基于贝叶斯网络的高速公路交通事故严重程度预测及致因分析

doi:10.3969/j.issn.1674-0696.2023.07.12

摘要/Abstract

摘要： 为了深入研究高速公路交通安全，剖析高速公路交通事故的发生机理以及各类因素对高速公路交通事故严重程度的影响，收集曲靖市境内沪昆高速段2017—2019年的1 939起交通事故进行研究。以事故严重程度为因变量，筛选出人、车、路、环境4个大类下的与事故严重程度相关的19个影响因素为自变量，采用数据融合法基于树增广型贝叶斯网络构建事故严重程度预测模型，量化各因素间的影响关系，经特征筛选找出关键致因，并结合案例进行推理分析。结果表明：影响高速公路交通事故严重程度的关键致因依次为天气情况、视距情况、路面情况等。模型对高速公路事故严重程度预测准确率可达84.27%，高于传统贝叶斯方法，模型有效性验证良好。针对事故主要致因提出改进建议，可为交管部门提供准确事故信息辅助决策，加快事故响应速度，提高事故应急指挥能力。

关键词: 交通运输工程；高速公路；事故严重程度；树增广型贝叶斯网络；致因分析

Abstract: In order to study the freeway traffic safety in depth, the mechanism of freeway traffic accidents and the influence of various factors on the severity of freeway traffic accidents were analyzed. 1939 traffic accidents on Shanghai-Kunming Expressway in Qujing City from 2017 to 2019 were collected for research. Taking the accident severity as dependent variable, 19 influencing factors related to the accident severity were selected as independent variables under four categories such as people, vehicle, road and environment. Based on tree-enhanced Bayesian network, a prediction model of accident severity was established by data fusion method, and the influence relationships among various factors were quantified. The key causes were found by feature screening, and the reasoning analysis based on case studies was carried out. The results show that the key factors affecting the severity of traffic accidents on freeways are successively weather conditions, sight distance conditions, road conditions, etc. The prediction accuracy of the proposed model for the severity of freeway accidents can reach 84.27%, which is higher than that of the traditional Bayesian method, and the validity of the proposed model is well verified. According to the main causes of the accident, some improvement suggestions are put forward, which can provide accurate accident information to assist decision-making for traffic management departments, speed up the accident response and improve the emergency command ability.

Key words: traffic and transportation engineering; freeway; accident severity; tree-enhanced Bayesian network; cause analysis

中图分类号:

U491.31

成卫1，马铭炜1，张小龙2. 基于贝叶斯网络的高速公路交通事故严重程度预测及致因分析[J]. 重庆交通大学学报（自然科学版）, 2023, 42(7): 87-95.

CHENG Wei1, MA Mingwei1, ZHANG Xiaolong2. Prediction and Cause Analysis of Freeway Traffic Accident Severity Based on Bayesian Network[J]. Journal of Chongqing Jiaotong University(Natural Science), 2023, 42(7): 87-95.

参考文献

［1］高岩,董宪元,田飞.高速公路交通安全现状分析及管理对策［J］.中国安全生产科学技术,2015,11(10):110-115.
GAO Yan, DONG Xianyuan, TIAN Fei. Present situation analysis on highway traffic safety and management countermeasures［J］. Journal of Safety Science and Technology,2015,11(10):110-115.
［2］《中国公路学报》编辑部.中国交通工程学术研究综述·2016 ［J］.中国公路学报,2016,29(6):1-161.
Editorial Department of China Journal of Highway and Transport. Review on Chinas traffic engineering research progress：2016 ［J］. China Journal of Highway and Transport, 2016, 29 (6): l-161.
［3］裴玉龙,马骥.道路交通事故道路条件成因分析及预防对策研究［J］.中国公路学报,2003，16 (4):78-83.
PEI Yulong, MA Ji. Research oncountermeasures for road condition causes of traffic accidents ［J］. China Journal of Highway and Transport, 2003,16 (4)：78-83.
［4］李文权,王炜.交通事故的时间分布规律［J］.中国安全科学学报, 2005，15 (4):56-61,113.
LI Wenquan, WANG Wei. Time distribution of traffic accident ［J］. China Safety Science Journal, 2005,15(4)：56-61,113.
［5］赵金宝,邓卫,王建.基于贝叶斯网络的城市道路交通事故分析［J］.东南大学学报(自然科学版),2011,41(6):1300-1306.
ZHAO Jinbao, DENG Wei, WANG Jian. Bayesian network-based urban road traffic accidents analysis［J］. Journal of Southeast University（Natural Science Edition）,2011,41（6）：1300-1306.
［6］马壮林,邵春福,李霞.基于Logistic模型的公路隧道交通事故严重程度的影响因素［J］.吉林大学学报(工学版),2010,40(2):423-426.
MA Zhuanglin，SHAO Chunfu，LI Xia. Analysis of factors affecting accident severity in highway tunnels based on logistic model ［J］. Journal of Jilin University（Engineering and Technology Edition），2010,40(2):423-426.
［7］ BUCSUHZY K, MATUCHOV E, Z ??倴 U。VALA R, et al. Human factors contributing to the road traffic accident occurrence［J］. Transportation Research Procedia,2020,45:555-561.
［8］ LIYANAGE L N. The effect of human factor on the prevalence and severity of road accidents［J］. American Research Journal of Humanities & Social Science,2020，30(3):46-52
［9］ TAMAKLOE R, LIM S, SAM E F, et al. Investigating factors affecting bus/minibus accident severity in a developing country for different subgroup datasets characterised by time, pavement, and light conditions［J］. Accident Analysis and Prevention,2021,159: 106268.
［10］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 Xiaofeng, WU Yaxin, HAO Jinging, et al. Severityfactors 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.
［11］ MA Zhengjing, MEI Gang, CUOMO S. An analytic framework using deep learning for prediction of traffic accident injury severity based on contributing factors［J］. Accident Analysis and Prevention,2021,160: 106322.
［12］ WEN Huiying, XUE Gang. Injury severity analysis of familiar drivers and unfamiliar drivers in single-vehicle crashes on the mountainous highways［J］. Accident Analysis and Prevention,2020,144:105667.
［13］贺玉龙,陈兵硕,高鹏旺,等.基于未确知测度理论的高速公路交通安全评价［J］.重庆交通大学学报(自然科学版),2021, 40(2):8-12.
HE Yulong, CHEN Bingshuo, GAO Pengwang, et al. Highway traffic safety evaluation based on unascertained measure theory［J］. Journal of Chongqing Jiaotong University(Natural Science),2021, 40 (2):8-12.
［14］刘海珠. 道路交通事故严重程度影响因素分析及预测模型建立［D］.长春：吉林大学,2014.
LIU Haizhu. The Analysis of Influencing Factors for Crash Severity and the Establishment of Prediction Model［D］. Changchun：Jilin University,2014.
［15］陈昭明,徐文远,曲悠扬,等.基于混合Logit模型的高速公路交通事故严重程度分析［J］.交通信息与安全,2019,37(3):42-50.
CHEN Zhaoming, XU Wenyuan, QU Youyang, et al. Severity of traffic crashes on freeways based on mixed logit model ［J］. Journal of Transport Information and Safety, 2019， 37（3）：42-50.
［16］ HOU Qingzhong, MENG Xianghai, LENG Junqiang, et al. Application of a random effects negative binomial model to examine crash frequency for freeways in China［J］. Physica A: Statistical Mechanics and Its Applications, 2018,509：937-944.
［17］曹杰.贝叶斯网络结构学习与应用研究［D］.合肥：中国科学技术大学,2017.
CAO Jie. Bayesian Network Structure Learning and Application Research［D］. Hefei：University of Science and Technology of China,2017.
［18］ COOPER G F, HERSKOVITS E. A Bayesian method for the induction of probabilistic networks from data［J］. Machine Learning,1992,9(4):309-347.

