TBM penetration rate prediction ensemble model based on full-scale linear cutting test

Accurate and effective prediction of TBM penetration rate (PR) is significant for ensuring TBM tunneling safety, improving tunneling efficiency and optimizing construction cost. Establishing a prediction model is usually an effective method to solve this critical problem. The type of TBM penetration rate prediction models can be divided into two categories: theoretical models and empirical models. Each model has its advantages, but there are also shortcomings. To make the advantages of the two models complement each other and further improve the accuracy and application scope of the prediction model, this paper proposes a prediction ensemble model of PR based on a full-scale linear cutting test and machine learning algorithm. A semi-theoretical TBM penetration rate prediction model is established through the full-scale linear cutting test and the rock-breaking analysis of granite and sandstone with different strengths. Based on the XGBoost intelligent algorithm, an empirical model of the penetration rate prediction is also established. On this basis, the Bagging algorithm combines these two models to form an ensemble prediction model of TBM penetration rate. We collected rock mass and operational parameters in the Hangzhou Second Water Source Water Transfer Channel Project to verify the semi-theoretical, empirical, and ensemble models, respectively. The results show that the three models' prediction errors are all less than 15%, and the ensemble model has a smaller error of 10.2%. This result confirms that the ensemble model can effectively improve prediction accuracy and has good engineering applicability.