基于数据融合技术的路段出行时间预测方法 - 交通运输工程学报.pdf

第8 卷　第6 期 交 通 运 输 工 程 学 报 Vol.8　No.6 2008 年12 月 Journal of T raffic and Transportation Engineering Dec.2008 :1671-1637(2008)06-0088-05 刘红红, 杨兆升 ( , 　130025) 　:为了精确预测路段出行时间, 分 了国内外基于多数据源的路段出行时间预测方法的优缺 点, 应用自适应卡尔曼滤波算法, 通过融合环形线圈检测器数据和浮动车数据, 建立了路段出行时间 估计模型, 在交通高峰期和事故情况下, 比较了采用基于环形线圈检测器、浮动车和自适应卡尔曼滤 波3 种出行时间预测方法预测路段出行时间的平均绝对百分比误差。比较结果表明:基于自适应卡 尔曼滤波算法融合了来自环形线圈检测器和浮动车的数据, 预测值更接近实测值, 预测精度高。 :智能交通系统;路段出行时间预测;自适应卡尔曼滤波;数据融合 :U4 1.14　　　:A Estimating methods of link travel timesbased on data fusion technology LIU Hong-hong, YANG Zhao-sheng (School of Transportation, Jilin University, Changchun 130025, Jilin, China) Abstract:In order to exactly predict link travel times, the advantages and disadvantages of existing prediction methods w ere analyzed, adaptive Kalman filter algorithm w as used, and link travel time estimation models w ere presented by combining traffic data from probe vehicles and loop detection.A daptive Kalman filter(AKF)algorithm-based link travel time estimation models were compared w ith loop detector data-based methods and probe vehicles-based methods under the circumstances of peak hours and traffic accident, the average absolute percentages of the computation error w ere analyzed.A nalysis result indicates that AKF algorithm is an effective method that may fuse the traffic data from different sources, its predictive values are closer to the measured values so its prediction accuracy is higher.1 tab, 7 figs, refs. Key words:intelligent transportation system ;link travel time estimation;adaptive Kalman filter; data fusion + Author resume:LIU Hong-hong (1 73-), female, associate professor, PhD, 86-431-850 4273, liuhonghong200307 @ .cn.