摘要
为精确的预测铁路的货运量,采用了混合神经网络的方法进行建模。在分析某铁路以往货运量的基础上,确定了混合神经网络的特征参数,并根据实际情况确定了输入层和隐含层的神经元个数,从而得到了模型的结构,最终建立了一个用于预测铁路货运量的混合神经网络模型。
In order to achieve a more accurate prediction of railway freight volume, the paper establishes a model for it based on hybrid neural network technology. On the basis on the analysis of past freight volumes, it ascertains the characteristic parameters of the network, decides upon the number of neurons on the input layer and the hidden layer in accordance with the reality of practice, thus the structure of the model, and finally establishes a hybrid neural network model for the prediction of railway freight volume.
出处
《物流技术》
2010年第3期96-98,共3页
Logistics Technology
关键词
货运量
混合神经网络
预测方法
freight volume
hybrid neural network
prediction method
