On Surface Settlement Prediction Technique in Shallow Buried High-speed Railway Tunnel Construction
In order to solve the problem that the basic data collection of shallow buried high-speed railway tunnel construction is less intensive and the prediction accuracy of surface settlement is low,the traditional BP neural network model is combined with the GM grey prediction theory of prediction function,and the GM-BPNN com-bined prediction model is constructed to optimize the traditional surface settlement prediction method in the con-struction of high-speed railway tunnel.According to the optimization plan,the random process of ground surface settlement is adopted to build a data model,so as to improve data collection efforts and obtain reliable basic infor-mation.By constructing the nonlinear mapping relationship between ground surface settlement and random varia-bles,the land surface settlement state is predicted according to the obtained data information,so that the neural network has the ability of nonlinear data approximation in the prediction of land surface settlement.Thus,the whole prediction is realized and the accuracy of measurement is guaranteed.The experimental results show that this method can improve the overall prediction accuracy,predict the surface settlement phenomenon in time,and ensure the construction safety.
万方数据
维普
