优化的灰色非等距GM(1,1)预测模型在沉降监测中的应用

Application of optimized non- equidistance GM(1,1)prediction model in subsidence monitoring

初始值的选取和背景值的构造是影响灰色非等距GM(1,1)模型预测精度的两个重要因素。通过最小二乘原理选取非等距GM(1,1)模型的最优初值,利用指数函数法构造新的背景值,构建了优化的灰色非等距GM(1,1)预测模型。最后,结合秀山湖二期工程的沉降实测数据,运用新陈代谢的计算模式进行预测验证,并与传统的非等距GM(1,1)预测模型进行比较。结果表明:基于新陈代谢式优化的非等距GM(1,1)预测模型的拟合精度和预测精度优于传统的非等距GM(1,1)预测模型,新的预测模型的适用性更强。

The original values,conformation of background values perform important double factors to the precision of the gray Non-equidistance GM（ 1,1） model. In this paper,we selected the optimal initial values of the Non-equidistance GM（ 1,1） model by the least square principle,created new background values by exponential function method,producing the optimized gray Non-equidistance GM（ 1,1） prediction model. Combined with data of the subsidence monitoring of the second phase of Xiu Shan Lake project,the metabolism computing model is used to prediction and we effectively compared the traditional Non-equidistance GM（ 1,1） model and the optimized Non-equidistance GM（ 1,1） model. The results show that the optimized Non-equidistance GM（ 1,1） prediction model based on the Metabolism prediction model of the accuracy is better than the traditional Non-equidistance GM（ 1. 1） prediction model,new prediction model performed better applicability,which has practical reference value.