论文部分内容阅读
铁路行包运量预测是以运输需求和内部供给为导向,综合考虑各种影响因素,对行包运量现状和发展的正确把握。探讨利用人工神经网络结合主成分分析的方法,建立铁路行包运量预测模型,解释并预测行包专列开行后铁路行包运量的增长趋势。实例分析的仿真结果表明,采用主成分分析法的广义回归神经网络模型结构简洁、预测精度高、收敛速度快,对相关铁路部门和企业的决策具有参考意义。
The forecast of railway package transportation is based on the transportation demand and internal supply, comprehensively considering various influencing factors and correctly grasping the status quo and development of the package transportation. This paper explores the use of artificial neural network combined with principal component analysis to establish the forecast model of railway package traffic volume and explain and predict the growth trend of the total amount of package traffic. The simulation results of the example analysis show that the generalized regression neural network model based on principal component analysis has the advantages of concise structure, high prediction accuracy and fast convergence rate, which is of reference value to the decision-making of relevant railway departments and enterprises.