Search

Tunnel boring machines (TBMs) are essential for excavating metro tunnels, reducing disruptions to surrounding rock, and ensuring efficient progress. This study examines how machine learning (ML) models can predict key tunneling outcomes, focusing on making these predictions clearer. Specifically, the models aim to predict surface settlements (ground sinking) and the TBM's penetration rate (PR) during the Athens Metro Line 2 extension to Hellinikon. For surface settlements, four artificial neural networks (ANNs) were developed, achieving an accuracy of over 79%, on average. For the TBM's PR, both an XGBoost Regressor (XGBR) and ANNs performed consistently well, offering reliable predictions. This study emphasizes model transparency mostly. Using the SHapley Additive exPlanations (SHAP) library, it is possible to explain how models make decisions, highlighting key factors like geological conditions and TBM operating data. With SHAP's Tree Explainer and Deep Explainer techniques, the study reveals which parameters matter most, making ML models less of a "black box" and more practical for real-world metro tunnel projects. By showing how decisions are made, these tools give decision-makers confidence to rely on ML in complex tunneling operations. [ABSTRACT FROM AUTHOR]

Ore dilution is a fundamental problem for the production process in underground mining operations. Especially in open stoping methods of underground mining, the continuous estimation, monitoring and treatment of instability issues is considered necessary in order to maintain the consistency of the production process. This paper aims to combine empirical nomograms of stability estimation and numerical approaches and thus link the extensive experiences of the empirical design and the quantitative data derived by numerical analyses. To facilitate this, a large number of different geomechanical conditions were modeled and analyzed in the pursuit of obtaining valid and applicable relationships between the empirical stability graphs' approaches and the numerical simulation models. The parametric analysis was made to express the stability conditions and the dilution with specific design characteristics, using prevalent stability-graph approaches while the numerical models were tested using the RS2 software package. The obtained results include direct and easy-to-use mathematical expressions that can be applied during the initial design of the stoping process, especially for the case of sidewalls (hanging walls and foot walls). Furthermore, through the research, an initial proposal is made for a dilution-based stability graph that could be utilized for the early identification of dilution. [ABSTRACT FROM AUTHOR]