摘要
客运量预测是进行公路网规划的必要环节和计算公路经济效益的基础.为了提高公路客运量的预测精度,在现有客运量预测模型基础上,采用IOWGA算子将三次指数平滑、GM(1,1)预测和BP神经网络结合起来,建立组合预测模型,并以全国公路客运量为例,验证预测结果的精度.分析计算结果,将该模型所得结果与其他常用方法相比,与实际客运量之间相差较小,预测精度较好,可以作为预测公路客运量的有效方法.
Passenger traffic volume forecast is a necessary part of road network planning and basis of calculating highway cost-effective. In order to improve prediction accuracy of highway passenger transportation volume, the paper uses IOWGA operator to combine three exponential smoothing model, GM (1,1) forecast model and BP neural network to establish a combination forecasting model on the basis of existing passenger volume forecasting models. Then the paper takes historical highway passenger volume of China for example to verify the accuracy of the predictions. According to the compared calculation, it can be obtained that the combination model gets the smaller error and better prediction accuracy, so that the model can be used as an effective method of forecasting highway passenger volume.
出处
《武汉理工大学学报(交通科学与工程版)》
2013年第6期1153-1157,共5页
Journal of Wuhan University of Technology(Transportation Science & Engineering)
关键词
公路客运量
IWOGA算子
组合预测
highway passenger transportation volume
IWOGA operator
three exponential smoothingmodel
GM (1,1)
BP neural network
combination forecasting