基于潜在类别模型的急陡弯路段驾驶行为辨析

doi:10.13229/j.cnki.jdxbgxb.20230192

摘要/Abstract

摘要：

针对急陡弯中各类驾驶员的行车特征区分问题，提出了基于车辆行驶参数的驾驶员行为分类方法。通过分析实车驾驶数据，筛选出车型、入弯前速度、出弯后速度、入弯前减速行为、是否跟驰行驶以及入/出弯间速度差6项变量，构建了潜在类别模型，并基于该模型确定了各类驾驶员的特征。结果表明：该模型可将急陡弯中的驾驶员分为平稳型、受限型和自由型3类。平稳型驾驶员各项特征参数均居于3类驾驶员的中位，倾向于匀速入、出弯；受限型驾驶员在入弯时有最明显的减速或跟驰行驶特征，而自由型驾驶员则拥有最高的入、出弯速度，且出弯后的减速行为最为明显。

关键词: 交通运输系统工程, 驾驶行为, 急陡弯, K-means聚类, 潜在类别模型, 驾驶员分类

Abstract:

The issue of distinguishing driving behavior characteristics in steep sharp curves was addressed by employing a behavior classification method based on vehicle driving parameters. After analyzing real driving data， six variables were selected， including vehicle type， velocity before curve， velocity after curve， deceleration before curve， car-following driving and differences in velocity pre- and post-curve. The characteristics of each type of drives were determined based on the construction of the latent model. The findings that drivers could be classified into three categories： stable drivers， restricted drivers， and free drivers. Stable drivers exhibited parameter values that fell between all three types， they tended to enter and exit curves at a consistent speed. Restricted drivers showed significant features of deceleration or car-following driving before curves. Conversely， the free drivers had the highest velocity before and after curve with their differences in velocity pre- and post-curve were also the highest.

Key words: engineering of communications and transportation system, driving behavior, steep sharp curve, K-means clustering, latent class model, driver classification

中图分类号:

U491.255

李德林,陈俊先,王永岗,王露,沈照庆. 基于潜在类别模型的急陡弯路段驾驶行为辨析[J]. 吉林大学学报(工学版), 2024, 54(12): 3526-3533.

De-lin LI,Jun-xian CHEN,Yong-gang WANG,Lu WANG,Zhao-qing SHEN. Identification of driving behavior on steep sharp curves based on latent class model[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(12): 3526-3533.

