Study on Roadside Accident Prediction of Multi-bridge and Multi-tunnel Section on Expressway in Mountainous Area
尚婷1, 唐杰1, 黄政东2, 周亮宇1, 吴鹏1
1. School of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, China; 2. School of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, China
Study on Roadside Accident Prediction of Multi-bridge and Multi-tunnel Section on Expressway in Mountainous Area
1. School of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, China; 2. School of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, China
摘要In order to ensure the roadside traffic safety of the multi-bridge and multi-tunnel section on the expressway in mountainous areas and optimize the roadside traffic facilities, and reduce the road traffic accidents caused by the over-frequency changes of the driving environment among the bridge group and tunnel group and their intervals, combining with the driving rules, the prediction model of the numbers of roadside accidents, passenger and freight vehicle accidents in multi-bridge and multi-tunnel section on the expressway in mountainous areas is established by using statistics, machine learning and other related theories. In order to analyze the influence of driving environment of expressway on drivers visual, psychological and operational characteristics, 10 prediction indicators are selected from the aspects of road alignment, traffic structure, traffic environment and weather condition. The action mechanism between roadside accidents and 10 predictive indicators is explained by employing Spearman correlation analysis. The roadside accident prediction model based on BPNN, GA-BPNN and PSO-BPNN are established. MAE, RMSE and MAPE are used as the model evaluation indicators to select the optimal model. The roadside accident data including rollover, side collision and collision with fixed objects are verified by examples by using the accident patterns of Chongqing-Hunan Expressway in the past 5 years. The result shows that (1) the roadside accidents of the roadside accidents of multi-bridge and multi-tunnel section on expressway in mountainous area are comprehensively affected by 10 prediction indicators, which are positively correlated with the length of road section, the proportion of curved roads and the proportion of bridges, and the influence of length of road section is the greatest; (2) compared with BPNN and GA-BPNN prediction models, the errors of MAE, RMSE, and MAPE of PSO-BPNN are reduced by 18. 5%, 17. 65%, and 24. 16% on average, and the model prediction error is smaller and the accuracy is higher; (3) the accurate prediction of the number of roadside accidents and the number of passenger and freight vehicle accidents can provide effective decision-making support for the optimization design of roadside facilities.
Abstract：In order to ensure the roadside traffic safety of the multi-bridge and multi-tunnel section on the expressway in mountainous areas and optimize the roadside traffic facilities, and reduce the road traffic accidents caused by the over-frequency changes of the driving environment among the bridge group and tunnel group and their intervals, combining with the driving rules, the prediction model of the numbers of roadside accidents, passenger and freight vehicle accidents in multi-bridge and multi-tunnel section on the expressway in mountainous areas is established by using statistics, machine learning and other related theories. In order to analyze the influence of driving environment of expressway on drivers visual, psychological and operational characteristics, 10 prediction indicators are selected from the aspects of road alignment, traffic structure, traffic environment and weather condition. The action mechanism between roadside accidents and 10 predictive indicators is explained by employing Spearman correlation analysis. The roadside accident prediction model based on BPNN, GA-BPNN and PSO-BPNN are established. MAE, RMSE and MAPE are used as the model evaluation indicators to select the optimal model. The roadside accident data including rollover, side collision and collision with fixed objects are verified by examples by using the accident patterns of Chongqing-Hunan Expressway in the past 5 years. The result shows that (1) the roadside accidents of the roadside accidents of multi-bridge and multi-tunnel section on expressway in mountainous area are comprehensively affected by 10 prediction indicators, which are positively correlated with the length of road section, the proportion of curved roads and the proportion of bridges, and the influence of length of road section is the greatest; (2) compared with BPNN and GA-BPNN prediction models, the errors of MAE, RMSE, and MAPE of PSO-BPNN are reduced by 18. 5%, 17. 65%, and 24. 16% on average, and the model prediction error is smaller and the accuracy is higher; (3) the accurate prediction of the number of roadside accidents and the number of passenger and freight vehicle accidents can provide effective decision-making support for the optimization design of roadside facilities.
基金资助:Supported by the Chongqing Science and Technology Bureau Foundation and Frontier Project (No. cstc2019jcyj-msxmX0695);the Youth Science and Technology Project of Chongqing Education Commission (No. KJQN201900722); the Chongqing Municipal Education Commission Primary and Secondary Schools Innovative Talents Training Project Plan (No. CY200704); the Chongqing Postgraduate Research Innovation Project (No. 2020S0034).
