基于数据驱动的双护盾TBM施工参数优化OA

In order to solve the internal contradiction between tunnel deformation control and tunneling efficiency improvement when the double shield tunnel boring machine operate under complex geological conditions,this study proposes a data-driven optimization model to optimize TBM tunneling parameters.The model integrates CatBoost,XGBoost and sequential least squares quadratic programming(SLSQP)algorithm.CatBoost servers as the core algorithm to accurately predict tunnel deformation.XGBoost captures the nonlinear mapping relationship between TBM parameters,and the SLSQP algorithm optimizes tunneling parameters under constraints.The proposed mode was developed and validated using field data of a mountain rail transit project in Sichuan,China.The results show that the R2 of the CatBoost deformation prediction model is 0.923,the MSE is 0.023,and the prediction result is better.After optimization,the average propulsion speed is increased by 17.6%compared with that before optimization,the predicted deformation value is basically maintained near the original level,and the change rate is controlled below 3.45%.The model significantly improves the propulsion efficiency under the premise that the tunnel deformation does not exceed the safety threshold.The research conclusions provide reference for TBM construction decision-making.