Estimation of the TBM advance rate under hard rock conditions using XGBoost and Bayesian optimization

TLDR

The advance rate of a tunnel boring machine under hard rock conditions is a key parameter for successful tunneling engineering. The study aims to improve TBM advance‑rate prediction accuracy by combining XGBoost with Bayesian optimization. Using 1,286 data sets from the Peng Selangor Raw Water Transfer tunnel, the authors built XGBoost models with Bayesian‑optimized hyper‑parameters that incorporated rock mass, intact rock, and machine specifications, and evaluated them via five‑fold cross‑validation with RMSE and R² metrics. The BO‑XGBoost model outperformed the default XGBoost, achieving RMSE 0.0967 and R² 0.9806, and variable‑importance analysis showed machine parameters had the greatest influence.

Abstract

The advance rate (AR) of a tunnel boring machine (TBM) under hard rock conditions is a key parameter in the successful implementation of tunneling engineering. In this study, we improved the accuracy of prediction models by employing a hybrid model of extreme gradient boosting (XGBoost) with Bayesian optimization (BO) to model the TBM AR. To develop the proposed models, 1286 sets of data were collected from the Peng Selangor Raw Water Transfer tunnel project in Malaysia. The database consists of rock mass and intact rock features, including rock mass rating, rock quality designation, weathered zone, uniaxial compressive strength, and Brazilian tensile strength. Machine specifications, including revolution per minute and thrust force, were considered to predict the TBM AR. The accuracies of the predictive models were examined using the root mean squares error (RMSE) and the coefficient of determination (R2) between the observed and predicted yield by employing a five-fold cross-validation procedure. Results showed that the BO algorithm can capture better hyper-parameters for the XGBoost prediction model than can the default XGBoost model. The robustness and generalization of the BO-XGBoost model yielded prominent results with RMSE and R2 values of 0.0967 and 0.9806 (for the testing phase), respectively. The results demonstrated the merits of the proposed BO-XGBoost model. In addition, variable importance through mutual information tests was applied to interpret the XGBoost model and demonstrated that machine parameters have the greatest impact as compared to rock mass and material properties.