通讯作者:
SHANG Ting
引用本文:
尚婷, 唐杰, 黄政东, 周亮宇, 吴鹏. Study on Roadside Accident Prediction of Multi-bridge and Multi-tunnel Section on Expressway in Mountainous Area[J]. Journal of Highway and Transportation Research and Development, 2022, 16(4): 78-91.
SHANG Ting, TANG Jie, HUANG Zheng-dong, ZHOU Liang-yu, WU Peng. Study on Roadside Accident Prediction of Multi-bridge and Multi-tunnel Section on Expressway in Mountainous Area. Journal of Highway and Transportation Research and Development, 2022, 16(4): 78-91.
[1] ZEGGER C V,REINFURT D W. Accident Effects of Sideslope and Other Roadside Features on Two-lane Roads[J].Transportation Research Record,1988(1195):33-47. [2] DUMBAUGH E. Design of Safe Urban Roadsides:An Empirical Analysis[J]. Transportation Research Record Journal of the Transportation Research Board,2006,1961(1):74-82. [3] CAI Ming, CHENG Guo-zhu, ZHANG Su-lu, et al. Risk Assessment of Highway Roadside Accidents Based on Bayesian Network[J].Journal of Transportation Systems Engineering and Information Technology:2019,19(2):206-212. (in Chinese) [4] CHENG Guo-zhu, CHENG Rui, XU Liang, et al. Probabilistic Prediction of Road Accidents in Outer Lane of Small Curve Section Highways[J]. Journal of Harbin Institute of Technology, 2021, 53(3):178-185. (in Chinese) [5] LIU Yan, CHEN Jian-lei, LIU Zhi-gang, et al. Assessment Method for Roadside Risk Grade of Freeway in Mountainous Areas[J].Journal of Chongqing Jiaotong University(Natural Science Edition):2015,34(1):87-90. (in Chinese) [6] GAO Hai-long, KAN Wei-sheng, LI Chang-cheng,et al. Roadside Accidents Prediction Model for Two-lane Highway[J].Journal of Highway and Transportation Research and Development:2007,24(7):127-131. (in Chinese) [7] ZHANG Tie-jun, TANG Cheng-cheng. Research of Roadside Accident Prediction Models for Common Segments of Two-lane Roads in China[J].Journal of Highway and Transportation Research and Development:2008,25(4):147-150, 158. (in Chinese) [8] MA Zhuang-lin, ZHANG Hong-lu, ZHANG Yi-yi,et al. Roadside Accident Frequency Prediction Model on Expressway[J].Journal of Chang'an University(Natural Science Edition):2017(37):119-126. (in Chinese) [9] ZHANG Su-lu. Roadside Accident Forecasting and Risk Evaluation Method of Highway Horizontal Curve Segment[D]. Harbin:Harbin Institute of Technology, 2017. (in Chinese) [10] ZHEN Heng, LI Chang-cheng, LIU Yu, et al. A Roadside Safety Assessment Method Based on Bayesian Network[J]. Journal of Highway and Transportation Research and Development, 2008,25(2):139-144,154. (in Chinese) [11] ZHANG Tie-jun,TANG Cheng-cheng et al. A Study on Accident Modification Factor About Roadside Hazard Rating in Accident Prediction Models for Two Lane Highway in Mountainous Area[J]. Highway,2007(9):116-122. (in Chinese) [12] CHEN Hai-long,PENG Wei et al. Research on Improved BP Neural Network in Forecasting Traffic Accidents[J]. Journal of East China Normal University (Natural Science), 2017, (2):66-73. (in Chinese) [13] SUN Ke-da. The Research of Road Traffic Accident Predictive Model Based on Genetic BP Neural Networks[D]. Hangzhou:Zhejiang University of Technology, 2008. (in Chinese) [14] YE Feng, SUN Ke-da et al. The Application of Macroscopic Forecast of Road Traffic Accident Predictive Model Based on Genetic Neural Networks[J]. Journal of Zhejiang University of Technology, 2008,36(3):106-110. (in Chinese) [15] QIN Wei. Expressway Neural Network Crash Prediction Model Based on Negative Binomial Regression Analysis[D]. Harbin:Harbin Institute of Technology, 2017. (in Chinese) [16] JALAYER M, ZHOU H G. Evaluating the Safety Risk of Roadside Features for Rural Two-lane Roads Using Reliability Analysis[J]. Accident