Influence of the Combination Equilibrium of Horizontal and Crest Vertical Curves on Highway Safety

doi:10.12141/j.issn.1000-565X.210658

Abstract

Abstract:

To throughly analyze the quantitative relationship between the equilibrium of horizontal and vertical alignment combination and road safety, aiming at the “horizontal curve(HC)+crest vertical curve(CVC)” (referred to as HC-CVC) alignment combination, this study collected the road alignment (a total of 477 km), the traffic data and accident data from 2011 to 2018 of four interstate roads in Washington, D.C. as training data and test data. According to the characteristics of horizontal and vertical alignment combination, the paper suggested to consider the dislocation value, the horizontal curve radius, the vertical curve radius, the length of horizontal curve and the length of vertical curve as variables to characterize the equilibrium of horizontal and vertical alignment combination. Three machine learning models, namely, Decision Trees, Random Forests and Extremely Randomized Trees, were applied for model training to analyze the influence of HC-CVC combination on the accident rate per 100 000 000 vehicle kilometers. The prediction and fitting accuracy of Random Forests is the highest among all models. What’s more, sensitivity analysis and numerical analysis based on Random Forests model show that: when the horizontal curve radius is greater than 2.8 km or the vertical curve radius is greater than 58 km, the increase of horizontal and vertical curve radius has little impact on the road safety. At the same time, this paper also studied the correlation between variables and accident and suggested the value range of the variables when the horizontal curve radius is small. The research conclusions can provide reference for the subsequent quantitative optimization design and safety improvement of horizontal and vertical alignment combination.

Key words: highway alignment, road safety, combination of horizontal and crest vertical curves, equilibrium of horizontal and vertical alignment combination, machine learning

CLC Number:

U491.21

WANG Xiaofei, LI Siyu, CHEN Mi, et al. Influence of the Combination Equilibrium of Horizontal and Crest Vertical Curves on Highway Safety[J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(7): 76-84.

Figures/Tables 9

Fig.1

Fig.2

Table 1

Alignment， traffic and accident statistics"

变量的名称和单位	平均值	标准差	最小值	最大值
$R A$ /［ $次 ? k m ? 10 - 8 v e h - 1$ ］	11.46	11.88	0.00	59.33
错位值（即竖曲线起点与平曲线起点的差值） $x 1$ /m	98.27	225.24	-498.90	869.05
平曲线半径 $x 2$ /m	1 872.39	1 757.39	89.92	12 192.00
竖曲线半径 $x 3$ /m	23 318.62	22 905.28	3 762.96	121 920.00
平曲线长度 $x 4$ /m	440.95	244.47	67.97	1 506.63
竖曲线长度 $x 5$ /m	295.40	181.63	60.96	914.40
限制速度/（km·h^-1）	108.66	7.11	83.69	112.65
总车道数	4.95	1.37	3.00	9.00
右侧硬路肩宽度/m	2.89	0.64	0.00	6.71
左侧硬路肩宽度/m	1.22	0.70	0.00	3.05

