城市公交枢纽换乘客流OD动态预测方法

Dynamic Prediction Method of Transfer OD Matrix for Urban Transit Hub

换乘枢纽衔接公交线路的换乘客流OD是APTS下实施公交多线路动态协调调度的基础数据。以公交线路上下车乘客数的自动获取为前提,建立换乘OD推算优化模型,并设计了BP神经网络求解算法,应用数值试验对神经网络中的核心参数进行了标定。算例表明:BP神经网络为动态更新公交枢纽换乘客流OD提供了一种经济、有效的方法。

A transfer OD matrix is the basic data for coordination dispatching among transit lines in a transit hub under Advance Public Transportation System(APTS).A BP artificial neural network(ANN) model is applied to track the weights of OD pairs within a transit hub through using the data of boarding and alighting transfer passengers at each transit line.The key issues associated with the estimation process are deeply studied,including the design of ANN,the learning and stopping rules,and the calibration of model parameters through computational experiment.The results of the example from a transit hub reveal that the proposed model provides an economic and effective method for dynamic prediction of transfer OD matrix for a transit hub.