Accident Risk Identification and Impact Mechanisms in Nighttime
 Highway Maintenance Work Zones

doi:10.16097/j.cnki.1009-6744.2025.02.015

Abstract

Abstract: The complex and variable nighttime environment and constricted driving space significantly increase the risk of traffic accidents in maintenance work zones. To identify risk characteristics and capture the underlying relationships between influencing factors and accident risks, this study employs drone aerial footage to capture traffic flow videos of a nighttime maintenance work zone on a highway segment in Chongqing, China. The Tracker software is used to extract microscopic vehicle trajectory data, thereby revealing traffic flow characteristics such as spatiotemporal trajectories, vehicle speed, and headway distribution in nighttime maintenance work zones. The probability of accidents and the severity of potential accident consequences are evaluated based on time-and energy-based safety surrogate measures. Furthermore, an Extreme Gradient Boosting (XGBoost) algorithm was utilized to construct a Loss Energy Index (Z_LEI ) prediction model for vehicle collisions, and the SHAP (SHapley Additive exPlanations) algorithm was applied to quantify and interpret the impact mechanisms of features such as speed, headway, traffic conflicts, and deceleration rates to avoid collisions on the Z_LEI . The results indicate that headway distance shows a decreasing-then increasing trend from the warning zone to the transition zone. Severe rear-end collisions are highly prone to occur when headway distances are between 2.5 and 3.0 meters. Additionally, large trucks have a higher lane-changing risk compared to smaller vehicles. The key factors influencing Z_LEI include deceleration rate to avoid collisions, lane-changing conflicts (t^c _TTC ) , headway, speed, and travel time. When traffic flow exceeds 1000 pcu·h^-1 and vehicle speed falls within the range of (1.25, 2.50) m·s^-1, Z_LEI increases as the inter-vehicle distance decreases and the deceleration rate to avoid collisions rises. When traffic flow is below 1000 pcu·h^-1, and headway is within the range of (3.0, 8.0) seconds, Z_LEI increases with higher inverse time-to-collision ( 1 /t^c _TTC ) . For vehicle speeds within (12.5, 20.0) m·s^-1, Z_LEI increases with a rising Deceleration Rate to Avoid a Collision (A_DRAC ) .

Key words: traffic engineering, potential accident severity, collision loss energy index, highway nighttime maintenance work zones, vehicle trajectory data

摘要： 复杂多变的夜间环境和压缩的行驶空间显著增加养护作业区的交通事故风险。为辨析风险特征以及捕捉影响因素与事故风险的内在联系，本文通过无人机航拍重庆市某段高速公路夜间养护作业区的交通流视频，利用Tracker软件提取车辆微观轨迹数据，揭示夜间养护作业区时空轨迹、车速和车头时距分布等交通流特征；基于时间和能量的安全替代指标分别研判事故发生的可能性和潜在事故后果的严重性；最后，通过极限梯度提升算法(XGBoost)构建车辆碰撞损失能量指数(Z_LEI)预测模型，并结合SHAP(SHapley Additive exPlanations)算法量化解释速度、车头时距、交通冲突和避免碰撞减速度等特征因素对潜在碰撞损失能量指数的影响机理。结果表明，从警告区到过渡区的车头时距呈现先减小后增大的趋势，车头间距在2.5~3.0 m易发生严重追尾事故，大货车换道风险比小型车更大；避免碰撞减速度、换道冲突(t^c_TTC)、车头时距、速度和行程时间等是影响车辆Z_LEI的重要特征因素；当车流量大于1000pcu·h^-1，且车辆速度在(1.25, 2.50) m·s^-1范围时，Z_LEI随相邻车距离的减小而增大，随避免碰撞减速度的增大而增大；当车流量小于等于1000 pcu·h^-1 ，且车头时距在(3.0,8.0) s范围时，Z_LEI随1/ t^c_TTC的增大而增大，车辆速度在(12.5,20.0) m·s-1时，，Z_LEI随避免碰撞减速度(A_DRAC )的增大而增大。

关键词: 交通工程, 潜在事故严重程度, 碰撞损失能量指数, 高速公路夜间养护作业区, 车辆轨迹数据

CLC Number:

U491.31

ZHANG Heshan, ZENG Changkun, WANG Haiyang, TIAN Fengming, ZHENG Zhanji, ZHANG Yu. Accident Risk Identification and Impact Mechanisms in Nighttime Highway Maintenance Work Zones[J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 157-168.

张河山, 曾长坤, 王海洋, 田丰铭, 郑展骥, 张羽. 高速公路夜间养护作业区事故风险辨识及影响机理研究[J]. 交通运输系统工程与信息, 2025, 25(2): 157-168.

