GM(1,1)幂模型的研究现状及展望  

Research Status and Prospect of GM(1,1)Power Model

作　　者：马永梅 葛国菊 Ma Yongmei;Ge Guoju(College of Management,China University of Science and Technology,Hefei 230038,China;College of Applied Mathematics,Chaohu University,Chaohu Anhui 238000,China)

机构地区：[1]中国科学技术大学管理学院,合肥230038 [2]巢湖学院数学与统计学院,安徽巢湖238000

出　　处：《统计与决策》2020年第17期42-45,共4页Statistics & Decision

基　　金：安徽省自然科学基金重点项目(KJ2016A505);安徽省高校优秀青年骨干人才国内访问研修项目(gxgnfx2018034);安徽省重点教学研究项目(2016jyxm0691)。

摘　　要：数据由于受外界环境影响多呈现非线性特征,因此GM(1,1)幂模型具有更加广阔的应用前景。文章整理归纳近年来有关GM(1,1)幂模型的论文,发现大部分学者在模型参数优化问题上研究较多,主要考虑改变初始条件、背景值选取、灰导数改进、参数求解等问题,以MLS法、PSO算法为主要研究方法。在未来的研究中,关于GM(1,1)幂模型的应用将会在更大范围展开,伴随新形势下产生的特殊数据,也将会产生更合适的GM(1,1)幂模型的衍生模型。Due to the influence of the external environment,the data often presents nonlinear characteristics,therefore,the GM(1,1)power model has a broader application prospect.This paper summarizes the papers on GM(1,1)power model in recent years,finding that most scholars have done much research on the optimization of model parameters,mainly considering changing initial conditions,selecting background value,improving grey derivative,and solving parameters,with MLS method and PSO algorithm as the main research methods.In the future research,the application of GM(1,1)power model will be expanded in a wider scope.With the special data generated under the new situation,more suitable derivative models of GM(1,1)power model will also be produced.

关 键 词：GM(1 1)幂模型 参数优化 预测精度 MLS法 PSO算法 

分 类 号：N941.5[自然科学总论—系统科学]