Journal of Systems Engineering and Electronics ›› 2009, Vol. 31 ›› Issue (10): 2394-2398.

• 系统工程 • 上一篇    下一篇

初始值优化的离散灰色预测模型

姚天祥1, 刘思峰2, 党耀国2   

  1. 1. 南京信息工程大学经济管理学院, 江苏, 南京, 210044;
    2. 南京航空航天大学经济与管理学院, 江苏, 南京, 210016
  • 收稿日期:2008-04-25 修回日期:2009-06-19 出版日期:2009-10-20 发布日期:2010-01-03
  • 作者简介:姚天祥(1971- ),男,助理研究员,博士,主要研究方向为灰色系统理论.E-mail:ytxnj@163.com

Discrete grey prediction model based on optimized initial value

YAO Tian-xiang1, LIU Si-feng2, DANG Yao-guo2   

  1. 1. Coll. of Economics and Management, Nanjing Univ. of Information Science and Technology, Nanjing 210044, China;
    2. Coll. of Economics and Management, Nanjing Univ. of Aeronautics and Astronautics, Nanjing 210016, China
  • Received:2008-04-25 Revised:2009-06-19 Online:2009-10-20 Published:2010-01-03

摘要: 针对经典GM(1,1)模型的不足,研究了离散GM(1,1)模型选取不同初始迭代点的模拟数据增长率特点.应用最优化技术求解初始迭代点,证明了改进的离散GM(1,1)模型能够完全模拟指数序列.提出了两类分段修正离散GM(1,1)模型,对建模机理进行了证明,并对改进模型进行了推广.结果表明,优化初始迭代点的分段修正离散GM(1,1)模型能够完全拟合分段等比序列.

Abstract: To solve the insufficiency of traditional GM(1,1) model,this paper studies the growth rate of the simulation values under different initial values of discrete GM(1,1) model.Optimization techniques is applied to solve the initial value,which proves that the modified discrete GM(1,1) model can perfectly simulate the exponential sequence.Two kinds of segmental corrected discrete GM(1,1) models are provided to prove the modeling mechanism and expand the conclusions.The results indicates the segmental corrected discrete GM(1,1) model with optimized initial values can perfectly simulate segmental geometric sequences.

中图分类号: