基于改进等维信息灰色模型的高铁隧道沉降预测研究

Research on Settlement Prediction of High Speed Railway Tunnel Based on Improved Gray Model of Equal Dimension Information

等维信息灰色模型是对传统灰色模型的改进,但其模型背景值仍设定为0.5,为了使模型的预测性能得到提高,本文提出了基于粒子群PSO算法的等维信息灰色模型来优化模型的背景值,以消除灰色模型本身固有的偏差。根据已有的高铁隧道沉降监测数据,对其进行小波去噪处理,再分别建立传统GM(1,1)模型、等维信息GM(1,1)模型和PSO-等维信息GM(1,1)模型进行拟合预测,并与原始数据进行对比。预测结果表明,改进后的等维信息GM(1,1)模型的预测精度更高。

the gray model of equal dimension information is the improvement of traditional grey model,but the model background value is still set to 0.5,in order to improve the prediction performance of the model,the grey model of equal dimension information based on PSO algorithm is proposed to optimize the background value of the model in order to eliminate the inherent deviation of the grey model.According to the monitoring data of high-speed railway tunnel settlement,the settlement data of wavelet denoising,then establish the traditional GM（ 1,1） model,the dimension information GM（ 1,1） model and PSO-（ 1,1） GM dimensional information model forecasting,and compared with the original data. The results show that the improved GM（ 1,1） model has higher prediction accuracy.