[1]	李升朝，吴越，白雪萌，王玥，张海. 基于TOPSIS与灰色关联的危货车辆违规报警研究[J]. 重庆交通大学学报（自然科学版）, 2021, 40(07): 61-66.
[2]	王永岗，张衡，彭志鹏，周琬琦. 基于结构方程模型的出租车事故影响因素分析[J]. 重庆交通大学学报（自然科学版）, 2021, 40(06): 36-42.
[3]	鄢小文1，徐建闽2. 基于协调路径的节点关联性模型研究[J]. 重庆交通大学学报（自然科学版）, 2020, 39(09): 31-37.
[4]	王立晓1，左志1，杨晔1，刘江水2. 基于Scobit的交通事故受伤严重程度模型[J]. 重庆交通大学学报（自然科学版）, 2020, 39(04): 1-5.
[5]	陈一锴1，王富超1，王凯1，郑宏富2，石琴1. 基于二元Logistic的公路货运超载关键影响因素识别[J]. 重庆交通大学学报（自然科学版）, 2018, 37(05): 92-96.
[6]	杨春风，庄灿，孙吉书，闫晓晨. 道路交通事故多因素分析[J]. 重庆交通大学学报（自然科学版）, 2018, 37(04): 87-95.
[7]	孙小端，侯洋洋，贺玉龙，冯丙丙. 青藏高原双车道事故严重程度预测模型的建立[J]. 重庆交通大学学报（自然科学版）, 2017, 36(7): 106-110.
[8]	郑福维1，肖健2，卿湘涛1，谢宇枫3，张丹丹1. 吉凤茶高速公路气象要素特征分析[J]. 重庆交通大学学报（自然科学版）, 2017, 36(6): 109-114.
[9]	于泉，王萌，邓小惠. 基于向前搜索和K均值聚类的信号交叉口行人群集分类方法研究[J]. 重庆交通大学学报（自然科学版）, 2015, 34(1): 100-104.
[10]	邱洪波，杨斌，黄勇. 基于灰色理论的城市核心区道路交通安全分析[J]. 重庆交通大学学报（自然科学版）, 2013, 32(6): 1228-1231.
[11]	邱洪波，杨斌，黄勇. 基于灰色理论的城市核心区道路交通安全分析[J]. 重庆交通大学学报（自然科学版）, 2013, 32(6): 1228-1231.
[12]	徐慧芬，徐建涛. 山城主干道设计常见问题及安全设计要点[J]. 重庆交通大学学报（自然科学版）, 2013, 32(2): 244-0247.
[13]	徐慧芬，徐建涛. 山城主干道设计常见问题及安全设计要点[J]. 重庆交通大学学报（自然科学版）, 2013, 32(2): 244-247.
[14]	曹建军. 道路交通事故当量死亡人数的计算模型研究[J]. 重庆交通大学学报（自然科学版）, 2013, 32(1): 91-94.
[15]	郭静，艾明昱. 我国城市公共交通安全现状及对策[J]. 重庆交通大学学报（自然科学版）, 2012, 31(增1): 610-611.