基于冲突预测的混驾环境快速路合流区安全评价方法

doi:10.16097/j.cnki.1009-6744.2026.02.022

摘要/Abstract

摘要： 为缓解人工驾驶与智能网联车辆混驾环境下快速路合流区的交通冲突，提升行车安全水平与通行效率，提出基于冲突预测的安全评价方法。首先，建立面向人工驾驶车辆和智能网联车辆的微观交通流仿真模型，分析交通冲突影响要素；其次，针对人工驾驶与智能网联为主两种场景，基于冲突类型和冲突严重程度，构建相应的交通冲突预测模型和安全评价指标体系；然后，针对现有安全等级评价方法难以刻画合流区风险在临界状态的非线性突变特征的问题，通过正弦函数优化传统白化权函数，将改进后的灰色聚类法与综合集成赋权法相耦合，构建混驾环境下快速路合流区的综合安全评价方法。基于重庆市杨公桥立交合流区实例数据及74组交叉实验仿真开展验证，结果表明，各类交通冲突预测值与SUMO仿真冲突数的相对误差均值为5.24%；随着智能网联渗透率的增加，冲突总数以渗透率40%附近为界，先缓慢增长，后快速下降，由此以智能网联渗透率40%作为人工驾驶为主和智能网联车辆为主的两种混驾情景区分标准；当智能网联车辆渗透率增至40%以上时，杨公桥立交合流区的安全等级从三级和四级为主转变为以一级和二级为主，表明提升智能网联渗透率有助于提高合流区安全水平。

关键词: 城市交通, 安全评价方法, 改进灰色聚类法, 快速路合流区, 冲突预测

Abstract: To mitigate traffic conflicts in expressway merge zones under mixed traffic conditions involving manually driven and intelligent connected vehicles, thereby enhancing driving safety and traffic efficiency, this paper proposes a conflict-prediction based safety evaluation method for expressway merge zones. The micro-level traffic flow simulation models are established for both manually driven and intelligent connected vehicles to analyze factors influencing traffic conflicts. For scenarios dominated by either manually driven or intelligent connected vehicles, corresponding traffic conflict prediction models and safety evaluation indicator systems are developed based on conflict types and severity levels. To address the limitation of existing safety rating evaluation methods in capturing the nonlinear sudden changes in risk characteristics during critical states in merge zones, this study optimizes the traditional whitening weight function using a sine function. By coupling the improved grey clustering method with a comprehensive integrated weighting approach, this paper proposes a comprehensive safety evaluation method for merge zones in mixed-traffic environments. The proposed method was validated using real-world data from the Yanggongqiao Interchange merge zone in Chongqing and 74 sets of cross-experiment simulations. The results show that the mean relative error between predicted conflict values and SUMO simulation conflict counts was 5.24% . As the penetration rate of intelligent connected vehicles increases, the total number of conflicts first grows slowly and then declines rapidly around a penetration rate of 40%. Therefore, a penetration rate of 40% is adopted as the threshold to distinguish between mixed-driving scenarios dominated by manually driven vehicles and those dominated by intelligent connected vehicles. When the penetration rate of intelligent connected vehicles exceeds 40%, the safety level of the Yanggongqiao Interchange merging zone shifts from predominantly Levels 3 and 4 to predominantly Levels 1 and 2. This indicates that increasing the penetration rate of intelligent connected vehicles contributes to enhancing the safety level of the merging zone on expressways.

Key words: urban transportation, safety assessment method, improved gray clustering method, expressway merging zone, conflict prediction

中图分类号:

U121

彭博, 辛子怡, 蔡晓禹, 雷财林, 潘旭萌. 基于冲突预测的混驾环境快速路合流区安全评价方法[J]. 交通运输系统工程与信息, 2026, 26(2): 232-243.

PENG Bo, XIN Ziyi, CAI Xiaoyu, LEI Cailin, PAN Xumeng. Safety Evaluation Method for Merging Zones on Expressways in Mixed-traffic Environments Based on Conflict Prediction[J]. Journal of Transportation Systems Engineering and Information Technology, 2026, 26(2): 232-243.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2026.02.022

http://www.tseit.org.cn/CN/Y2026/V26/I2/232

参考文献

[1]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. [LYU 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.]

[2]刘雪,宋勇刚,王欣,等.基于互联网数据城市快速路地点安全分析方法[J]. 交通运输系统工程与信息, 2018, 18(5): 53-59. [LIU X, SONG Y G, WANG X, et al. Location security analysis of urban expressway based on internet data[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(5): 53-59.]

[3] 朱顺应,蒋若曦,王红,等.机动车交通冲突技术研究综述[J]. 中国公路学报,2020, 33(2): 15-33. [ZHU S Y, JIANG R X, WANG H, et al. Review of research on traffic conflict techniques[J]. China Journal of Highway and Transport, 2020, 33(2): 15-33.]

[4] BARHOUMI O, ZAKI M H, TAHAR S. A formal approach to road safety assessment using traffic conflict techniques[J]. IEEE Open Journal of Vehicular Technology, 2024, 5: 606-619.

[5]PAUL A B, GORE N, ARKATKAR S, et al. Traffic conflict-based safety assessment framework for evaluating treatment effects at urban unsignalized intersections: A case study from Surat, India[J]. Journal of Transportation Engineering, Part A: Systems, 2025, 151(8): 05025004.

[6] 胡立伟,张瑞杰,赵雪亭,等.道路环形交叉口机动车冲突风险区识别模型研究[J].交通运输系统工程与信息, 2024, 24(1): 168-178. [HU L W, ZHANG R J, ZHAO X T, et al. Roundabout motor vehicle conflict risk identification model[J]. Journal of Transportation Systems Engineering and Information Technology, 2024, 24(1): 168-178.]

