基于驾驶风格的山区公路穿村镇段行车风险场灵敏度分析

doi:10.16097/j.cnki.1009-6744.2024.06.028

交通运输系统工程与信息 ›› 2024, Vol. 24 ›› Issue (6): 316-325.DOI: 10.16097/j.cnki.1009-6744.2024.06.028

基于驾驶风格的山区公路穿村镇段行车风险场灵敏度分析

戢晓峰^a,b，王健^a,b，徐迎豪^a,b，卢梦媛^a,b，覃文文^*a,b

昆明理工大学，a.交通工程学院；b.云南省现代物流工程研究中心，昆明650504

收稿日期:2024-07-17 修回日期:2024-08-03 接受日期:2024-08-13 出版日期:2024-12-25 发布日期:2024-12-18
作者简介:戢晓峰(1982- )，男，湖北随州人，教授，博士。
基金资助:
国家自然科学基金 (52062024)；云南省交通运输厅科技创新及示范项目(2023-83(II))；云南省基础研究计划面上项目 (202401AT070309)。

Driving Style-based Sensitivity Analysis of Driving Risk Field in Mountain Highway Sections Passing Through Villages and Towns

JI Xiaofeng^a,b,WANG Jian^a,b,XU Yinghao^a,b,LU Mengyuan^a,b,QIN Wenwen^*a,b

a. Faculty of Transportation Engineering; b. Yunnan Modern Logistics Engineering Research Center, Kunming University of Science and Technology, Kunming 650504, China

Received:2024-07-17 Revised:2024-08-03 Accepted:2024-08-13 Online:2024-12-25 Published:2024-12-18
Supported by:
NationalNaturalScienceFoundation of China (52062024)；Yunnan Province Transportation Science and Technology Innovation Demonstration Research Project (2023-83(II))；YunnanProvincialBasicResearch Program General Project (202401AT070309)。

摘要/Abstract

摘要： 针对山区公路穿村镇段交通事故多发的现实问题，本文提出一种考虑驾驶风格的行车风险识别方法，通过灵敏度分析揭示驾驶风格在风险评估中的影响，并以云南省典型山区公路穿村镇段为实例进行验证。首先，利用无人机采集车辆轨迹数据，建立轨迹分析数据库；其次，基于行车风险场理论并通过事故数据的相关性分析，刻画穿村镇段行车环境对车辆行驶的风险影响，进一步引入驾驶风格因子，建立考虑驾驶风格的行车风险场，实现多要素的综合考虑与行车风险量化；最后，基于Sobol全局灵敏度分析方法，分析考虑驾驶风格前后模型关键参数的全局灵敏度，并实现区域风险的可视化。研究结果表明：当选择速度均值、加速度均值和冲击度方差进行驾驶风格划分，K值为4时聚类效果最佳；Sobol法有效评估了参数灵敏度，当考虑驾驶人行为场后，总灵敏度分布更加均匀，模型考虑因素更为广泛，其中速度和冲击度标准差为最显著参数，总灵敏度分别为0.41和0.34；对多车共同作用产生的风险可视化显示，势场范围随道路线形变化而变化，在穿村镇交叉口风险值最显著，整体行驶速度降比为17.39%，将进一步发挥风险场理论在微观交通风险评估中的作用。

关键词: 交通工程, 风险场模型, 灵敏度分析, 穿村镇道路, 驾驶风格, 山区公路

Abstract: In response to the high frequency of traffic accidents on mountainous roads passing through villages and towns, this paper proposes a driving risk identification method considering driving style and reveals the influence of driving style in risk assessment through sensitivity analysis. The method is verified with a typical mountainous road passing through villages and towns in Yunnan Province as an example. The vehicle trajectory data is collected through drones and a trajectory database is established for the analysis. Based on the theory of driving risk field and through correlation analysis of accident data, the impact of driving environment on vehicle driving in the village and town section is characterized. Furthermore, driving style factors are introduced to establish a driving risk field that considers driving style, achieving comprehensive consideration of multiple factors and quantification of driving risk. Based on the Sobol global sensitivity analysis method, the global sensitivity of key parameters of the model before and after considering driving style is analyzed, and the visualization of regional risks is realized. The results indicate that when selecting the mean velocity, mean acceleration, and variance of impact for driving style classification, the clustering effect is best when the K value is 4. The Sobol method effectively evaluates parameter sensitivity. When considering the driver behavior field, the overall sensitivity distribution is more uniform, and the model considers a wider range of factors. Among them, the standard deviation of speed and impact are the most significant parameters, and the overall sensitivity is respectively 0.41 and 0.34. The visualization of the risks generated by the joint action of multiple vehicles shows that the potential field range varies with the shape of the road, and the risk value is most significant at the intersection through villages and towns, with an overall speed reduction ratio of 17.39%. This will further enhance the role of risk field theory in the field of micro traffic risk assessment.

