合流区域多车交互风险实时评估方法

doi:10.13229/j.cnki.jdxbgxb20210148

摘要/Abstract

摘要：

为探究合流区多车交互换道条件下的交通安全状况，开展了合流区多车交互风险实时评估研究。考虑车辆动力学以及多车交互作用特性，构建了基于车辆物理状态层、多车交互层和风险概率层的贝叶斯分层风险实时评估模型。利用MCMC吉布斯取样法标定模型参数，采用后验预测 $p$ 值、参数分位数变化检验模型参数的有效性，通过仿真分析评价模型的实时评估性能，采用k-means聚类法对多车交互风险进行分级。结果表明：模型参数BGR统计值均小于0.1，Durbin-Watson后验p值、正态性假设p值、检验分布对称性p值和峰度p值都接近0.5，说明该风险评估模型收敛且具有良好的拟合性，各级风险的AUC结果表明模型对低风险、较高风险及高风险的识别较为准确，性能较好。本文研究可对一定时段内的车辆运行风险进行评估，为驾驶决策提供参考依据。

关键词: 交通运输安全工程, 风险实时评估, 贝叶斯分层模型, 合流区域, 多车交互

Abstract:

To explore the traffic safety characteristics of the multi-vehicle interactive lane-changing at the merging area， the study of real-time multi-vehicle interactive risk assessment was carried out. Considering the characteristics of vehicle dynamics and multi-vehicle interaction， a Bayesian hierarchical model of real-time risk assessment was constructed based on the physical state layer， multi-vehicle interaction layer and risk probability layer of vehicles. The model parameters were calibrated by MCMC Gibbs sampling method. The model validity was tested by posterior prediction of p value and variation of parameter quantile. And the predictive performance of the model was evaluated by simulation analysis. The method of k-means clustering was adopted to classify the risk level of multi-vehicle interaction. The results show that the statistical BGR of model parameters are all less than 0.1. And the p value of Durbin-Watson's posterior， normal hypothesis， test distribution symmetry and kurtosis are all close to 0.5. So the risk assessment model is convergent and has good fitting. The AUC results show that the model is more accurate in identifying low risk， higher risk and highest risk， which has good performance. The research can evaluate the vehicle operation risk in a certain period of time and provide a reference for driving decision-making.

Key words: transportation safety engineering, real-time risk assessment, Bayesian hierarchical model, merging area, multi-vehicle interaction

中图分类号:

U492.8

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.

Jie-yu ZHU,Yan-li MA. Real-time risk assessment method of multi-vehicle interaction at merging area[J]. Journal of Jilin University(Engineering and Technology Edition), 2022, 52(7): 1574-1581.

图/表 14

图1

表1

图2

图3

表2

矩阵构造"

	1	2	3	4	5	6	7	8
1	_	$S 12$	$S 13$	$S 14$	$S 15$	$S 16$	$S 17$	$S 18$
2	$S 21$	_	$S 23$	$S 24$	$S 25$	$S 26$	$S 27$	$S 28$
3	$S 31$	$S 32$	_	$S 34$	$S 35$	$S 36$	$S 37$	$S 38$
4	$S 41$	$S 42$	$S 43$	_	$S 45$	$S 46$	$S 47$	$S 48$
5	$S 51$	$S 52$	$S 53$	$S 54$	_	$S 56$	$S 57$	$S 58$
6	$S 61$	$S 62$	$S 63$	$S 64$	$S 65$	_	$S 67$	$S 68$
7	$S 71$	$S 72$	$S 73$	$S 74$	$S 75$	$S 76$	_	$S 78$
8	$S 81$	$S 82$	$S 83$	$S 84$	$S 85$	$S 86$	$S 87$	_

表2

表3

多车交互模型参数标定"

交互车辆数/辆	$β 1$ / $10 - 2$	$β 2$ / $10 - 2$	$β 3$ / $10 - 3$	$β 4$ / $10 - 3$	$τ$
2	0.232	1.037	1.064	4.950	3.914
3	0.130	0.107	0.207	4.977	3.711
4	1.022	0.647	7.976	2.387	3.612
5	1.022	0.647	7.976	2.387	3.411
6	1.022	0.472	7.976	2.387	3.209
7	1.295	0.107	0.207	4.977	3.108

