基于乘积ARIMA模型的城市轨道交通进出站客流量预测

发布时间：2018-05-15 03:24

本文选题：交通运输规划与管理 + 城市轨道交通　；参考：《北京交通大学学报》2014年02期

【摘要】：基于城市轨道交通自动售检票(Automatic Fare Collection,AFC)系统采集的进出站客流的历史数据,构建乘积差分自回归移动平均(Auto_Regressive Integrated Moving Average,ARIMA)模型,实现对进出站客流量的精确预测.通过自相关和偏自相关函数进行数据的平稳性和周期性分析,消除趋势性和周期性特征影响;考虑到处理后数据的周期性和短期相关性之间的乘积关系,构建乘积ARIMA进出站客流预测模型,并以广州地铁各车站进出站客流量数据为例进行了模型的参数标定.模型预测值与实际值的对比分析显示该模型的平均绝对百分误差保持在5%以内,表明该模型具有很高的预测精度和良好的适用性.
[Abstract]:Based on the historical data of passenger flow in and out stations collected by the automatic Fare Collection system of urban rail transit, a product differential autoregressive Integrated Moving average (ARIMA) model is constructed to accurately predict the passenger flow in and out of the station. The influence of trend and periodicity is eliminated by using autocorrelation and partial autocorrelation function to analyze the stability and periodicity of data, considering the product relationship between periodicity and short-term correlation of processed data, A product ARIMA passenger flow prediction model is constructed, and the parameters of the model are calibrated by taking the passenger flow data of each station in and out of Guangzhou subway station as an example. The comparison between the model prediction value and the actual value shows that the average absolute percent error of the model is less than 5%, which indicates that the model has high prediction accuracy and good applicability.
【作者单位】：北京交通大学交通运输学院;广州市地下铁道总公司;
【基金】：国家科技支撑计划项目资助(2011BAG01B01)
【分类号】：U293.13;U293.5

【参考文献】