Add to citation manager EndNote|Ris|BibTeX

URL: http://www.tseit.org.cn/EN/10.16097/j.cnki.1009-6744.2025.02.015

http://www.tseit.org.cn/EN/Y2025/V25/I2/157

References

[1]杨洋,王文慧,吴先宇,等.高速公路非常规交通事故研究综述[J]. 应用基础与工程科学学报,2024,32(3): 601-626. [YANG Y, WANG W H, WU X Y, et al. Review of the research toward freeway unconventional traffic accidents[J]. Jorunal of Basic Science and Engineering, 2024, 32(3): 601-626.]

[2] ARDITI D, LEE D, POLAT G. Fatal accidents in nighttime vs. daytime highway construction work zones [J]. Journal of Safety Research, 2007, 38(4): 399-405.

[3] RANGASWAMY R, ALNAWMASI N, ZHANG Y. Analysis of injury severity of work zone crashes on rural and urban work zones: Accounting for out-of-sample prediction and temporal instability[J]. Accident Analysis &Prevention, 2024, 203: 107641.

[4] THEOFILATOS A, ZIAKOPOULOS A, PAPADIMITRIOU E, et al. Meta-analysis of the effect of road work zones on crash occurrence[J]. Accident Analysis & Prevention, 2017, 108: 1-8.

[5]ZHANG K, HASSAN M. Identifying the factors contributing to injury severity in work zone rear-end crashes[J]. Journal of Advanced Transportation, 2019, 2019(1): 4126102.

[6]吕能超,王玉刚,周颖,等.道路交通安全分析与评价方法综述[J]. 中国公路学报, 2023, 36(4): 183-201. [LV N C, WANG Y G, ZHOU Y, et al. Review of road traffic safety analysis and evaluation methods[J]. China Journal of Highway and Transport, 2023, 36(4): 183 201.]

[7]杨洋,贺昆,王云鹏,等.面向动态交通流的高速公路事故风险模型空间移植研究[J].交通运输系统工程与信息,2023, 23(3): 174-186. [YANG Y, HE K, WANG Y P, et al. Spatial transplantation for modeling of freeway traffic crash risk based on dynamic traffic flow[J]. Journal of Transportation Systems Engineering and Information Technology, 2023, 23(3): 174-186.]

[8]WENG J, XUE S, YANG Y, et al. In-depth analysis of drivers' merging behavior and rear-end crash risks in work zone merging areas[J]. Accident Analysis & Prevention, 2015, 77: 51-61.

[9] MENG Q, WENG J. Evaluation of rear-end crash risk at work zone using work zone traffic data[J]. Accident Analysis & Prevention, 2011, 43(4): 1291-1300.

[10] 李耘, 张生瑞,茹渑博.高速公路施工区车流跟驰追尾冲突风险[J]. 长安大学学报(自然科学版),2017,37(2): 81-88. [LI Y, ZHANG S R, RU M B. Car following rear end conflict risk of freeway work zone[J]. Journal of Chang'an University(Natural Science Edition), 2017, 37 (2): 81-88.]

[11] KIM S, KIM Y, KIM Y, et al. PID-based freeway work zone merge control with traffic state prediction under mixed traffic flow of connected automated vehicles and manual vehicles[J]. Journal of Advanced Transportation, 2024, 2024(1): 5554608.

[12] 蒋若曦, 朱顺应,王磊,等.基于交通冲突的高速公路施工区安全评价[J]. 中国安全科学学报,2019,29(6): 116-121. [JIANG R X, ZHU S Y, WANG L, et al. Traffic safety assessment of highway workzone based on traffic conflict[J]. China Safety Science Journal, 2019, 29(6): 116-121.]

[13] ZHOU S, YANG X, YANG J, et al. Speed characteristics and safety risk level evaluation for nighttime roadway work area[J]. Procedia-Social and Behavioral Sciences, 2013, 96: 2713-2724.

[14] WANG J, SONG H, FU T, et al. Crash prediction for freeway work zones in real time: A comparison between convolutional neural network and binary logistic regression model[J]. International Journal of Transportation Science and Technology, 2022, 11(3): 484-495.

[15] MOGHADDAM F R, AFANDIZADEH S, ZIYADI M. Prediction of accident severity using artificial neural networks[J]. International Journal of Civil Engineering, 2011, 9(1): 41-48.

[16] SUN J. Real- time crash prediction on urban expressways: Identification of key variables and a hybrid support vector machine model[J]. IET Intelligent Transport Systems, 2016, 10(5): 331-337.

[17] WANG B, CHEN T, ZHANG C, et al. Toward safer highway work zones: An empirical analysis of crash risks using improved safety potential field and machine learning techniques[J]. Accident Analysis & Prevention, 2024, 194: 107361.