表3

图4

表4

图5

表5

表6

表7

图6

表8

参考文献 19

1	Ahammed M A, Hassan Y, Sayed T A. Modeling driver behavior and safety on freeway merging areas[J]. Journal of Transportation Engineering, 2008, 134(9):370-377.
2	Lee C, Abdel-Aty M. Analysis of crashes on freeway ramps by location of crash and presence of advisory speed signs[J]. Journal of Transportation Safety & Security, 2009, 1(2):121-134.
3	Mergia W Y, Eustace D, Chimba D, et al. Exploring factors contributing to injury severity at freeway merging and diverging locations in Ohio[J]. Accident Analysis and Prevention, 2013, 55(6):202-210.
4	Cafiso S, Graziano A D, Silvestro G D, et al. Development of comprehensive accident models for two-lane rural highways using exposure, geometry, consistency and context variables[J]. Accident Analysis & Prevention, 2010, 42(4):1072-1079.
5	Geedipally S R, Lord D, Dhavala S S. The negative binomial-Lindley generalized linear model: Characteristics and application using crash data[J]. Accident Analysis and Prevention, 2012, 45:258-265.
6	Eustace D, Aylo A, Mergia W Y. Crash frequency analysis of left-side merging and diverging areas on urban freeway segments——a case study of I-75 through downtown Dayton, Ohio[J]. Transportation Research Part C, 2015, 50(1):78-85.
7	王雪松, 宋洋, 黄合来, 等. 基于分层负二项模型的城郊公路安全影响因素研究[J].中国公路学报, 2014, 27(1):100-106.
	Wang Xue-song, Song Yang, Huang He-lai, et al. Research on influencing factors of Suburban Highway safety based on hierarchical negative binomial model[J]. Chinese Journal of Highways, 2014, 27(1):100-106.
8	马聪, 张生瑞, 马壮林, 等. 高速公路交通事故非线性负二项预测模型[J].中国公路学报, 2018, 31(11):176-185.
	Ma Cong, Zhang Sheng-rui, Ma Zhuang-lin, et al. Nonlinear negative binomial forecasting model for expressway traffic accidents[J]. Chinese Journal of Highways, 2018, 31(11):176-185.
9	郭璘, 周继彪, 董升, 等. 基于改进K-means算法的城市道路交通事故分析[J].中国公路学报,2012,31(4):270-279.
	Guo Lin, Zhou Ji-biao, Dong Sheng, et al. Analysis of urban road traffic accidents based on improved K-means algorithm [J]. Chinese Journal of Highways, 2012,31(4):270-279.
10	Abdel A M, Pande A. Identifying crash propensity using specific traffic speed conditions[J]. Journal of Safety Research, 2005, 36(1):97-108.
11	马艳丽,范璐洋,吕天玲,等.车辆运行风险贝叶斯网络量化分级方法[J].哈尔滨工业大学学报, 2020,52(3):33-37.
	Ma Yan-li, Fan Lu-yang, Lv Tian-ling, et al. Bayesian network quantitative classification method of vehicle operation risk[J]. Journal of Harbin Institute of Technology, 2020,52(3):33-37.
12	Xiong X, Chen L, Liang J, et al. Vehicle driving risk prediction based on markov chain model[J]. Discrete Dynamics in Nature and Society, 2018: 1-12.
13	Mohamed, M, Ahmed H. Application of stochastic gradient boosting technique to enhance reliability of real-time risk assessment: use of automatic vehicle identification and remote traffic microwave sensor data[J]. Transportation Research Record, 2018, 2386(1):26-34.
14	Ma Y, Qi S, Fan L, et al. Dynamic bayesian network approach to evaluate vehicle driving risk based on on-road experiment driving data[J]. IEEE Access, 2019, 99: 135050-135062.
15	Sun Jie, Sun Jian. A dynamic Bayesian network model for real-time crash prediction using traffic speed conditions data[J]. Transportation Research, Part C: Emerging Technologies, 2015, 54(5):176-186.
16	Abdel A M, Pande A, Lee C, et al. Crash risk assessment using intelligent transportation systems data and real-time intervention strategies to improve safety on freeways[J]. Journal of Intelligent Transportation Systems, 2007, 11(3):107-120.
17	Yang K, Wang X, Yu R, et al. A Bayesian dynamic updating approach for urban expressway real-time crash risk evaluation[J]. Transportation Research Part C: Emerging Technologies, 2018, 96:192-207.
18	John K. Doing Bayesian Data Analysis: A Tutorial with R and BUGS[M]. Beijing: China Machine Press, 1900.
19	刘金山, 夏强. 基于MCMC算法的贝叶斯统计方法[M]. 北京:科学出版社, 2015.

