基于振荡序列的GM(1,1)模型  

GM(1,1) model based on oscillation sequences

作　　者：钱吴永[1] 党耀国[1] 

机构地区：[1]南京航空航天大学经济与管理学院,南京210016

出　　处：《系统工程理论与实践》2009年第3期149-154,共6页Systems Engineering-Theory & Practice

基　　金：国家自然科学基金(70473037);江苏省软科学重点项目(BK2006025)

摘　　要：针对GM(1,1)模型对非负光滑单调序列的预测精度较高,而对振荡序列的预测效果不理想的情况.提出了先通过加速平移变换将振荡序列变为单调增加序列,然后再对加速平移变换后的序列进行加权均值生成变换,再以加权均值生成变换得到的序列建立GM(1,1)模型进行预测.通过具体算例的计算表明,这种方法能够提高GM(1,1)模型的预测精度,可应用于对振荡序列建立GM(1,1)模型,从而扩大了GM(1,1)模型的应用范围.Although the GM(1,1)model has a high forecast accuracy on the nonnegative smooth monotone sequence,it has not ideal forecast effect on oscillation sequence.So this paper proposed a conversion method.Firstly,it turns the oscillation sequence into monotone sequence by means of accelerated translation theory,then makes Weighting Mean Value Generating operation,finally it establishes GM(1,1)model on the basis of Weighting Mean Value Generating sequence.The example shows that this method can improve the forecast...

关 键 词：振荡序列 加速平移变换 加权均值生成 GM(1 1)模型 

分 类 号：N941.5[自然科学总论—系统科学]