Analysis and Prediction of Rear-End Conflicts on Road Sharp Curves

doi:10.12141/j.issn.1000-565X.220430

Abstract

Abstract:

In order to realize the active prevention and control of rear-end collision on sharp curves, a dynamic prediction method of rear-end conflicts was proposed based on converged multi-source data. In this study, firstly, a model for distinguishing rear-end conflicts on sharp curves and a classification criteria of conflict level threshold were proposed by using the vehicle traveling data collected by drones and millimeter wave radar. The spatial distribution characteristics of such conflicts on sharp curves was subsequently analyzed. Then, 13 variables related to traffic flow characteristic such as vehicle type, ratio of large vehicle, and speed difference between sections were selected as input variables, and dynamic combined prediction models of rear-end conflicts on sharp curves with BP neural network, random forest and support vector machine algorithms were constructed based on particle swarm algorithm, respectively. The prediction performance of each prediction model was evaluated based on confusion matrix and area under curve, and the black box interpretation method was used to analyze the significant influence variables and the probabilities of rear-end conflicts occurrence. The results show that the TTC values of rear-end conflicts on sharp curves are smaller than those on flat or normal curved sections, and such conflicts are more serious on the gentle curve exit sections, and the conflicts risk on the inner side of the curves is the highest; the particle swarm algorithm- random forest model has the best performance in predicting the rear-end conflicts, with a sensitivity of 90.70%; the impact of average vehicle headway on rear-end conflict in sharp curve sections is the most significant. When the average vehicle headway is around 25 meters, the probability of conflict is the lowest. Factors such as mean centripetal acceleration and mean velocity also have a significant influence on it.

Key words: sharp curve, time to collision, rear-end conflict, dynamic prediction, conflict probability, particle swarm algorithm

CLC Number:

U491.31

WANG Yonggang, CHEN Junxian, ZHENG Shaoya, et al. Analysis and Prediction of Rear-End Conflicts on Road Sharp Curves[J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(4): 80-87.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Table 1

Table 2

Table 3

Table 4

Table 5

Fig.4

Fig.5

Fig.6

References 20

1	赵晓华，关伟，黄利华，等．急弯处警告标志位置对驾驶行为的影响研究［J］．公路交通科技，2014，31（9）：101-107.
	ZHAO Xiaohua， GUAN Wei， HUANG Lihua，et al ．Research on influence of warning sign position in sharp curve on driving behavior［J］．Journal of Highway and Transportation Research and Development，2014，31（9）：101-107.
2	陆欢，戢晓峰，杨文臣，等．高原山区公路环境下交通事故形态致因分析［J］．中国安全科学学报，2019，29（5）：44-49.
	LU Huan， JI Xiaofeng， YANG Wenchen，et al ．Cause analysis of different patterns of traffic accidents on plateau mountain roads［J］．China Safety Science Journal，2019，29（5）：44-49.
3	OTHMAN S， THOMSON R， LANNER G ．Are driving and overtaking on right curves more dangerous than on left curves？［J］．Annals of Advances in Automotive Medicine，2010，54：253-264.
4	RAKOTONIRAINY A， CHEN S， SCOTT P B，et al ．A novel approach to assessing road-curve crash severity ［J］. Journal of Transportation Safety & Security，2015，7（4）：358-375.
5	MCCARTT A T， NORTHRUP V S， RETTING R A ．Types and characteristics of ramp-related motor vehicle crashes on urban interstate roadways in northern Virginia ［J］．Journal of Safety Research，2004，35（1）：107-114.
6	ELVIK R ．The more （sharp） curves， the lower the risk ［J］．Accident Analysis & Prevention，2019，133：105322.
7	ESSA M， SAYED T ．Traffic conflict models to evaluate the safety of signalized intersections at the cycle level ［J］．Transportation Research Part C：Emerging Technologies，2018，89：289-302.
8	LU G， LIU M， WANG Y，et al ．Quantifying the severity of traffic conflict by assuming moving elements as rectangles at intersection ［J］．Procedia-Social and Behavioral Sciences，2012，43：255-264.
9	TARKO A P ．Estimating the expected number of crashes with traffic conflicts and the lomax distribution-a theoretical and numerical exploration ［J］. Accident Analysis & Prevention，2018，113：63-73.
10	孟祥海，徐汉清，王浩，等．基于TTC及DRAC的高速公路施工区追尾冲突研究［J］．交通信息与安全，2012，30（6）：6-10.
	MENG Xianghai， XU Hanqing， WANG Hao，et al ．Rear-end conflict of freeway work zone based on TTC and DRAC ［J］．Journal of Transport Information and Safety，2012，30（6）：6-10.
11	VOGEL K. A Comparison of headway and time to collision as safety indicators ［J］．Accident Analysis & Prevention，2003，35（3）：427-433.
12	谢济铭，秦雅琴，彭博，等．多车道交织区车辆跟驰行为风险判别与冲突预测［J］．交通运输系统工程与信息，2021，21（3）：131-139.
	XIE Jiming， QIN Yaqin， PENG Bo，et al ．Risk discrimination and conflict prediction of vehicle-following behavior in multi-lane weaving sections ［J］．Journal of Transportation Systems Engineering and Information Technology，2021，21（3）：131-139.
13	陆建，张文珺，杨海飞，等．基于碰撞时间的追尾风险分析［J］．交通信息与安全，2014，32（5）：58-76.
	LU Jian， ZHANG wenjun， YANG Haifei，et al ．Analysis of rear-end risk based on the indicator of time to collision ［J］．Journal of Transport Information and Safety，2014，32（5）：58-76.
14	FORMOSA N， QUDDUS M， ISON S，et al ．Predicting real-time traffic conflicts using deep learning ［J］．Accident Analysis & Prevention，2020，136：105429.
15	柳本民，廖岩枫，涂辉招，等．基于模拟实验的低等级公路车辆过弯风险预测模型［J］．同济大学学报（自然科学版），2021，49（4）：499-506.
	LIU Benmin， LIAO Yanfeng， TU Huizhao，et al ．Risk prediction model of vehicle driving in small radius curves based on simulation experiment ［J］．Journal of Tongji University （Natural Science），2021，49（4）：499-506.
16	交通部公路安全保障工程技术组．公路安全保障工程实施技术指南［M］．北京：人民交通出版社，2007.
17	HAN B， WU Y， SONG Y ．A novel active contour model based on median absolute deviation for remote sensing river image segmentation ［J］．Computers & Electrical Engineering，2017，62：209-223.
18	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 Xiaofeng， XIE Shikun， QIN Wenwen，et al ．Dynamic prediction of traffic accident risk in risky curve sections based on vehicle trajectory data ［J］．China Journal of Highway and Transport，2022，35（4）：277-285.
19	房锐，张琪，胡澄宇，等．基于风险矩阵的干线公路弯道路段交通冲突风险评估模型［J］．交通运输系统工程与信息，2021，21（2）：166-172.
	FANG Rui， ZHANG Qi， HU Chengyu，et al ．Risk assessment model based on risk matrix for traffic conflict on arterial highway bend section ［J］．Journal of Transportation Systems Engineering and Information Technology，2021，21（2）：166-172.
20	HAN H. The utility of receiver operating characteristic curve in educational assessment： performance prediction ［J］．Mathematics，2022，10（9）：1493.

