基于改进灰色-马尔可夫链方法的铁路货运量预测

Prediction of Railway Freight Volumes Based on Improved Gray-Markov Chain

科学的货运量预测对铁路发展战略的制定具有十分重要的意义.针对灰色模型的预测结果精确度受原始数据变化幅度的影响较大,且要求累加生成的数据列具有指数性质的缺点,采用带波动的多项式来替代GM(1,1)模型中的指数形曲线,并通过马尔可夫链对其预测结果进行修正,从而建立改进的灰色-马尔可夫链预测模型,同时利用该改进模型对我国铁路货运量进行预测,并与传统的GM(1,1)模型、改进的GM(1,1)模型和灰色-马尔可夫模型3种预测方法进行了比较,结果表明:提出的预测方法具有较高的精度,具有一定的可行性和有效性,预测结果可指导铁路建设与管理.

The freight volumes prediction is very important to decision-making of railway development strategies.In the paper,aiming at shortcoming of tradition gray prediction model,the fluctuation polynomial is utilized to displace the exponent curve in the model of GM（1,1）,and the prediction results are adjusted by Markov chain,then the prediction model based on improved Gray-Markov chain is established.The railway freight volumes are predicted by the model,and the traditional GM（1,1）,improved GM（1,1） and Gray-Markov chain are compared. The results show the prediction model put forward in paper is more accurate, and the method is feasible and effective. The prediction results can direct the construction and management of highway.