Key words: traffic engineering, risk field model, sensitivity analysis, road through the village and town, driving style; mountain roads

中图分类号:

U491.2

戢晓峰, 王健, 徐迎豪, 卢梦媛, 覃文文. 基于驾驶风格的山区公路穿村镇段行车风险场灵敏度分析[J]. 交通运输系统工程与信息, 2024, 24(6): 316-325.

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.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/10.16097/j.cnki.1009-6744.2024.06.028

http://www.tseit.org.cn/CN/Y2024/V24/I6/316

参考文献

[1]张铁军, 尹心怡,肖贵平.公路穿村镇路段速度管理设施设置位置研究[J].公路,2017, 62(10): 172 176. [ZHANG T J, YIN X Y, XIAO G P. Study on location of speed management facilities for highway crossing villages and towns[J]. Highway, 2017, 62(10): 172-176.]

[2] 戢晓峰,詹换勤,普永明,等.山区公路穿村镇路段过境车辆事故严重程度推理分析[J].交通运输系统工程与信息,2022, 22(3): 231-237. [JI X F, ZHAN H Q, PU Y M, et al. Reasoning analysis of the severity of accidents involving vehicles passing through villages on mountainous highways[J]. Journal of Transportation Systems Engineering and Information Technology, 2022, 22(3): 231-237.]

[3]王建强,吴剑,李洋.基于人—车—路协同的行车风险场概念, 原理及建模[J]. 中国公路学报,2016, 29(1): 105-114. [WANG J Q, WU J, LI Y. Concept, principle and modeling of driving risk field based on human vehicle-road collaboration[J]. China Journal of Highway, 2016, 29(1): 105-114.]

[4]何仁,赵晓聪,杨奕彬,等.基于驾驶人风险响应机制的人机共驾模型[J].吉林大学学报(工学版),2021,51 (3): 799-809. [HE R, ZHAO X C, YANG Y B, et al. A human-machine co-driving model based on driver risk response mechanism[J]. Journal of Jilin University (Engineering Edition), 2021, 51(3): 799-809.]

[5]李林恒,甘婧,曲栩,等.智能网联环境下基于安全势场理论的车辆跟驰模型[J].中国公路学报,2019,32 (12): 76-87. [LI L H, GAN J, QU X, et al. Vehicle following model based on safety potential field theory in smart grid environment[J]. Chinese Journal of Highway, 2019, 32(12): 76-87.]

[6] LIU X, WANG Y, JIANG K, et al. Interactive trajectory prediction using a driving risk map-integrated deep learning method for surrounding vehicles on highways[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(10): 19076-19087.

[7] FENG F, BAO S, SAYER J R, et al. Can vehicle longitudinal jerk be used to identify aggressive drivers? An examination using naturalistic driving data[J]. Accident Analysis & Prevention, 2017, 104: 125-136.

[8] MURPHEY Y L, MILTON R, KILIARIS L. Driver's style classification using jerk analysis[C]//2009 IEEE Workshop on Computational Intelligence in Vehicles and Vehicular Systems, IEEE, 2009: 23-28.

[9] SU C, DENG W, SUN H, et al. Forward collision avoidance systems considering driver's driving behavior recognized by Gaussian Mixture Model[C]//2017 IEEE Intelligent Vehicles Symposium (IV), IEEE, 2017: 535 540.

[10] 王旭, 马菲,廖小棱,等.基于多分类监督学习的驾驶风格特征指标筛选[J].交通信息与安全,2022,40(1): 162-168. [WANG X, M F, LIAO X L, et al. Driving style feature index screening based on multi classification supervised learning[J]. Traffic Information and Safety, 2022, 40(1): 162-168.]

[11] 吴杨俊, 徐翠强,陈杰,等.内燃动力包隔振参数灵敏度分析及优化设计[J]. 中南大学学报(自然科学版), 2021, 52(11): 3872-3884. [WU Y J, XU C Q, CHEN J, et al. Parameter sensitivity analysis and optimization design of vibration isolation for internal combustion power pack[J]. Journal of Central South University: Science and Technology, 2021, 52(11): 3872-3884.]