Table 1

Table 2

Table 3

Fig.3

Fig.4

Fig.5

Fig.6

References 24

1	OROSZ G， MOEHLIS J， BULLO F ．Robotic reactions：delay-induced patterns in autonomous vehicle systems［J］．Physical Review E，2010，81（2）：025204/1-4.
2	OROSZ G， WILSON R E， STÉPÁN G ．Traffic jams：dynamics and control［J］．Philosophical Transactions of the Royal Society，2010，368（1928）：4455-4479.
3	KANELLAIDIS G， VARDAKI S ．Highway geometric design from the perspective of recent safety developments［J］．Journal of Transportation Engineering，2011，137（12）：841-844.
4	World Health Organization ．Global status report on road safety 2015［M］．Geneva：World Health Organization，2015.
5	JUNG S， WANG K，OH C，et al ．Development of highway safety policies by discriminating freeway curve alignment features［J］．KSCE Journal of Civil Engineering，2018，22（4）：1418-1426.
6	EASA S M， STRAUSS T R， HASSAN Y，et al ．Three-dimensional transportation analysis：planning and design［J］．Journal of Transportation Engineering，2002，128（3）：250-258.
7	LANK C， STEINAUER B ．Increasing road safety by influencing drivers’speed choice with sound and vibration［J］．Transportation Research Record：Journal of the Transportation Research Board，2011（2248）：45-52.
8	戢晓峰，吴亚欣，郝京京，等．平纵组合路段事故严重程度致因辨识模型［J］．交通运输系统工程与信息，2020，20（6）：197-204.
	JI Xiao-feng， WU Ya-xin， HAO Jing-jing，et al ．Severity factors analysis model of traffic accident on combined horizontal and vertical alignments［J］．Journal of Transportation Systems Engineering and Information Technology，2020，20（6）：197-204.
9	梁夏，郭忠印，方守恩．道路线形与道路安全性关系的统计分析［J］．同济大学学报（自然科学版），2002，30（2）：203-206.
	LIANG Xia， GUO Zhong-yin， FANG Shou-en. Statistic analyses of relations between road alignment and road safety［J］．Journal of Tongji University （Natural Science），2002，30（2）：203-206.
10	BAUER K M， HARWOOD D W ．Safety effects of horizontal curve and grade combinations on rural two-lane highways［C］∥Proceedings of 92th Annual Meeting of the Transportation Research Board．Washington，D.C.：Transportation Research Board，2013.
11	涂圣文，王冰，邓梦雪，等．考虑平纵组合的事故预测模型在双车道公路线形安全分析中的应用［J］.公路，2019，64（7）：196-203.
	TU Shengwen， WANG Bing， DENG Mengxue，et al. Application of accident prediction model in safety analysis of two-lane highway alignment considering horizontal and vertical combination［J］．Highway， 2019，64（7）：196-203.
12	HASSAN Y， EASA S M， ASCE M. Effect of vertical alignment on driver perception of horizontal curves［J］．Journal of Transportation Engineering，2003，129（4）：399-407.
13	王福建，魏晓冬，张郃生，等．平竖重合路段的弯道错觉及其对交通事故的影响［J］．中国公路学报，2009，22（3）：40-44.
	WANG Fu-jian， WEI Xiao-dong， ZHANG He-sheng，et al. Curve illusion resulted from combination of horizontal and vertical curves and its influence on traffic accidents ［J］．China Journal of Highway and Transport，2009，22（3）：40-44.
14	陈海龙，彭伟．改进BP神经网络在交通事故预测中的研究［J］．华东师范大学学报（自然科学版），2017（2）：61-68.
	CHEN Hailong， PENG Wei ．Research on improved BP neural network in forecasting traffic accidents［J］．Journal of East China Normal University （Natural Science），2017（2）：61-68.
15	邱锋. 基于智能算法的高速公路隧道交通事故预测研究［D］．西安：长安大学，2018.
16	ABELLÁN J， LÓPEZ G， dE OÑA J. Analysis of traffic accident severity using decision rules via decision trees［J］．Expert Systems with Applications，2013，40（15）：6047-6054.
17	孙轶轩，邵春福，赵丹，等．交通事故严重程度C5.0决策树预测模型［J］．长安大学学报（自然科学版），2014，34（5）：109-116.
	SUN Yixuan， SHAO Chunfu， ZHAO Dan，et al. Traffic accident severity prediction model based on C5.0 decision tree［J］．Journal of Chang’an University （Natural Science Edition），2014，34（5）：109-116.
18	沈阳．基于机器学习的高速公路平面线形指标推荐方法研究［D］．西安：长安大学，2020.
19	周志华．机器学习［M］．北京：清华大学出版社，2016.
20	BREIMAN L ．Random forests［J］．Machine Learning，2001；45（1）：5-32.
21	公路路线设计规范：［S］.
22	刘钊，杜威，闫冬梅，等．基于K近邻算法和支持向量回归组合的短时交通流预测［J］．公路交通科技，2017，34（5）：122-128，158.
	LIU Zhao， DU Wei， YAN Dongmei，et al. Short-term traffic flow forecast based on combination of K nearest neighbor algorithm and support vector regression［J］．Journal of Highway and Transportation Research and Development，2017，34（5）：122-128，158.
23	HUANG Helai， ZENG Qiang， PEI Xin，et al ．Predicting crash frequency using an optimised radial basis function neural network mode l［J］．Transportmetrica A： Transport Science，2016，12（4），330-345. .
24	许金良．道路勘测设计［M］．5版．北京：人民交通出版社，2019.

模型	max_depth	max_features	n_estimators
决策树	2	1
随机森林	3	3	4
极端随机树	16	1	32

模型	MAE		RMSE （测试集）	SMAPE/% （测试集）
模型	训练集	测试集	RMSE （测试集）	SMAPE/% （测试集）
决策树	7.34	9.25	13.77	67.94
随机森林	6.92	7.89	12.35	62.22
极端随机树	6.95	9.86	15.29	72.11

[1]	ZHOU Chuhao, LIN Peiqun, YAN Mingyue. Traffic Data Imputation Based on Self-Supervised Learning [J]. Journal of South China University of Technology(Natural Science Edition), 2023, 51(4): 101-114.
[2]	SONG Jian, WANG Wenlong, LI Dong, et al. Injection molding part size prediction method based on Stacking integration learning [J]. Journal of South China University of Technology(Natural Science Edition), 2022, 50(6): 19-26.
[3]	LIN Peiqun XIA Yu ZHOU Chuhao. Freeway Travel Time Prediction Based on Spatial and Temporal Characteristics of Road Networks [J]. Journal of South China University of Technology(Natural Science Edition), 2021, 49(8): 1-11.
[4]	JIA Ruo, DAI Shenghong, HUANG Ni, et al. Literature Review on Traffic Congestion Identification Methods [J]. Journal of South China University of Technology (Natural Science Edition), 2021, 49(4): 124-139.
[5]	ZHAO Jing, WANG Xuancang, FAN Zhenyang, et al. Evaluation on Performance of Asphalt Pavement Based on Support Vector Machine [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(9): 116-123.
[6]	ZHANG Ziye, LI Mingchang, LIANG Lingrui, et al. Improved Transfer Learning Algorithm Based on Cross-domain in Recommendation System [J]. Journal of South China University of Technology (Natural Science Edition), 2020, 48(11): 99-106.
[7]	. Elastic Property Prediction of Materials Based on Machine Learning and Feature Selection [J]. Journal of South China University of Technology (Natural Science Edition), 2019, 47(5): 48-55.
[8]	Fu Gui Han Guo- qiang Lu Feng Xu Zi- xin. Short- Term Traffic Flow Forecasting Model Based on Support Vector Machine Regression [J]. Journal of South China University of Technology (Natural Science Edition), 2013, 41(9): 71-76.
[9]	Yin Xun-fu Hao Zhi-feng. Regularized Kernel Density Estimation Algorithm Based on Sparse Bayesian Regression [J]. Journal of South China University of Technology (Natural Science Edition), 2009, 37(5): 123-129.