山区高速公路多桥隧段路侧事故预测研究

Study on Roadside Accident Prediction of Multi-bridge and Multi-tunnel Section on Expressway in Mountainous Area

为保障山区高速公路多桥隧段路侧交通安全,优化路侧交通设施,减少桥梁群、隧道群及桥隧群间因行驶环境变化过频造成的路侧交通事故,结合驾驶员行车规律,借助统计学、机器学习等相关理论,建立了山区高速公路多桥隧环境下路侧事故起数、客货车事故数量的预测模型。为分析高速公路行车环境对驾驶员视觉、心理和操作特性的影响,从道路线形、交通构造物、交通环境及天气条件4个方面选取了10个预测指标;通过Spearman相关性分析,解释了路侧事故与10个预测指标间的作用机理;建立了基于BPNN(BP神经网络)、GA-BPNN(GA-BP神经网络)、PSO-BPNN(PSO-BP神经网络)的路侧事故预测模型,以MAE(平均绝对误差)、RMSE(均方根误差)、MAPE(平均绝对百分比误差)为模型评价指标,择优选取预测模型。利用渝湘高速公路近5 a事故形态,对侧翻、侧面相撞及碰撞固定物的路侧事故数据进行了实例验证。结果表明:山区高速公路多桥隧段路侧事故受到10个预测指标的综合影响,与路段长度、弯道比例、桥梁比例等因素呈正相关,且路段长度的影响程度最大;相较于BPNN和GA-BPNN预测模型,PSO-BPNN的MAE,RMSE,MAPE误差指标平均降低18.5%,17.65%,24.16%,模型预测误差更小、精度更高;路侧事故起数、客货车事故数量的精确预测,可为路侧设施优化设计提供有效的决策支撑。

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.