[12] 戢晓峰, 徐迎豪,普永明,等.山区双车道公路货车移动遮断小客车跟驰风险预测模型[J].吉林大学学报(工学版), 2024, 54(5): 1323-1331. [JI X F, XU Y H, PU Y M, et al. Risk prediction model for trucks blocking passenger cars on two-lane highways in mountainous areas[J]. Journal of Jilin University (Engineering Edition), 2024, 54(5): 1323-1331.]

[13] WANG J, WU J, ZHENG X, et al. Driving safety field theory modeling and its application in pre-collision warning system[J]. Transportation Research Part C: Emerging Technologies, 2016, 72: 306-324.

[14] WANG Q, LI H, LU L, et al. Global sensitivity analysis of earth-moon transfer orbit parameters based on sobol method[J]. International Journal of Aerospace Engineering, 2022, 2022(1): 6587890.

[1]	宋现敏, 刘博, 李海涛, 湛天舒, 李世豪, 张云翔. 考虑综合效益的周期型停车预约分配模型[J]. 交通运输系统工程与信息, 2025, 25(1): 24-35.
[2]	曹丹妮, 王涛, 杨松坡, 屈云超, 吴建军. 混合流环境下瓶颈区域车道定制化速度调控研究[J]. 交通运输系统工程与信息, 2025, 25(1): 76-85.
[3]	韩烽凡, 刘爽, 朱亚迪, 杨烨, 王曦. 数据驱动的城轨车站行人仿真方法研究[J]. 交通运输系统工程与信息, 2025, 25(1): 86-91.
[4]	覃文文, 白碧璇, 韩春阳, 戢晓峰, 谷金晶, 田毕江. 山区双车道公路弯道路段小客车跟驰状态转移预测[J]. 交通运输系统工程与信息, 2025, 25(1): 92-101.
[5]	彭金栓, 张淋俊, 周磊, 袁浩, 任超宇, 徐磊. 高速公路跟车情景下认知分心影响机制与识别方法[J]. 交通运输系统工程与信息, 2025, 25(1): 221-230.
[6]	邬岚, 周佳雨, 李根. 技术标准更新视角下电动自行车事故严重程度影响因素演化分析[J]. 交通运输系统工程与信息, 2025, 25(1): 231-240.
[7]	林译峰, 温惠英. 高速公路隧道不同车辆实时跟驰风险影响因素分析[J]. 交通运输系统工程与信息, 2025, 25(1): 298-310.
[8]	尚婷, 胥浩, 梁叶, 周翱. 基于博弈论云物元的地下环道出入口视觉负荷研究[J]. 交通运输系统工程与信息, 2025, 25(1): 345-354.
[9]	卢凯, 陈志学, 林永杰, 郭海锋. 考虑跨相位冲突的环形交叉口信号周期计算方法[J]. 交通运输系统工程与信息, 2024, 24(6): 86-101.
[10]	郑建明, 华一丁, 张宇飞, 路文豪, 石佩鑫, 覃斌, 赵目龙. 考虑风险场景的驾驶员紧急制动模型研究[J]. 交通运输系统工程与信息, 2024, 24(6): 219-231.
[11]	罗霜, 杨书群, 徐进. 小净距“隧道—互通”路段车辆行驶轨迹特征研究[J]. 交通运输系统工程与信息, 2024, 24(6): 326-338.
[12]	赵红专, 张继康, 潘佳雯, 袁泉, 许恩永, 魏金占, 周旦, 刘承堃. 基于改进视觉算法的自动驾驶风险预判模型[J]. 交通运输系统工程与信息, 2024, 24(5): 79-90.
[13]	何晖宇, 丁瑞, 应聃, 张宇豪, 张河山, 徐进. 苜蓿叶立交交织区冲突特征及严重程度影响因素分析[J]. 交通运输系统工程与信息, 2024, 24(5): 246-258.
[14]	唐铁桥, 钟静燃, 袁小婷, 覃梦欣. 基于扩展决策场的机场落客区车辆－旅客行为建模分析[J]. 交通运输系统工程与信息, 2024, 24(5): 309-317.
[15]	黄岩, 李海军, 闫学东, 段克. 雾天网联车辆跟驰模型构建及行为影响分析[J]. 交通运输系统工程与信息, 2024, 24(4): 41-49.

基于驾驶风格的山区公路穿村镇段行车风险场灵敏度分析

Driving Style-based Sensitivity Analysis of Driving Risk Field in Mountain Highway Sections Passing Through Villages and Towns

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics