基于ET交易数据的高速公路行程速度提取模型.docVIP

基于ETC交易数据的高速公路行程速度 提取模型 北京工业大学北京市城市交通运行保障工程技术研 宄中心北京市城市规划设计研宄院 为了提高高速公路运行状态的监测水平，基于ETC交易数据预处理，根据计算 周期内路段ETC数据量的大小，搭建了不同样木量水平条件下行程速度的提取 模型。利用包含对象路段的多个0D对ETC交易数据提取路段的行程速度，提出 基于0D对速度折减系数和可信度权值的速度修正方法，解决丫小样本条件下速 度提取可信度较低的问题。以北京市高速公路路段数据进行了现场验证。结果表 明，模型的平均绝对误差为4. 5km/h左右，平均相对误差为6. 5%左右；高峰和非 高峰时期的误差均方差分别为2. 38km/h和3. 39km/h,说明高峰时期的速度提取 稳定性优于非高峰时期。仅利用ETC数据不能完整反映车辆的行驶状态，未来可 融合其他数据源，进一步提高高速公路运行状态提取的准确性和可靠度。 关键词： 交通工程;ETC数据;速度提取模型;数据挖掘;高速公路;信息提取; 翁剑成（1981-）,傅士，副教授.研究方向：智能交 通. :youthweng@bjut. edu.cn 收稿曰期:2017-08-29 A Model of Travel Speed Calculation for Freeway Road Segments with ETC Transaction Data WENG Jiancheng WANG Yuan YUAN Rongliang MA Siyong Beijing Engineering Research Center of Urban Transport Operation Guarantee, Beijing University of Technology; Beijing Municipal Institute of city Planning Design; Abstract： Aiming to enhance the level of monitoring of expressway status, aproccdurc of data preprocessing is presented，and structure of ETC transaction data within a calculation period is analyzed to establish a dual-level calculation model of travel speed under different levels of sample sizes. Tn order to improve credibility of velocity extraction under conditions of small samples, the ETC data of different cntcr-lcavc toll plazas pairs is used to extracting the travel speed of a road section. A velocity correction method is proposed bases on the speed reduction factor a and speed reliable weight 0 coming from OD investigation. The model is verified by a special designed field experiments. The results show that the mean absolute error is 4. 5 km/h, and the average relative error is about 6. 5%. The mean square errors are 2. 38 km/h and3. 39 km/h in peak and non-peak periods, respectively. It shows that stability of the model in peak periods is better than which in non-peak periods. However, the results cannot entirety reflect driving states. Tn future, other data can be applied to increase the accuracy and reliability of traffic running status on freeways. Keyword