吉林大学学报(工学版) ›› 2024, Vol. 54 ›› Issue (5): 1323-1331.doi: 10.13229/j.cnki.jdxbgxb.20220744

• 交通运输工程·土木工程 • 上一篇    

山区双车道公路货车移动遮断小客车跟驰风险预测模型

戢晓峰1,2(),徐迎豪1,2,普永明1,2,郝京京1,2,覃文文1,2()   

  1. 1.昆明理工大学 交通工程学院,昆明 650504
    2.云南省现代物流工程研究中心,昆明 650604
  • 收稿日期:2022-09-03 出版日期:2024-05-01 发布日期:2024-06-11
  • 通讯作者: 覃文文 E-mail:yiluxinshi@sina.com;qinww@kust.edu.cn
  • 作者简介:戢晓峰(1982-),男,教授,博士. 研究方向:交通安全与交通规划. E-mail:yiluxinshi@sina.com
  • 基金资助:
    国家自然科学基金项目(52062024);云南省交通运输厅科技创新及示范项目(2021-90-3);云南省交通运输厅科技创新及示范项目(2022-27(二));云南省基础研究计划青年项目(202101AU070166)

Risk prediction model of passenger car following behavior under truck movement interruption of two-lane highway in mountainous area

Xiao-feng JI1,2(),Ying-hao XU1,2,Yong-ming PU1,2,Jing-jing HAO1,2,Wen-wen QIN1,2()   

  1. 1.School of Transportation Engineering, Kunming University of Science and Technology, Kunming 650504, China
    2.Yunnan Modern Logistics Engineering Research Center, Kunming 650604, China
  • Received:2022-09-03 Online:2024-05-01 Published:2024-06-11
  • Contact: Wen-wen QIN E-mail:yiluxinshi@sina.com;qinww@kust.edu.cn

摘要:

选取典型山区双车道公路弯道和直道为研究对象,基于无人机航拍视频提取的交通轨迹数据,通过轻度提升机算法构建了货车移动遮断下小客车跟驰风险预测模型,采用支持向量机、随机森林验证了模型有效性,分析了模型关键特征参数风险作用机制。实验结果表明:基于轻度提升机算法的风险预测模型准确率达96.9%,具有优越性,速度差、跟驰间距是模型关键特征参数,直道上单因子重要度更大;相比弯道,直道路段危险驾驶行为突出,大幅横向偏移等不稳定跟驰特征明显;由模型解释器结果可知,当速度差小于0.5 m/s、跟驰间距大于40 m时,是较为安全的跟驰状态。

关键词: 交通运输安全工程, 跟驰风险预测, 轻度提升机算法, 货车移动遮断, 山区双车道公路

Abstract:

Taking the typical mountainous two-lane highway bend and straight road as the research object, based on traffic trajectory data extracted by UAV aerial video, the risk prediction model of passenger car following under the movement interruption of truck was constructed by the light gradient boosting machine algorithm (LGBM). The support vector machine (SVM) and random forest machine (RF) were used to verify the validity of the model, and the risk mechanism of the key characteristic parameters of the model was analyzed. The experimental results show that the accuracy of the risk prediction model based on the LGBM algorithm is 96.9%, which is superior. The speed difference and the following distance are the key characteristic parameters of the model, and the single factor importance on the straight road is greater. Compared with the curve, the dangerous driving behavior of straight road section is prominent, and the unstable following characteristics such as large lateral offset are obvious; the results of the model interpreter show that when the speed difference is less than 0.5 m/s and the car-following distance is greater than 40 m, it is a safe car-following state.

Key words: traffic and transportation safety engineering, risk prediction of car-following, LGBM algorithm, truck movement interruption, mountain two-lane highway

中图分类号: 

  • U491.31

表1

冲突风险等级划分规则"

风险等级含义冲突可能性划分规则
四级车辆间具有严重冲突,存在较大碰撞风险碰撞时间<1%分位值
三级车辆间同时具有严重和一般冲突,存在潜在碰撞风险1%分位值碰撞时间<5%分位值
二级车辆间存在一般冲突,可及时避让5%分位值碰撞时间<85%分位值
一级车辆间存在轻微冲突,可安全行驶85%分位值碰撞时间

表2

模型评价指标"

