采用BP神经网络建立了乌江银盘枢纽工程河段货运量的预测模型,并对货运量进行了实际预测,分析认为神经网络预测结果较戴尔斐法和GM(1,1)法更为合理。 BP neural network was used to establish the forecast model of river freight volume of Wujiang Yinpan Project, and the actual forecast of freight volume was carried out. The results showed that the prediction results of neural network were more reasonable than that of Delphi and GM (1,1).