您目前所在的位置:首页 - 期刊简介 - 详细页面

铁道科学与工程学报

JOURNAL OF RAILWAY SCIENCE AND ENGINEERING

第13卷    第9期    总第78期    2016年9月

[PDF全文下载]    [Flash在线阅读]

    

文章编号:1672-7029(2016)09-1859-05
基于幂函数x-a变换的GM(1,1)模型在货运量预测中的应用研究
宋建强,鲍学英,王起才,董朝阳2

(1.兰州交通大学 土木工程学院,甘肃 兰州 730070;
2.兰州中川铁路有限公司 技术装备部,甘肃 兰州 730000
)

摘 要: 针对传统GM(1,1)模型对原始数列的光滑度要求较高且预测结果误差较大的问题,通过对原始货运量数据用幂函数x-a进行处理,将处理后的数据带入GM(1,1)模型进行预测,提出基于幂函数x-a变换的GM(1,1)货运量预测模型。最后,通过将该模型应用到实际案例中,验证基于幂函数x-a变换的GM(1,1)货运量预测模型较传统的GM(1,1)模型在预测精度方面有了较大幅度的提高,预测的相对误差降低了8.7%。研究结果表明,基于幂函数x-a变换的GM(1,1)模型可以更有效的对货运量进行预测。

 

关键字: 灰色模型;幂函数变换;货运量;预测

GM (1, 1) model based on power function x-a transformation and its application in freight volume forecasting
SONG Jianqiang, BAO Xueying,WANG Qicai,DONG Zhaoyang2

1.School of Civil Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China;
2. Technical Equipment Depaltment, Lanzhou Zhongchuan Railway Co, Ltd, Lanzhou 730000, China

Abstract:In order to minis the excessive error and improve the smoothness of the sequence from traditional GM(1,1) mode in freight volume forecasting , this paper presents GM (1,1) freight volume forecasting model based on power function x-a transformation by using the power function x-a transformation to deal with the original freight volume data and bringing the processed data into the GM (1,1) model. Finally, by applying the model to the actual case, the model in forecasting accuracy has been significantly improved than traditional GM (1, N) model and the relative error of the prediction is reduced by 8.7%. It indicates that the GM (1,1) model based on power function x-a transformation can be more effective to forecast the freight volume.

 

Key words: grey model; power function transformation; freight volume; forecast

ISSN 1672-7029
CN 43-1423/U

主管:中华人民共和国教育部 主办:中南大学 中国铁道学会 承办:中南大学
湘ICP备09001153号 版权所有:《铁道科学与工程学报》编辑部
------------------------------------------------------------------------------------------
地 址:湖南省长沙市韶山南路22号 邮编:410075
电 话:0731-82655133,82656174   传真:0731-82655133   电子邮箱:jrse@mail.csu.edu.cn