相关文章 15

[1]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	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.
[9]	郭应时, 付锐, 赵凯, 马勇, 袁伟. 驾驶人换道意图实时识别模型评价及测试[J]. 吉林大学学报(工学版), 2016, 46(6): 1836-1844.
[10]	孙璐，徐建，崔相民. 面板数据模型分析及交通事故预测[J]. 吉林大学学报(工学版), 2015, 45(6): 1771-1778.
[11]	王喆, 杨柏婷, 刘昕, 刘群, 宋现敏. 基于模糊聚类的驾驶决策判别[J]. 吉林大学学报(工学版), 2015, 45(5): 1414-1419.
[12]	马勇, 石涌泉, 付锐, 郭应时. 驾驶人分心时长对车道偏离影响的实车试验[J]. 吉林大学学报(工学版), 2015, 45(4): 1095-1101.
[13]	徐建, 孙璐. 解决交通事故数据分析中零值问题的模型[J]. 吉林大学学报(工学版), 2015, 45(3): 769-775.
[14]	金立生, 王岩, 刘景华, 王亚丽, 郑义. 基于Adaboost算法的日间前方车辆检测[J]. 吉林大学学报(工学版), 2014, 44(6): 1604-1608.
[15]	金立生,牛清宁,刘景华,秦彦光,吕欢欢. 不同道路线形下驾驶人认知分散状态监测[J]. 吉林大学学报(工学版), 2014, 44(3): 642-647.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

t/s	x/m	y/m	v/（km·h^-1）	a/（m·s^-2）	θ/（°）
258.600	689.331	-68.385	75.838	3.462	-5.7
258.667	690.336	-66.073	66.279	6.792	-5.5
258.733	691.214	-63.897	63.866	3.627	-5.3
258.800	692.009	-62.313	63.117	2.000	-5.1
258.867	693.339	-60.087	62.482	3.390	-5.0
258.933	693.918	-58.232	64.088	8.913	-4.8
…	…	…	…	…	…
259.667	702.272	-36.304	63.419	2.971	-3.0
259.733	703.415	-34.323	61.016	4.147	-2.8

假设	统计量	p值
误差独立性	Durbin‐Watson	0.683
正态性	基于x²检验	0.372
方差齐性	Levene	0.401
偏度	偏度系数	0.418
峰度	峰度系数	0.537

车辆编号	车道	位置/m	速度 /（km·h^-1）	加速度 /（m·s^-2）	方向角 /（°）
…	…	…	…	…	…
26	1?1	554.596	65.41	1.79	163.85
27	4?1	445.012	54.32	0.19	163.86
31	5?1	390.686	60.06	0.09	162.76
33	4?1	337.727	57.12	-0.21	163.74
34	4?1	315.543	58.45	-0.20	163.56
36	1?1	338.451	58.14	-0.02	163.83
37	1?1	311.347	61.54	-0.07	163.79
…	…	…	…	…	…

风险级别	AUC	标准误差	渐近概率	95% LCL	95% UCL
低	0.716 95	0.051 31	1.869 76E-4	0.616 39	0.817 51
一般	0.684 68	0.055 30	0.004 71	0.576 29	0.793 06
较高	0.771 43	0.048 97	5.590 11E-6	0.675 46	0.867 41
高	0.803 34	0.045 98	1.876 27E-7	0.713 22	0.893 46