基于残差改正的动态非等时距灰色模型及应用

Dynamic Unequal Interval Grey Model Based on Residual Error Correction and Its Application

介绍了动态非等时距GM(1,1)模型的建模原理、建模过程以及精度评定方法,阐明了动态非等时距GM(1,1)模型中维度选择、残差改正的问题,结合高层建筑沉降监测实例进行分析,将动态非等时距残差GM(1,1)模型预测结果与实测值进行比较,得出动态非等时距残差GM(1,1)模型在建筑物沉降监测中具有很高预测精度的结论,证明了该方法的可行性与可靠性,适用于高层建筑沉降监测。

In this paper, the modeling principles, the modeling processes and the accuracy assessment methods for dynamic unequal interval GM（1,1）model are introduced. The problem of dimension selection and residual error correction in dynamic unequal interval CM （1,1）model is explained. Combining one subsidence monitoring example of high-buildings and comparing prediction of dynamic unequal interval residual GM （ 1,1 ） model and measured value, the result shows that dynamic unequal interval residual GM（1,1）model has high prediction accuracy. The feasibility and reliability of this method have been proved to be suitable for subsidence monitoring of high-buildings.