冲突严重程度等级	冲突阈值/s
冲突严重程度等级	上行	下行
严重冲突	（0，1.4］	（0，1.3］
一般冲突	（1.4，3.2］	（1.3，3.4］
轻微冲突	（3.2，5.1］	（4，5.4］

指标	定义
CX	车型（0表示小型车，1表示大型车）
N	大车混入率（%）
DR	方向（0表示上行，1表示下行）
V1	断面速度差（m/s）
Q	断面交通量（辆/min）
SM1	路段平均车头间距（m）
VM	平均车速（m/s）
VD	车速标准差（m/s）
WM	平均角速度（（°）/s）
WD	角速度标准差（（°）/s）
AM	平均向心加速度（m/s²）
AD	向心加速度标准差（m/s²）
SM	平均车头间距（m）
SD	车头间距标准差（m）
A2M	平均纵向加速度（m/s²）
A2D	纵向加速度标准差（m/s²）

预测模型	预测值	真实值
预测模型	预测值	冲突发生	冲突不发生
PSO-BPNN	冲突发生	31	7
PSO-BPNN	冲突不发生	11	23
PSO-RF	冲突发生	39	11
PSO-RF	冲突不发生	4	18
PSO-SVM	冲突发生	37	15
PSO-SVM	冲突不发生	5	15

评估指标	PSO-BPNN	PSO-RF	PSO-SVM
正确率	75.00	79.17	72.22
灵敏度	73.81	90.70	88.10
特异度	76.67	62.07	50.00
误报率	23.33	37.93	50.00

[1]	WEN Huiying, WU Jiabin, QI Weiwei, et al. CP-CS Fusion Model for On-Ｒamp Merging Area on the Highway [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(2): 50-57.
[2]	. Continuous Network Design under Stochastic User Equilibrium [J]. Journal of South China University of Technology (Natural Science Edition), 2017, 45(11): 0-0.
[3]	Chen Jin Guo Xiao-feng Li Song-lin Sun Zhen-ye. Structural Optimization of Pre-Bending Wind Turbine Blade Based on Parametric Modeling [J]. Journal of South China University of Technology (Natural Science Edition), 2014, 42(12): 90-96,111.