考虑风险异质特性的路网交通事故风险评估方法

doi:10.13229/j.cnki.jdxbgxb.20211356

摘要/Abstract

摘要：

针对目前通常采用的以事故数据驱动为主的路网交通风险评估方法，忽略了一般道路、隧道、桥梁等不同道路类型的风险致因差异影响，致使评估结果不准确的问题，提出了一种考虑风险异质特性的路网交通事故风险评估方法。该方法依据路网不同道路类型风险致因的先验知识及事故密度分布特性，提出一种“由粗到精”的风险异质路段级联划分策略，实现风险异质路段的准确划分。引入道路风险自适应的事故风险空间分布函数，构建异质风险路段交通风险评估模型，实现路网风险整体评估。结合国际公开事故数据库，将本文方法与固定带宽核密度估计方法进行对比，结果表明：本文方法对交通风险的挖掘能力更强，对路网风险的估计更加符合实际情况。

关键词: 交通工程, 路网风险评估, 密度峰值聚类, 异质风险, 交通安全

Abstract:

At present， the risk assessment for road network is mainly based on accident data-driven methods. These methods ignore the risk factors differences on different types of roads， such as the ordinary road， tunnel， bridge， and so on. And this will induce the risk assessment for road network is inaccuracy. Aiming at this problem， a traffic accident risk assessment method for road network was presented considering risk heterogeneity. In this method， a road cascading segmentation strategy from coarse to fine was proposed according to the risk factors prior knowledge of different road types and the distribution characteristics of accidents density. This would achieve the accurate division of road segments with heterogeneous risk. Then an adaptive accident risk spatial distribution function was introduced. And a traffic risk assessment model for road segments with heterogeneous risk was established to realize the overall risk assessment of road network. Based on the international open accident database， the proposed method was compared with kernel density estimation with fixed bandwidth. The results show that the presented method has a better ability to discover traffic risk. And the assessment of road network risk is more consistent with actual situation by using the presented method.

Key words: traffic engineering, road network risk assessment, density peaks clustering, heterogeneous risk, traffic safety

中图分类号:

U491.3

曹倩,李志慧,陶鹏飞,马永建,杨晨曦. 考虑风险异质特性的路网交通事故风险评估方法[J]. 吉林大学学报(工学版), 2023, 53(10): 2817-2825.

Qian CAO,Zhi-hui LI,Peng-fei TAO,Yong-jian MA,Chen-xi YANG. Traffic accident risk assessment method for road network considering risk heterogeneity[J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(10): 2817-2825.

图/表 13

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

图12

表1

参考文献 19

1	田准, 张生瑞. 优化经验贝叶斯事故黑点识别与排序方法[J]. 长安大学学报:自然科学版, 2019, 39(5): 115-126.
	Tian Zhun, Zhang Sheng-rui. Identification and ranking of accident black spots using advanced empirical Bayes method[J]. Journal of Chang'an University(Natural Science Edition), 2019, 39(5): 115-126.
2	Qu X B, Meng Q. A note on hotspot identification for urban expressways[J]. Safety Science, 2014, 66: 87-91.
3	Ghadi M, Torok A, Tanczos K. Integration of probability and clustering based approaches in the field of black spot identification[J]. Periodica Polytechnica-civil Engineering, 2019, 63(1): 46-52.
4	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 risky curve sections based on vehicle trajectory data[J]. China Journal of Highway and Transport, 2022, 35(4): 277-285.
5	范存威. 山区公路长下坡路段运营安全分析与评价[D]. 重庆: 重庆交通大学交通运输学院, 2012.
	Fan Cun-wei. Analysis and evaluation of operation safety in mountainous and long downhill sections[D]. Chongqing: College of Traffic and Transportation, Chongqing Jiaotong University, 2012.
6	李林超. 高速公路隧道出入口段交通安全分析与改善措施[D]. 西安: 长安大学公路学院, 2015.
	Li Lin-chao. Safety assessment and improvement at the entrance and exit of expressway tunnel[D]. Xi'an: School of Highway,Chang'an University, 2015.
7	过秀成, 盛玉刚, 潘昭宇, 等. 公路交通事故黑点总体特征分析[J]. 东南大学学报:自然科学版, 2007, 37(5): 930-933.
	Guo Xiu-cheng, Sheng Yu-gang, Pan Zhao-yu, et al. Analysis of general characteristics for highway traffic accident black-spots[J]. Journal of Southeast University (Natural Science Edition), 2007, 37(5): 930-933.
8	胡新民, 刘涛, 张天华, 等. 道路黑点识别与改善[J]. 交通运输工程学报, 2004, 4(1): 106-109.
	Hu Xin-min, Liu Tao, Zhang Tian-hua, et al. Highway black spot recognition and improvement[J]. Journal of Traffic and Transportation Engineering, 2004, 4(1): 106-109.
9	Borsos A, Cafiso S, D'agostino C, et al. Comparison of Italian and Hungarian black spot ranking[C]∥The 6th Transport Research Arena, Warsaw, Poland, 2016: 2148-2157.
10	耿超, 彭余华. 基于动态分段和DBSCAN算法的交通事故黑点路段鉴别方法[J]. 长安大学学报:自然科学版, 2018, 38(5): 131-138.
	Geng Chao, Peng Yu-hua. Identification method of traffic accident black spots based on dynamic segmentation and DBSCAN algorithm[J]. Journal of Chang'an University (Natural Science Edition), 2018, 38(5): 131-138.
11	Dereli M A, Erdogan S. A new model for determining the traffic accident black spots using GIS-aided spatial statistical methods[J]. Transportation Research Part A, 2017, 103: 106-117.
12	杨轸, 唐莹, 方守恩. 双曲正切函数在事故黑点鉴别中的应用[J]. 哈尔滨工业大学学报, 2011, 43(10): 143-148.
	Yang Zhen, Tang Ying, Fang Shou-en. Application of hyperbolic tangent function for accident prone location identification[J]. Journal of Harbin Institute of Technology, 2011, 43(10): 143-148.
13	崔洪军, 申晓静, 赵述捷, 等. 基于交通事故间距分布特征的事故黑点鉴定新方法[J]. 武汉理工大学学报, 2012, 34(2): 54-58.
	Cui Hong-jun, Shen Xiao-jing, Zhao Shu-jie, et al. New traffic accident black spots identification method based on abnormal accidents space[J]. Journal of Wuhan University of Technology, 2012, 34(2): 54-58.
14	Xia Z X, Yan J. Kernel density estimation of traffic accidents in a network space[J]. Computers, Environment and Urban Systems, 2008, 32(5): 396-406.
15	陈金林. 基于网络核密度估计城市路网事故黑点鉴别研究[D]. 南京: 东南大学交通学院, 2015.
	Chen Jin-lin. Research on identification hotspots in the urban road networks based on the network kernel density estimation method[D]. Nanjing: School of Transportation, Southeast University, 2015.
16	Anderson T K. Kernel density estimation and k-means clustering to profile road accident hotspots[J]. Accident Analysis and Prevention, 2009, 41(3): 359-364.
17	Bil M, Andrasik R, Janoska Z. Identification of hazardous road locations of traffic accidents by means of kernel density estimation and cluster significance evaluation[J]. Accident Analysis and Prevention, 2013, 55: 265-273.
18	Xie Z X, Yan J. Detecting traffic accident clusters with network kernel density estimation and local spatial statistics: an integrated approach[J]. Journal of Transport Geography, 2013, 31: 64-71.
19	Rodriguez A, Laio A. Clustering by fast search and find of density peaks[J]. Science, 2014, 344(6191): 1492-1496.