Analysis & Prevention, 2016,93:101-112. [17] ROQUE C, CARDOSO J L. SAFESIDE:A Computer-aided Procedure for Integrating Benefits and Costs in Roadside Safety Intervention Decision Making[J]. Safety Science, 2015, 74:195-205. [18] WU Xiao-feng, LU Hai-jun, YIN Tao. Highway Roadside Safety Active Guidance Technology[J].Journal of China & Foreign Highway,2010, 30(3):332-335. (in Chinese) [19] WANG Qing-zhou, CHEN Jia-meng, FAN Xin et al. A Study on Alignment Security of Tourist Highways in Mountain Areas Based on Heart Rate Change of Drivers[J]. Journal of Transport Information and Safety, 2018, 36(3):19-26. (in Chinese) [20] ZHANG Juan, ZHU Wen-qiang, LI Xiao-wei et al. Analysis of the Relationship of the Vehicle Drivers' Pupil Size Change with the Highway Alignment in the Status-in-situ of Long and Steep Continuous Slope[J]. Journal of Safety and Environment, 2018, 18(1):188-193. (in Chinese) [21] LING Lei, WU Hai-xiang. Expressway Traffic Safety Analysis[J].Journal of Highway and Transportation Research and Development:2003,20(S1):123-126. (in Chinese) [22] DUAN Meng-meng, Tang Bo-ming, HU Xu-hui, et al. Driver's Visual Load at Tunnel Entrance and Exit of Sections with High Ratio of Tunnels[J].Journal of Transportation Systems Engineering and Information Technology:2018, 18(3):117-123. (in Chinese) [23] YAN Ying, YE Fei, WANG Xiao-fei, et al. Analysis of Ambient Illumination and Driver's Pupil Area in Tunnel Group[J]. Journal of South China University of Technology (Natural Science Edition):2016,44(12):89-96. (in Chinese) [24] HU Jiang-bi, HE Lu-cheng, WANG Rong-hua, et al. Review of Safety Evaluation of Freeway Interchange[J]. China Journal of Highway and Transport, 2020,33(7):17-28. (in Chinese) [25] ZHANG Zhi-gang. Road Conditions, Traffic Environment and Traffic Accident Analysis[J].Journal of Highway and Transportation Research and Development, 2000,17(6):56-56. (in Chinese) [26] QIU Lei, CHIGAN Du, DENG Zhi-gang, et al. An Expressway Driving Risk Assessment Model Based on Influence Coefficient[J]. Journal of Highway and Transportation Research and Development, 2020, 37(3):126-132. (in Chinese) [27] WEN Hui-ying,XUE Gang. Comprehensive Analysis Method of Multi-factor Risks for Highway Traffic Accidents in Mountain Areas:Taking Rain and Fog Weather for Example[J].China Safety Science Journal:2019, 29(9):165-170. (in Chinese) [28] LU Huan, JI Xiao-feng, YANG Wen-chen, et al. Cause Analysis of Different Patterns of Traffic Accidents on Plateau Mountain Roads[J]. China Safety Science Journal:2019,29(5):44-49. (in Chinese) [29] CHEN Zheng, LI Qing-qing, XIAO Na-song, et al. Prediction of Diesel Spray Penetration Length Based on GA-BP Neural Network[J].Journal of Central South University(Science and Technology):2018,49(1):247-252. (in Chinese) [30] PENG Ya-qi, XU Cheng-dong, NIU Fei, et al. Prediction Model of Broadcast Ephemeris Orbit Error Based on PSO-BP Neural Network[J].System Engineering and Electronics:2019, 41(7):1617-1622. (in Chinese) [31] DUAN Meng-meng, Tang Bo-ming, LIU Tang-zhi, et al. Accident Prediction Model of Freeway with High Ratioof Bridges and Tunnels Based on Multivariate Nonlinear Regression[J]. Highway Engineering, 2018,43(6):126-130. (in Chinese) [32] FAN Zhong-zhou, ZHAO Yi, ZHOU Ning, et al. Integrated Model for Forecasting Waterway Traffic Accidents Based on the Gray-BP Neural Network[J].Journal of Safety and Environment:2020,20(3):857-861. (in Chinese) [33] DUAN Meng-meng, Tang Bo-ming, LIU Fei. Study on the Applicability of IHSDM in Accident Prediction of Freeway of High Proportion of Bridges and Tunnels in Mountain Area[J].Highway Engineering, 2018, 43(3):74-80. (in Chinese)
2022, Vol. 16 