[18] JIANG R, WU Q. The night driving behavior in a car following model[J]. Physica A: Statistical Mechanics and Its Applications, 2007, 375(1): 297-306.

[19] 陈吉清,翁楚滨,兰凤崇.智能车辆换道潜在冲突分析与风险量化方法[J]. 汽车工程, 2021, 43(11): 1565 1576. [CHEN J Q, WENG C B, LAN F C. Potential conflict analysis and risk quantification method of intelligent vehicle lane change[J].Automotive Engineering, 2021, 43(11): 1565-1576.]

[20] CHEN T, GUESTRIN C. Xgboost: A scalable tree boosting system[C]// New York: Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, 2016.

[21] 孙国锋, 景云,李和壁,等.基于可解释机器学习框架的列车乘车区段客流分布预测方法[J].交通运输系统工程与信息,2024, 24(2): 249-262. [SUN G F, JING Y, LI H B, et al. An interpretable machine learning framework-based approach for predicting passenger flow distribution in train riding sections[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(2): 249-262.]

[22] LUNDBERG S M, ERION G G, LEE S. A unified approach to interpreting model predictions[C]//New York: Proceedings of the 31st International Conference on Neural Information Processing Systems, 2018.

Accident Risk Identification and Impact Mechanisms in Nighttime Highway Maintenance Work Zones

高速公路夜间养护作业区事故风险辨识及影响机理研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics

[1]	DENG Yuanchang, JIANG Yunxuan, TAO Shengqin. Risk Identification Method for Abnormal Driving Behavior Based on Interpretable Ensemble Learning Model [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 180-189.
[2]	GONG Zhe, YANG Zhen, ZHENG Ruiping, YUAN Fang. Modeling andAnalysis of Driver's Short-term Response Behavior Heterogeneity Under Cut-in Scenarios [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 190-200.
[3]	WANG Jianjun, WU Jing, LI Jingtao, ZHOU Yingjie. ImpactAnalysis of Non-bus Vehicle Stopping on Delays at Main-auxiliary Bus Platforms [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(2): 241-252.
[4]	SONG Xianmin, LIU Bo, LI Haitao, ZHAN Tianshu, LI Shihao, ZHANG Yunxiang. APeriodic Parking Reservation and Allocation Model Considering Comprehensive Benefits [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 24-35.
[5]	CAO Danni, WANG Tao, YANG Songpo, QU Yunchao, WU Jianjun. Lane-based Speed Regulation of Bottlenecks Under Mixed Flow Environment [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 76-85.
[6]	HAN Fengfan, LIU Shuang, ZHU Yadi, YANG Ye, WANG Xi. Data-driven Pedestrian Simulation Method for Urban Rail Transit Station [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 86-91.
[7]	QIN Wenwen, BAI Bixuan, HAN Chunyang, JI Xiaofeng, GU Jinjing, TIAN Bijiang. Car-following State Transition Prediction on Horizontal Curves of Mountainous Two-lane Roads [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 92-101.
[8]	PENG Jinshuan, ZHANG Lingjun, ZHOU Lei, YUAN Hao, REN Chaoyu, XU Lei. Influence Mechanisms and Identification of Cognitive Distraction of Car-following on Expressways [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 221-230.
[9]	WU Lan, ZHOU Jiayu, LI Gen. Evolutionary Analysis of Factors Influencing Electric Bike Crash Severity from Perspective of Technical Standard Update [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 231-240.
[10]	LIN Yifeng, WEN huiying. Freeway Tunnel Real-time Car Following Risk Impact Factors Analysis [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 298-310.
[11]	SHANG Ting, XU Hao, LIANG Ye, ZHOU Ao. Visual Load Analysis of Underground Ring Road Junctions Using Game Theoretic Cloud Object Elements [J]. Journal of Transportation Systems Engineering and Information Technology, 2025, 25(1): 345-354.
[12]	LUKai, CHEN Zhixue, LIN Yongjie, GUO Haifeng. Calculation Method of Signal Cycle at Roundabouts Considering Cross-phase Conflicts [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6): 86-101.
[13]	ZHENGJianming, HUAYiding, ZHANGYufei, LU Wenhao, SHI Peixin, QIN Bin, ZHAO Mulong. Driver Emergency Braking Model Considering Risk Scenarios [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6): 219-231.
[14]	JI Xiaofeng, WANG Jian, XU Yinghao, LU Mengyuan, QIN Wenwen. Driving Style-based Sensitivity Analysis of Driving Risk Field in Mountain Highway Sections Passing Through Villages and Towns [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6): 316-325.
[15]	LUOShuang, YANG Shuqun, XU Jin. Vehicle Trajectory Characteristics on Tunnel-interchange Section with Short Connection [J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(6): 326-338.