相关文章 15

[1]	马壮林,崔姗姗,胡大伟,王晋. 限行政策下传统小汽车出行者出行方式选择[J]. 吉林大学学报(工学版), 2023, 53(7): 1981-1993.
[2]	张雅丽,付锐,袁伟,郭应时. 考虑能耗的进出站驾驶风格分类及识别模型[J]. 吉林大学学报(工学版), 2023, 53(7): 2029-2042.
[3]	尹超英,陆颖,邵春福,马健霄,许得杰. 考虑空间自相关的建成环境对通勤方式选择的影响[J]. 吉林大学学报(工学版), 2023, 53(7): 1994-2000.
[4]	潘恒彦,王永岗,李德林,陈俊先,宋杰,杨钰泉. 基于交通冲突的长纵坡路段追尾风险评估及预测[J]. 吉林大学学报(工学版), 2023, 53(5): 1355-1363.
[5]	宋灿灿,荆迪菲,谢俊峰,康可心. 设置广告牌的高速公路平曲线路段驾驶行为分析[J]. 吉林大学学报(工学版), 2023, 53(5): 1345-1354.
[6]	卢凯,徐广辉,叶志宏,林永杰. 考虑清空时间的双向队首绿波协调控制数解算法[J]. 吉林大学学报(工学版), 2023, 53(2): 421-429.
[7]	翁剑成,魏瑞聪,何寒梅,徐海辉,王晶晶. 基于关联路链组的城市路网短时交通流预测模型[J]. 吉林大学学报(工学版), 2023, 53(11): 3104-3112.
[8]	魏路,高磊,李晋宏,杨建,田玉林. 基于密度峰值聚类的交通控制子区划分方法[J]. 吉林大学学报(工学版), 2023, 53(1): 124-131.
[9]	张鑫,张卫华. 快速路合流区主线不同交通状态下的安全性分析[J]. 吉林大学学报(工学版), 2022, 52(6): 1308-1314.
[10]	曲大义,赵梓旭,贾彦峰,王韬,刘琼辉. 基于Lennard-Jones势的车辆跟驰动力学特性及模型[J]. 吉林大学学报(工学版), 2022, 52(11): 2549-2557.
[11]	董春娇,董黛悦,诸葛承祥,甄理. 电动自行车出行特性及骑行决策行为建模[J]. 吉林大学学报(工学版), 2022, 52(11): 2618-2625.
[12]	曲大义,黑凯先,郭海兵,贾彦峰,王韬. 车联网环境下车辆换道博弈行为及模型[J]. 吉林大学学报(工学版), 2022, 52(1): 101-109.
[13]	张文会,伊静,刘委,于秋影,王连震. 基于MADYMO的大客车追尾碰撞事故乘员损伤机理[J]. 吉林大学学报(工学版), 2022, 52(1): 118-126.
[14]	刘志伟,刘建荣,邓卫. 基于潜在类别的无人驾驶汽车选择行为[J]. 吉林大学学报(工学版), 2021, 51(4): 1261-1268.
[15]	徐进,潘存书,符经厚,刘俊,王郸祁. 典型道路场景以及场景切换时的速度行为特性[J]. 吉林大学学报(工学版), 2021, 51(4): 1331-1341.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

路段	方法	路段长度/km	事故数/起	增加率/%	加权事故数/起	增加率/%
风险值前10%	本文	1.35	200	4.7	228	9.1
风险值前10%	F-KDE	1.35	191	4.7	209	9.1
风险值前20%	本文	2.7	282	3.7	309	5.1
风险值前20%	F-KDE	2.7	272	3.7	294	5.1
风险值前30%	本文	4.05	330	1.5	355	2.3
风险值前30%	F-KDE	4.05	325	1.5	347	2.3