图/表 11

图1

表1

表2

图2

图3

表3

表4

表5

表6

表7

表8

参考文献 22

1	国家统计局.交通事故年度数据查询[DB/OL].[2023-01-12].
2	吕璞,柏强,陈琳. 融合深度反残差与注意力机制的山区高速公路事故严重程度预测模型[J]. 中国公路学报, 2021, 34(6): 205-213.
	Pu Lyu, Bai Qiang, Chen Lin. A model for predicting the severity of accidents on mountainous expressways based on deep inverted residuals and attention mechanisms[J]. China Journal of Highway and Transport, 2021, 34(6): 205-213.
3	胡立伟,薛刚,李林育,等. 高原地质及气象环境下公路交通风险致因耦合分析[J]. 中国公路学报, 2018, 31(1): 110-119.
	Hu Li-wei, Xue Gang, Li Lin-yu, et al. Analysis of coupling of highway traffic risks in geological and meteorological environment of plateau regions[J]. China Journal of Highway and Transport, 2018, 31(1): 110-119.
4	Praveena P, Srinivas P S. Modeling crash injury severity by road feature to improve Safety[J]. Traffic Injury Prevention, 2018, 19(1): 102-109.
5	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 Cheng-yu, 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.
6	曲昭伟,李霖,陈永恒,等.长区间掉头车辆特性分析及其安全评价[J].吉林大学学报:工学版,2024,54(8):2206-2213 .
	Qu Zhao-wei, Li Lin, Chen Yong-heng, et al. Traffic characteristics and safety analysis of long interval U-turn intersections[J]. Journal of Jilin University (Engineering and Technology Edition), 2024,54(8): 2206-2213 .
7	王海晓,李永翔,丁旭,等.基于边缘智能的城市下穿隧道车辆行车安全预测[J].吉林大学学报: 工学版, 2022, 52(6): 1337-1343.
	Wang Hai-xiao, Li Yong-xiang, Ding Xu, et al. Traffic safety prediction of urban underpass tunnel vehicles based on edge intelligence[J]. Journal of Jilin University (Engineering and Technology Edition), 2022, 52(6): 1337-1343.
8	Wu J W, Yan X D, Radwan E. Discrepancy analysis of driving performance of taxi drivers and non-professional drivers for red-light running violation and crash avoidance at intersections[J]. Accident Analysis & Prevention, 2016, 91: 1-9.
9	Mani K, Mun S W, Hayati K. Speeding among taxi drivers in Selangor, Malaysia[J]. Injury Prevention, 2010, 16(1): No.A14.
10	Ahmed M, Abdel A M, Yu R. Assessment of Interaction of crash occurrence mountainous freeway geometry, real-time weather, and traffic data[J]. Transportation Research Record, 2012(1): 51-59.
11	Yuan J, Abdel A M, Wang L, et al. Real-time crash risk analysis of urban arterials incorporating Bluetooth, weather and adaptive signal control data[DB/OL].[2023-01-13].
12	Athanasios T. Incorporating real-time traffic and weather data to explore road accident likelihood and severity in urban arterials[J]. Journal of Safety Research, 2017, 61: 9-21.
13	孟祥海,张道玉,吴佩洁. 滑动窗窗体长度及滑动步长对事故多发路段鉴别影响[J]. 交通运输系统工程与信息, 2018, 18 (4): 148-155.
	Meng Xiang-hai, Zhang Dao-yu, Wu Pei-jie. The impact of window size and sliding length on the results of black spots identification[J]. Journal of Transportation Systems Engineering and Information Technology, 2018, 18(4): 148-155.
14	Wang X, Feng M. Freeway single and multi-vehicle crash safety analysis: influencing factors and hotspots [J]. Accident Analysis & Prevention, 2019, 132(1): 52-68.
15	李骁楠,陈丰,董博文. 考虑桥梁结构运动的河口大跨桥梁事故风险因素分析[J]. 同济大学学报: 自然科学版, 2021, 49(6): 863-871.
	Li Xiao-nan, Chen Feng, Dong Bo-wen. Analysis of risk factors of estuarine long-span bridge considering bridge structure movement[J]. Journal of Tongji University (Nature Science), 2021, 49(6): 863-871.
16	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 Feng, Hu Ping, Huang Yu. Traffic safety evaluation of highway tunnel based on combined model[J]. Journal of Highway and Transportation Research and Development, 2021, 38(7): 85-95.
17	钱勇,马建霄,赵顗,等. 基于集对可拓物元模型的公路隧道运营环境安全评价方法[J]. 森林工程, 2020, 36(1): 87-95.
	Qian Yong, Ma Jian-xiao, Zhao Yi, et al. Safety evaluation method for highway tunnel operation environment based on set -pair extension matter element model[J]. Forest Engineering, 2020, 36(1): 87-95.
18	Yan M H, Xu J L. Prediction model for brake-drum temperature of large trucks on consecutive mountain downgrade routes based on energy conservation law[J]. Mathematical Problems in Engineering, 2018, 2018(11): No.4587673.
19	丰明洁,王婷,王雪松,等. 山区高速公路平纵组合路段设计安全评估[J]. 北京工业大学学报, 2018, 44(6): 919-925.
	Feng Ming-jie, Wang Ting, Wang Xue-song, et al. Safety evaluation of combined horizontal and vertical alignments on mountainous freeways[J]. Journal of Beijing University of Technology, 2018, 44(6): 919-925.
20	寇云蛟. 小半径弯坡路段行车特性分析与安全处置策略研究[D]. 重庆:重庆交通大学交通运输学院, 2020.
	Kou Yun-jiao. Analysis of driving characteristics and study of safety disposal strategy in small radius curve section[D]. Chongqing:College of Traffic & Transportation, Chongqing Jiaotong University, 2020.
21	张晓波. 三岔型枢纽互通事故高发匝道的形成机制与安全提升研究[J]. 中国安全生产科学技术, 2022, 18(2): 198-205.
	Zhang Xiao-bo. Study on formation mechanism and safety improvement of accident-prone ramp on "T" shape hub interchange [J]. Journal of Safety Science and Technology, 2022, 18(2): 198-205.
22	邱皓政. 潜在类别模型的原理与技术[M]. 北京: 教育科学出版社, 2008.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

