灰色Verhulst-时间序列组合模型在沉降监测中的应用

Application of Combination Model Based on Grey Verhulst-time Series in Settlement Monitoring

针对传统单一的灰色模型、时间序列模型在进行沉降监测数据模型存在精度较低的问题,本文提出了一种灰色Verhulst模型和时间序列模型的组合优化模型。首先,对灰色Verhulst模型、时间序列模型的基本理论进行阐述;其次,建立了灰色Verhulst-时间序列模型,即以灰色Verhulst模型得到的样本数据拟合值作为时间序列模型进行预测的样本值;最后,通过以某建筑物沉降监测点为例进行计算并进行灰色Verhulst模型、时间序列模型以及灰色Verhulst-时间序列模型的预测结果对比。实验结果表明,灰色Verhulst-时间序列组合优化模型的预测精度最高,均方差为0.3275 mm,验证了该组合模型更贴合建筑物沉降的变形趋势。

Aiming at the low accuracy of the traditional single grey model and time series model in the settlement monitoring data model,this paper adopts the combined optimization model established by the grey Verhulst model and the time series model.Firstly,the basic theory of grey Verhulst model and time series model is expounded;secondly,the grey Verhulst-time series model is established,namely the fitting value of the sample data obtained by the grey Verhulst model is used as the sample value for the prediction of the time series model;finally,taking a building settlement monitoring point as an example to calculate and compare the prediction results of grey Verhulst model,time series model and grey Verhulst-time series model.The experimental results show that the grey Verhulst-time series combined optimization model has the highest prediction accuracy,with a mean square error of 0.3275 mm.It is verified that the grey Verhulst-time series combined optimization model is more suitable for the deformation trend of the building settlement.