双车道高速公路追尾事故实时预测模型

A Real-hime Prediction Model for Rear-end Crash on Two-lane Freeway

现有的高速公路实时事故预测模型对高速公路信息化采集设备的布设密度和采集的数据粒度要求很高,在低信息化的高速公路管理工作上难以得到应用.结合国内高速公路信息化现状,使用单个检测器所采集的数据,对髙速公路追尾事故实时风险进行研究.基于江苏省扬州市启扬髙速公路上布设的超声波交通流检测器所采集的交通流数据,采用配对案例对照方法和二元逻辑回归,建立了双车道高速公路追尾事故实时预测模型.对事故前5-20 m in的交通流数据分别构建流量时空矩阵、速度时空矩阵、平均车头间距时空矩阵,通过引人矩阵特征值简化建模过程并避免了指标间的相关性过高问题.模型总体精度85.7%,事故预测精度33.3%,误报率低于2% ,相比已有模型总体预测精度较高,误报率较低,表明了该方法应用于追尾事故实时预测领域的可行性和有效性.

The existing models for real-time crash prediction are difficult to be applied in the freeway managementsystem that high-resolution traffic data cannot be collected. In this study, a real-time prediction model for reai^end crashis proposed based on the traffic data collected using a single detector. Based on the traffic data collected by ultrasonic detectorson Qiyang Freeway in Yangzhou〉 Jiangsu Province, China, the methods of matched case-control and binary logisticregression are used to develop a real-time prediction model for reai^end crash for a two-lane freeway. Three spatio-temporalmatrixes？ including a flow matrix〉 a speed matrix and an average space headway matrix？ are extracted from thetraffic data 5 - 20 minutes before crashes. Eigenvalues of matrixes are introduced to simplify the modeling process and avoida strong correlation among the parameters. Results show that overall accuracy of this proposed model is 85.7% , andaccuracy of prediction for crash rate is 33.3%？ with a corresponding false alarm rate less than 2 % . Thus the performanceand effectiveness of this proposed model is verified.