[7]HANG L, DUAN X, ZHANG M, et al. Research on the safety characteristics of mixed traffic flow under different penetration scenarios of autonomous vehicles[J]. Tehnički Vjesnik, 2022, 29(5): 1609-1621.

[8]HE Y, XIA J. Comprehensive evaluation on traffic safety of mixed traffic flow in a freeway merging area based on a cloud model: From the perspective of traffic conflict[J]. Symmetry, 2025, 17(6): 855.

[9] 赵涛,张宁,王小超,等.基于图神经网络轨迹预测的合流区交通冲突预测方法[J].山东大学学报(工学版), 2024, 54(2): 36-46. [ZHAO T, ZHANG N, WANG X C, et al. A traffic conflict prediction for method for merging areas based on trajectory prediction with graph neural network[J]. Journal of Shandong University (Engineering Science), 2024, 54(2): 36-46.]

[10] ISLAM Z, ABDEL-ATY M. Traffic conflict prediction using connected vehicle data[J]. Analytic Methods in Accident Research, 2023, 39: 100275.

[11] OUYANG P, WU J, XU C, et al. Traffic safety analysis of inter-tunnel weaving section with conflict prediction models[J]. Journal of Transportation Safety and Security, 2022, 14(4): 630-654.

[12] 王晓翠, 张礼敬.通行车辆的激增对扬子江隧道交通安全的影响研究[J]. 公路,2017,62(8): 184-190. [WANG X C, ZHANG L J. Research on the impact of traffic surge on the traffic safety of the Yangtze river tunnel[J]. Highway, 2017, 62(8): 184-190.]

[13] 薛锋, 胡萍,黄宇.基于组合模型的公路隧道交通安全评价[J]. 公路交通科技, 2021, 38(7): 85-95. [XUE F, HU P, HUANG Y. Traffic safety evaluation of highway tunnel based on combined model[J]. Highway and Transportation Research and Development, 2021, 38(7): 85-95.]

[14] 刘志强,王涛.基于改进TOPSIS的驾驶行为实时安全性评估方法[J]. 重庆理工大学学报,2021,35(11): 58 66. [LIU Z Q, WANG T. Real-time safety assessment method of driving behavior based on improved TOPSIS [J]. Journal of Chongqing University of Technology, 2021, 35(11): 58-66.]

[15] 陈亚振, 林玉坤.高速公路改扩建作业区行车安全风险评价及临时安全防护体系研究[J].土木工程,2022, 11(8): 944-953. [CHEN Y Z, LIN Y K. Research on traffic safety risk assessment and temporary safety protection system in expressway reconstruction and expansion operation area[J]. Hans Journal of Civil Engineering, 2022, 11(8): 944-953.]

[16] 杜渐, 杨海益,李洋,等.基于可解释机器学习框架的高速公路安全风险及影响要素识别[J].交通信息与安全, 2023, 41(5): 24-34. [DU J, YANG H Y, LI Y, et al. Identification of safety risk in freeway and impact factors based on an interpretable machine learning framework [J]. Transport Information and Safety, 2023, 41(5): 24 34.]

[17] 于翔海,白佃国,于光,等.基于XGBoost模型的城市道路实时交通事故风险预测研究[J].公路交通科技, 2023, 40(4): 237-247. [YU X H, BAI D G, YU G, et al. Study on predicting real-time traffic accident risk of urban road based on XGBoost model[J]. Highway and Transportation Technology, 2023, 40(4): 237-247.]

[18] MILANéS V, SHLADOVER S E. Modeling cooperative and autonomous adaptive cruise control dynamic responses using experimental data[J]. Transportation Research Part C: Emerging Technologies, 2014, 48: 285 300.

[19] TALAVERA E, DíAZ-ÁLVAREZ A, JIMéNEZ F, et al. Impact on congestion and fuel consumption of a cooperative adaptive cruise control system with lane level position estimation[J]. Energies, 2018, 11(1): 194.

[20] BU F, TAN H-S, HUANG J. Proceedings of the 2010 American control conference, design and field testing of a cooperative adaptive cruise control system[C]. Baltimore: IEEE, 2010.

[21] MUKHAMETZYANOV I. Specific character of objective methods for determining weights of criteria in MCDM problems: Entropy, CRITIC and SD[J]. Decision Making: Applications in Management and Engineering, 2021, 4 (2): 76-105.

[22] 俞洪良,杨正涵,徐铨彪,等.基于DEMATEL-ISM的水利工程EPC项目价值增值机理研究[J].浙江大学学报(理学版), 2024, 51(1): 120-130. [YU H L, YANG Z H, XU QB, et al. Research on value-added mechanism of hydraulic engineering with EPC general contracting mode based on DEMATEL-ISM[J]. Journal of Zhejiang University (Science Edition), 2024, 51(1): 120-130.]

[23] 徐进, 刘妍伶,金勇,等.超大流量高速公路短净距交织区车辆运行特征与行车风险[J/OL].交通运输工程学报, (2025-09-02) [2026-02-27]. https://doi.org/ 10.19818/j.cnki.1671-1637.2026.029. [XU J, LIU Y L, JIN Y, et al. Vehicle operational characteristics and driving risks in shortspacing weaving areas of ultra high traffic volume expressways[J/OL]. Journal of Traffic and Transportation Engineering, (2025-09-02) [2026-02-27]. https://doi.org/10.19818/j.cnki.1671 1637.2026.029.]