指标(符号)含义公式
查准率(P预测样本有多少概率真正的正样本P=TPTP+FP
查全率(R有多少比例正样本被正确预测R=TPTP+FN
F1值(F1)PR的综合指标F1=2×P×RP+R

图1

无人机视频采集路段"

图2

Geroge提取跟驰轨迹数据流程"

表3

跟驰行为特征参数单样本t检验"

变量(符号)单位路段均值标准差差分的95%置信区间Sig.(双侧)
下限上限
车头时距(Tijs直道2.911.432.862.960
弯道3.531.893.473.590
跟驰间距(Sijm直道21.2419.0520.6521.840
弯道24.0113.8023.5524.470
跟驰速度差(Vijm/s直道0.882.190.810.960.01
弯道0.152.190.080.220
小客车相对偏移(Lm直道-0.430.21-0.65-0.220
弯道-0.280.11-0.32-0.230
小客车速度(Vjm/s直道39.5514.6039.0740.040
弯道35.7418.4035.1636.310

图3

小客车速度对车头间距的影响"

图4

小客车速度频率分布"

图5

小客车横向偏移极值分布"

图6

轨迹数据TTC累计频率分布"

表4

风险等级划阈值"

风险等级TTC/s
四级(0,2.9)

三级

二级

一级

(2.9,5.9)

(5.9,8.3)

(8.3,+

图7

主成分方差贡献率"

表5

关键特征参数"

类别参数物理量计算方式
货车货车速度Vi/(km·h-1/
货车加速度Ai/(m·s-2/
货车轨迹曲率Cur/
货车长度H/m/
小客车小客车速度Vj/(km·h-1/
小客车加速度Aj/(m·s-2/
小客车相对偏移L/mxi-xj,向东xj-xi,向西
交通流车头时距Tij/sTij=(Sij+H)/Vj
跟驰间距Sij/mSij=(xi-xj)2+(yi-yj)2-H
速度差Vij/(m·s-1Vi-Vj

图8

机器学习混淆矩阵"

表6

混淆矩阵衍生指标"

预测模型PrecisionRecallF1值
LGBM0.9690.9650.966
SVM0.9140.9070.907
RF0.9650.9630.963

图9

LGBM关键特征参数重要度排序"

图10

风险概率关系曲线图"

