大交通量高货车比高速公路作业区交通
风险预测方法研究

doi:10.16638/j.cnki.1671-7988.2025.022.024

摘要/Abstract

摘要： 高速公路作业区的固定与移动瓶颈叠加，会引发交通流“水锤效应”，尤其在大交通量、高货车比路段，该效应是诱发交通事故的重要原因。为从源头减少此类事故，文章提出一种考虑“水锤效应”的交通冲突预测模型，可在作业区交通风险升高时向管理者实时预警。通过模拟仿真实验与随机森林建模分析，对比宏观模型（MAM）与微观模型（MIM）的预测精度发现，MIM 模型预测精度（R 2 =93.49%）显著优于 MAM 模型。进一步结合宏微观交通流特性及 MIM 模型的特征重要性分析，明确了交通冲突与单车运动状态、车车交互作用、交通瓶颈的密切关联，并证实“水锤效应”对作业区交通安全存在显著负面影响。

关键词: 大交通量；高货车比；作业区；水锤效应；交通冲突预测

Abstract: The superimposition of fixed and mobile bottlenecks in highway work zones triggers the "water hammer effect" in traffic flow. This effect is a key factor inducing traffic accidents, especially on road sections with high traffic volume and a high proportion of trucks. To reduce such accidents at the source, this paper proposes a traffic conflict prediction model that accounts for the "water hammer effect", which can provide real-time early warnings to managers when traffic risks in work zones increase. Through simulation experiments and random forest modeling analysis, a comparison of the prcediction accuracy between the macroscopic model (MAM) and the microscopic model (MIM) shows that the MIM model has significantly higher prediction accuracy (R 2 =93.49%) than the MAM model. Further analysis combining macro and micro traffic flow characteristics with the feature importance of the MIM model clarifies the close correlation between traffic conflicts and individual vehicle movement states, vehicle-to-vehicle interactions, and traffic bottlenecks, and confirms that the "water hammer effect" exerts a significant negative impact on traffic safety in work zones.

Key words: high traffic volume; high truck ratio; work zone; water hammer effect; traffic conflict prediction

王哲轩. 大交通量高货车比高速公路作业区交通风险预测方法研究[J]. 汽车实用技术, 2025, 50(22): 133-140.

WANG Zhexuan. Research on Traffic Risk Prediction Method for Highway Work Zones with Large Traffic Volume and High Truck Ratio[J]. Automobile Applied Technology, 2025, 50(22): 133-140.

参考文献

[ 1 ] KHATTAK A J,COUNCIL F M.Effects of Work Zone Presence on Injury and Non-Injury Crashes[J].Accident Analysis and Prevention,2002,34(1):19-29. [ 2 ] 中国交通运输部.公路养护安全作业规程:JTG H30 －2015[S].北京:中华人民共和国交通运输部,2015. [ 3 ] GARBER N J,ZHAO M.Distribution and Characteristics of Crashes at Different Locations within Work Zones in Virginia:02-R12[R].Charlottesville:Virginia Transportation Research Council,2002. [ 4 ] LECLERCQ L.Bounded Acceleration Close to Fixed and Moving Bottlenecks[J].Transportation Research, Part B.Methodological,2007,41(3):309-319. [ 5 ] SIMONI M D,CLAUDEL C G.A Fast Simulation Algorithm for Multiple Moving Bottlenecks and Applications in Urban Freight Traffic Management[J]. Transportation Research,Part B.Methodological,2017, 104(10):238-255. [ 6 ] HOU L,GONG P B,SUN H,et al.Emergency PumpRate Regulation to Mitigate Water-Hammer Effect:An Integrated Data-Driven Strategy and Case Studies[J]. Energies,2024,17(5):1-14. [ 7 ] FU C Y,SAYED T.Random Parameters Bayesian Hierarchical Modeling of Traffic Conflict Extremes for Crash Estimation[J].Accident Analysis and Prevention, 2021,157(7):1-10. [ 8 ] LI Y,YANG Z H,XING L,et al.Crash Injury Severity Prediction Considering Data Imbalance:A Wasserstein Generative Adversarial Network with Gradient Penalty Approach[J].Accident Analysis and Prevention,2023, 192(11):1-18. [ 9 ] GETTMAN D,PU L,SAYED T,et al.Surrogate Safety Assessment Model and Validation:FHWA-HRT-08- 051[R].Washington:Federal Highway Administration, 2008. [10] GUO X,WANG L,CAO J,et al.Trajectory Data-Based Severe Conflict Prediction for Expressways under Different Traffic States[J].Physica A.Statistical Mechanics and its Applications,2023,621:1-14. [11] WU L,SUN Z C,LIU J B,et al.Unveiling the Impact of Heterogeneous Driving Behaviors on Traffic Flow:A Mesoscale Multi-Agent Modeling Approach[J].Computers and Electrical Engineering,2024,119(1):1-16. [12] ARUN A,HAQUE M M,WASHINGTON S,et al.A Systematic Review of Traffic Conflict-Based Safety Measures with a Focus on Application Context[J].Analytic Methods in Accident Research,2021,32:100185. [13] 傅挺,袁浩然,胡伟超,等.道路交通安全风险评估及主动防控策略探析[J].道路交通管理,2025(2):30-33. [14] GUO Y Y,SAYED T, ESSA M.Real-Time ConflictBased Bayesian Tobit Models for Safety Evaluation of Signalized Intersections[J].Accident Analysis and Prevention,2020,144(9):1-11. [15] KUANG Y,YU Y,QU X B.Novel Crash Surrogate Measure for Freeways[J].Journal of Transportation Engineering,Part A. Systems,2020,146(8):1-10. [16] MAHMUD S,FERREIRA L,HOQUE M S,et al.Application of Proximal Surrogate Indicators for Safety Evaluation:A Review of Recent Developments and Research Needs[J].Iatss Research,2017,41(4):153-163. [17] LI L H,GAN J,JI X K,et al.Dynamic Driving Risk Potential Field Model under the Connected and Automated Vehicles Environment and its Application in Car-Following Modeling[J].IEEE Transactions on Intelligent Transportation Systems,2022,23(1):122-141. [18] HU Y P,LI Y,HUANG H L,et al.A High-Resolution Trajectory Data Driven Method for Real-Time Evaluation of Traffic Safety[J].Accident Analysis and Prevention,2021,165(1):1-11. [19] GUO M,ZHAO X H,YAO Y,et al.A Study of Freeway Crash Risk Prediction and Interpretation Based on Risky Driving Behavior and Traffic Flow Data[J]. Accident Analysis and Prevention,2021,160(9):1-11. [20] 肖煌,梁佳政,孙吉月,等.基于特征工程与多模型对比的可解释交通预测研究[J].交通科技与管理,2025,6 (16):26-28,194. [21] HU Y P,LI Y,HUANG H L,et Al.A High-Resolution Trajectory Data Driven Method for Real-Time Evaluation of Traffic Safety[J].Accident Analysis and Prevention,2021,165(2):1-11. [22] 陈雅楠,修辉,李美玲,等.不中断交通高速公路改扩建交通仿真参数标定[J].公路交通技术,2021,37(4):138- 145. [23] 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. [24] XU R H,LUO F.Risk Prediction and Early Warning for Air Traffic Controllers' Unsafe Acts Using Association Rule Mining and Random Forest[J].Safety Science, 2021,135:1-10.