论文部分内容阅读
应用灰色系统理论计算了铁路货运量与货运量影响因素的关联度,并对其进行了排序。利用MAT-LAB软件,建立铁路货运量的RBF神经网络预测模型,对我国1992-2008年的铁路货运量进行仿真实验。结果表明基于灰色系统理论的RBF神经网络模型预测平均相对误差为0.44%,常规RBF神经网络模型的平均预测误差为1.47%,因此认为基于灰色系统理论的RBF神经网络的铁路货运量预测方法有效可行。
The gray system theory is used to calculate the degree of association between railway freight volume and freight volume influencing factors and to sort them. Using MAT-LAB software, the RBF neural network prediction model of railway freight volume was established, and the railway freight volume in China from 1992 to 2008 was simulated. The results show that the average relative error of RBF neural network model based on gray system theory is 0.44%, and the average prediction error of conventional RBF neural network model is 1.47%. Therefore, it is considered that the method of RBF neural network based on gray system theory is feasible and effective .