非等间距GM(1,1)模型背景值的构造及其应用

Bckground value building of non equidistant GM(1,1) model and its application

基于背景值构造理论,尝试使用Lagrange插值多项式,对一次累加生成序列(1-AGO)进行拟合,进而利用该函数构造出一个更为精准的背景值,并将此方法应用于人工降雨中不同时间播撒碘化银时的降雹量的建模当中.应用结果表明,该方法所建模型的拟合精度高于传统非等间距GM(1,1)模型的精度.这种建模结果亦证明了本文所提出改进方法的有效性.

Based on the theory of background value building,this paper attempts to use the Lagrange interpolation polynomial to fit accumulated generating sequence（1-AGO）,and then use the function to construct a more accurate background value,and this method is applied to the modeling of hail fall by seeding AgI at different time.The results of application show that the fitting precision of the improved non equidistant model is higher than that the traditional model.The modeling results show the effectiveness of this method.