【摘要】 为有效进行交通货运量预测,通过对货运量影响因素的分析,建立了关于货运量影响因素的层次分析模型,根据该模型构建了基于RBF神经网络的货运量预测方法。用我国1985~2004年的货运量统计数据对该神经网络进行训练和检验,并对2005~2006两年间的货运量进行预测。预测时设定了2005~2006年2 a间货运量各影响因素值,再运用RBF神经网络预测这两年的货运量。结果表明,2005年的预测值与国家统计局最近公布的实际数值有很好的一致性,表明这一方法的可行性。更多还原

【Abstract】 To forecast the freight volume more effectively,the authors analyzed the factors influencing freight volume and established an AHP model.Based on this model,a radial basis function neural network model for freight volume forecasting was presented.The historical statistical data from 1985 to 2004 were used to train and check the RBF ANN.Combination forecast method was used to forecast the factors influencing freight volume’s data from 2005 to 2006.RBF ANN was used to forecast the fright volume.The forecasting result is consistent with the statistical data of National Bureau of Statistics of China.更多还原