摘要
针对相互影响的多变量序列的预测问题,探讨了原始MGM(1,m)模型和灰色离散模型的建模机理,提出一类离散多变量MGM(1,m)的优化模型,由推导可得该模型是灰色离散模型的一般形式.该模型通过求解线性方程组直接对多变量进行模拟和预测,有效避免了白化方程和微分方程转化带来的误差.实例表明,该模型的预测精度较传统MGM(1,m)模型有显著提高,拓宽了多变量灰色预测模型的应用范围.
Based on the problem of prediction of the raw data series for the multi-variable with interac-tion,exploring the modeling mechanism of original MGM（1 ,m）model and discrete grey model.A type of optimization model of the discrete MGM（1,m）is constructed in this paper,it can be derived that this model is the general form of discrete grey models.The model can simulate and predict the data directly by getting the solution of linear equations.And it effectively avoids the conversion error of winterization equa-tions and differential equations.The simulation and prediction accuracy is proved to be higher than in the traditional MGM（1,m）model according to a practical example.The application range of multi-variable MGM（1 ,m）is widened.
出处
《内蒙古师范大学学报（自然科学汉文版）》
CAS
北大核心
2014年第2期133-136,141,共5页
Journal of Inner Mongolia Normal University(Natural Science Edition)
基金
国家自然科学基金面上项目(71271086)
河南省软科学研究计划项目(112400450187)
河南省教育厅重点软科学项目(13A790065)