1 戢晓峰,卢梦媛,覃文文.货车移动遮断影响下的小客车驾驶行为识别[J].交通运输系统工程与信息,2021, 21(5):174-182.
Ji Xiao-feng, Lu Meng-yuan, Qin Wen-wen. Identification of passenger car driving behavior under the influence of truck moving interruption[J]. Transportation Systems Engineering and Information Technology, 2021,21(5): 174-182.
2 Moridpour S, Mazloumi E, Mesbah M. Impact of heavy vehicles on surrounding traffic characteristics[J]. Journal of Advanced Transportation, 2015, 49(4): 535-552.
3 Gazis D C, Herman R. The moving and "phantom" bottlenecks[J]. Transportation Science, 1992, 26(3): 223-229.
4 Aghabayk K, Sarvi M, Young W. Understanding the dynamics of heavy vehicle interactions in car-following[J]. Journal of Transportation Engineering, 2012, 138(12): 1468-1475.
5 Sarvi M. Heavy commercial vehicles‐following behavior and interactions with different vehicle classes[J]. Journal of Advanced Transportation, 2013, 47(6): 572-580.
6 Xu C, Liu P, Wang W, et al. Evaluation of the impacts of traffic states on crash risks on freeways[J]. Accident Analysis & Prevention, 2012, 47: 162-171.
7 Hossain M, Muromachi Y. A Bayesian network based framework for real-time crash prediction on the basic freeway segments of urban expressways[J]. Accident Analysis & Prevention, 2012, 45: 373-381.
8 杨奎,余荣杰,王雪松.基于车道集计交通流数据的事故风险评估分析[J].同济大学学报,2016,44(10): 1567-1572.
Yang Kui, Yu Rong-jie, Wang Xue-song. Application of aggregated lane data from dual-loop detector to crash risk evaluation[J]. Journal of Tongji University, 2016, 44(10): 1567-1572.
9 Song Y, Kou S, Wang C. Modeling crash severity by considering risk indicators of driver and roadway: a Bayesian network approach[J]. Journal of Safety Research, 2021, 76: 64-72.
10 李志慧,孙雅倩,陶鹏飞,等.交通事故后的交通运行风险状态等级预测方法[J].吉林大学学报:工学版,2022,52(1):127-135.
Li Zhi-hui, Sun Ya-qian, Tao Peng-fei, et al. Forecasting method of traffic operation risk level after traffic accident[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(1): 127-135.
11 Sayed T, Zaki M H, Autey J. Automated safety diagnosis of vehicle-bicycle interactions using computer vision analysis[J]. Safety Science, 2013 59(11): 163-172.
12 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 Shun-ying, Jiang Ruo-xi, Wang Hong, et al. Summary of research on vehicle traffic conflict technology[J]. China Journal of Highway and Transport, 2020, 33(2): 15-33.
13 戢晓峰,谢世坤,覃文文,等.基于轨迹数据的山区危险性弯道路段交通事故风险动态预测[J].中国公路学报,2022,35(4):277-285.
Ji Xiao-feng, Xie Shi-kun, Qin Wen-wen, et al. Dynamic prediction of traffic accident risk in dangerous mountain bends based on trajectory data[J]. China Journal of Highways, 2022, 35(4): 277-285.
[1] 邬岚,赵乐,李根. 基于方差异质性随机参数模型的汇合行为分析[J]. 吉林大学学报(工学版), 2024, 54(4): 883-889.
[2] 王宏志,宋明轩,程超,解东旋. 基于改进YOLOv4-tiny算法的车距预警方法[J]. 吉林大学学报(工学版), 2024, 54(3): 741-748.
[3] 何杰,张长健,严欣彤,王琛玮,叶云涛. 基于微观动力学参数的高速公路特征路段事故风险分析[J]. 吉林大学学报(工学版), 2024, 54(1): 162-172.
[4] 潘恒彦,张文会,梁婷婷,彭志鹏,高维,王永岗. 基于MIMIC与机器学习的出租车驾驶员交通事故诱因分析[J]. 吉林大学学报(工学版), 2023, 53(2): 457-467.
[5] 贺宜,孙昌鑫,彭建华,吴超仲,江亮,马明. 电动载货三轮车风险行为及影响因素分析[J]. 吉林大学学报(工学版), 2023, 53(2): 413-420.
[6] 朱洁玉,马艳丽. 合流区域多车交互风险实时评估方法[J]. 吉林大学学报(工学版), 2022, 52(7): 1574-1581.
[7] 彭涛,方锐,刘兴亮,王海玮,庞彦伟,许洪国,刘福聚,王涛. 基于典型事故场景的雪天高速换道自动驾驶策略[J]. 吉林大学学报(工学版), 2022, 52(11): 2558-2567.
[8] 程国柱,程瑞,徐亮,张文会. 基于乘员伤害分析的公路路侧事故风险评价[J]. 吉林大学学报(工学版), 2021, 51(3): 875-885.
[9] 王露,刘玉雯,陈红. 侧风下峡谷桥隧连接段汽车的行驶特性[J]. 吉林大学学报(工学版), 2019, 49(3): 736-748.
[10] 代存杰,李引珍,马昌喜,柴获,牟海波. 不确定条件下危险品配送路线多准则优化[J]. 吉林大学学报(工学版), 2018, 48(6): 1694-1702.
[11] 王芳荣, 郭柏苍, 金立生, 高琳琳, 岳欣羽. 次任务驾驶安全评价指标筛选及其权值计算[J]. 吉林大学学报(工学版), 2017, 47(6): 1710-1715.
[12] 谭立东, 刘丹, 李文军. 基于蝇复眼的交通事故现场全景图像阵列仿生设计[J]. 吉林大学学报(工学版), 2017, 47(6): 1738-1744.
[13] 李显生, 孟祥雨, 郑雪莲, 程竹青, 任圆圆. 非满载罐体内液体冲击动力学特性[J]. 吉林大学学报(工学版), 2017, 47(3): 737-743.
[14] 王占中, 赵利英, 曹宁博. 基于多层编码遗传算法的危险品运输调度模型[J]. 吉林大学学报(工学版), 2017, 47(3): 751-755.
[15] 徐进, 陈薇, 周佳, 罗骁, 邵毅明. 汽车转向盘操作与驾驶负荷的相关性[J]. 吉林大学学报(工学版), 2017, 47(2): 438-445.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!