122. https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202121013.htm CHENG Y H, ZHANG J Q, LI J C, et al. Visual mining and analysis method of traffic accident text data[J]. Computer Engineering andApplications, 2021, 57(21): 116-122. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-JSGG202121013.htm
[41]	VOGEL K. A comparison of headway and time to collision as safety indicators[J]. Accident Analysis & Prevention, 2003, 35(3): 427-433.
[42]	潘勇, 唐自强, 龚贤武, 等. 基于行驶状态估计的车车协同纵向安全距离模型[J]. 公路交通科技, 2016, 33(7): 137-144. https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201607022.htm PAN Y, TANG Z Q, GONG X W, et al. Safety distance model of vehicle-vehicle cooperative longitudinal safety distance based on driving state estimation[J]. Journal of Highway and Transportation Technology, 2016, 33(7): 137-144. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-GLJK201607022.htm
[43]	KATRAKAZAS C, QUDDUS M, CHEN W H, et al. A new integrated collision risk assessment methodology for autonomous vehicles[J]. Accident Analysis & Prevention, 2019, 127(6): 61-79.
[44]	赵玮, 徐良杰, 冉斌, 等. 基于深度学习DBN算法的高速公路危险变道判别模型[J]. 东南大学学报, 2017, 47(4): 832-838. https://www.cnki.com.cn/Article/CJFDTOTAL-DNDX201704031.htm ZHAO W, XU L J, RAN B, et al. Identification model of dangerous lane change on expressway based on deep learning DBN algorithm[J]. Journal of Southeast University, 2017, 47(4): 832-838. (in Chinese) https://www.cnki.com.cn/Article/CJFDTOTAL-DNDX201704031.htm
[45]	SHI X P, WONG Y, LI M, et al. A feature learning approach based on XGBoost for driving assessment and risk prediction[J]. Accident Analysis & Prevention, 2019, 129(8): 170-179.