灰色-时序组合模型在地表变形预测中的应用

通过对某地铁监测点小波去噪后的数据建立灰色预测模型,分析了灰色预测的优缺点,针对灰色预测对波动性数据预测的不足,建立了灰色-时序组合模型。首先,利用灰色模型提取时间序列中的趋势项;然后,用时序模型对残差项进行建模分析,兼顾了数据的趋势性和波动性,弥补了灰色预测的不足,提高了预报精度。

Grey-TimeSeries Model in the Application of Ground Surface Deformation

Building a grey predication model based on wavelet denoising data of monitoring point in a underground station,this thesis analyzes the advantages and disadvantages of grey forecasting;Aiming at the shortcomings of the grey predication data to predict the volatility,grey-timing series model is established.At the first,grey model is utilized to extract trend term from time series,and then use time-series model is in use to stimulate modeling analysis of residual term,which takes both the trend and driving characters of data into account,and improves the disadvantages of grey predication so as to increase the predication precision.