【摘要】 准确预测公交车辆到站时间对于改善公交服务水平、提升公交吸引力、缓解交通拥堵具有重要意义.公交车辆到站时间受到实际路面情况影响很大,粒子滤波算法对于这种非线性、非高斯的随机系统具有很好的适用性.因此本文探索性地应用粒子滤波算法建立公交车辆到站时间预测模型(BAT-PF),并以北京市公交300路内环线位置数据为基础,选取高峰和平峰时刻进行实例研究,并将预测结果与卡尔曼滤波算法所得预测结果进行对比分析.结果表明,本文建立的公交车辆到站时间粒子滤波预测模型具有更好的适用性和稳定性,而且预测精度高.更多还原

【Abstract】 Providing accurate bus arrival time(BAT) can help to improve the service quality of a transit system, enhance bus attractiveness and ease traffic jams. BAT is greatly influenced by the complex road conditions, particle filter algorithm can be well applied to this kind of nonlinear and non-Gaussian systems.Therefore, a BAT based on particle filter algorithm prediction model(BAT-PF) is proposed tentatively. Then,based on the location data, a case study of the inner line 300 of Beijing is conducted. Bus arrival time during the morning peak hours and off-peak hours are forecasted by both the BAT-PF and the Kalman filter(KF).The results show that the BAT-PF is more applicable and stable to predict bus arrival time and has a higher accuracy.更多还原