基于小波神经网络的货运量预测

选取我国1979—2011年国民生产总值、能源生产总值、进出口贸易额、社会消费品零售总额和固定资产投资总额5项指标作为货运总量的主要影响因素，以货运总量为输出，建立了基于Morlet小波函数的小波神经网络预测模型。该模型能够揭示货运量与相关变量之间的非线性映射关系，经实例分析得到了较满意的结果，并通过与实际货运量和BP神经网络预测结果的对比，证明了小波神经网络在货运量预测方面应用的可行性。

Freight Volume Forecast Based on Wavelet Neural Network

The main intention of this paper is to establish the freight volume forecast model based on Morlet wavelet function, which is used by wavelet neural network. The 5 main factors of the freight volume in the present study are GDP, total energy produc tion, total value of imports and exports, total retail sales of consumer goods and total investment in fixed assets during 1979---2011 in China. The model can reveal the nonlinearity mapping relationship among the main factors related to the freight volume. The ex-ample analysis shows that the result is satisfactory, and the prediction method is effective and feasible.