编号	车牌	车型	入弯速度/（km·h^-1）	出弯速度/（km·h^-1）	速度差/（km·h^-1）	入弯前减速行为	跟驰行为
1	陕H68839	小汽车	62.86	62.39	0.47	无	无
2	陕EWD075	小汽车	57.10	42.73	14.36	有	无
3	陕HN5065	小汽车	54.22	49.14	5.08	无	无
4	陕A3B015	摩托	53.60	54.83	-1.22	有	无
5	陕A2UE90	小汽车	59.69	54.97	4.72	无	有
6	陕HW5988	小汽车	54.32	49.10	5.22	有	无
7	陕H18682	货车	66.24	55.55	10.69	有	无

外显变量	聚类数	聚类中心
入弯速度/（km·h^-1）	1	24.08
	2	36.86
	3	45.25
	4	55.55
	5	67.90
出弯速度/（km·h^-1）	1	23.00
	2	35.28
	3	44.10
	4	54.36
	5	67.25
速度差/（km·h^-1）	1	-8.53
	2	0.43
	3	6.73
	4	9.84

编号	变量名	水平	样本数量	样本比例/%
V₁	车型	1	534	82.28
		2	72	11.09
		3	43	6.63
V₂	入弯速度/（km·h^-1）	1	81	12.48
		2	185	28.51
		3	239	36.83
		4	96	14.79
		5	42	6.47
V₃	出弯速度/（km·h^-1）	1	75	11.56
		2	153	23.57
		3	264	40.68
		4	110	16.95
		5	47	7.24
V₄	速度差/（km·h^-1）	1	87	13.41
		2	282	43.45
		3	220	33.90
		4	60	9.24
V₅	入弯前减速行为	1	220	33.90
V₅	入弯前减速行为	2	429	66.10
V₆	跟驰行驶行为	1	282	43.45
V₆	跟驰行驶行为	2	367	56.55

潜在类别个数	AIC	BIC	χ2	p-value
2	7 004.29	7 143.03	2 443.92	4.00E-41
3	6 557.47	6 767.81	1 212.96	0.000 16
4	6 319.56	6 601.51	799.42	0.127
5	6 196.05	6 549.61	427.29	1.000

外显变量名称	水平	潜在类别
外显变量名称	水平	第1类	第2类	第3类
车型	1	0.870 5	0.750 1	0.847 1
	2	0.107 5	0.114 2	0.112 3
	3	0.022 0	0.135 8	0.040 6
入弯速度	1	0.000 2	0.380 9	0.000 3
	2	0.160 8	0.618 2	0.000 6
	3	0.838 8	0.000 5	0.068 7
	4	0.000 2	0.000 2	0.647 2
	5	0.000 1	0.000 1	0.283 2
出弯速度	1	0.000 1	0.328 4	0.000 3
	2	0.000 4	0.669 7	0.000 5
	3	0.966 4	0.001 6	0.001 0
	4	0.033 0	0.000 2	0.681 4
	5	0.000 1	0.000 1	0.316 9
入弯前减速行为	1	0.343 8	0.341 9	0.325 7
入弯前减速行为	2	0.656 2	0.658 1	0.674 3
跟驰行驶	1	0.416 5	0.627 0	0.171 2
跟驰行驶	2	0.583 5	0.373 0	0.828 8
总体概率		0.420 1	0.351 6	0.228 3