Machine learning, Multi-objective feature selection, Explainability, Energy consumption, Shield tunneling, Engineering geology. Rock mechanics. Soil mechanics. Underground construction, TA703-712

Recently, AI-based models have been applied to accurately estimate tunnel boring machine (TBM) energy consumption. Although data-driven models exhibit strong predictive capabilities, their outputs derived from “black box” processes are challenging to interpret and generalize. Consequently, this study develops an XGB_MOFS model that cooperates extreme gradient boosting (XGBoost) and multi-objective feature selection (MOFS) to improve the accuracy and explainability of energy consumption prediction. The XGB_MOFS model includes: (1) a causal inference framework to identify the causal relationships among influential factors, and (2) a MOFS approach to balance predictive performance and explainability. Two case studies are carried out to verify the proposed method. Results show that XGB_MOFS achieves a high degree of accuracy and robustness in energy consumption prediction. The XGB_MOFS model, balancing accuracy with explainability, serves as an effective and feasible tool for regulating TBM energy consumption.