An earth pressure balance (EPB) TBM is used in soft ground conditions, and these conditions lead to the fluctuation and instability of machine parameters. Machine parameters influence cutter wear and tunnel excavation. For this reason, to evaluate and predict the cutter wear of an EPB TBM, a 1D CNN model was used to provide machine-parameter-based cutter wear prediction using an EPB TBM operational dataset. The machine parameters were split into 80% training and 20% test datasets. Compared to traditional machine learning applications and two deep neural network models, the proposed model provided reliable results with a reasonable computational time. The correlation coefficient was 89.6% $R^2$, the mean squared error (MSE) was 57.6, the mean absolute error (MAE) was 1.6, and the computational wall time was 3 min 22 s.

Tunnel Boring Machines (TBMs) are pivotal in underground projects like subways, highways, and water supply tunnels. Predicting and monitoring jack speed and torque is crucial for optimizing TBM excavation efficiency. Conventionally, skilled operators manually adjust numerous tunnelling parameters to regulate the machine's progress. In contrast, machine learning (ML) algorithms offer a promising avenue where computers learn from operator actions to establish parameter relationships autonomously. This study introduces an innovative approach to enhancing operator monitoring and TBM data comprehension. A robust correlation between TBM operator behaviour and TBM logged data is established by leveraging an Optuna-assisted ML methodology—the research light on the intricate dynamics influencing TBM advance rate parameters. Operational data is collected from micro slurry tunnel boring machine (MSTBM) umbrella support excavations. The proposed framework harnesses Optuna, an advanced hyperparameter optimization platform, to dynamically refine jack speed and torque settings. Through meticulous analysis of the interplay between TBM operator decisions and real-time logged data, the AI model discerns patterns, empowering informed decision-making. Using Optuna, a range of models, including random forest (RF), K-nearest neighbours (kNN), decision tree (DT), XGBoost, Support Vector Machine (SVM), and Artificial Neural Network (ANN) were automatically compared and tuned. The best model's (RF) performance is evaluated through a correlation coefficient (R²) of 96%, mean squared error (MSE) of 119.7, and mean absolute error (MAE) of 4.42 for jack speed decision making while 83% of R², MSE of 0.62, and MAE of 0.42 for the torque decision making. This intelligent model can assist the TBM operator in making decisions about TBM control.

In tunnel construction, efficiently predicting the energy usage of tunnel boring machines (TBMs) is critical for optimizing operations and reducing costs. This research proposes a novel method for predicting the specific energy of micro slurry tunnel boring machines (MSTBMs) using an explainable neural network (xNN) that leverages operator-monitored data. The xNN model provides transparency and interpretability by integrating the Shapley additive explanation (SHAP) technique, enabling tunneling engineers and operators to gain valuable insights into the prediction process. Extensive data from MSTBM umbrella pipe support excavation are the foundation for training, testing, and unseen data in the xNN model. The specific energy formula derived from the operational parameters of the MSTBM defines the dependent variable for the xNN model. The test dataset evaluates the model’s performance with an R² of 98.7%, an MSE of 2.40, and an MAE of 0.003, demonstrating its accuracy and reliability. Ten percent of the dataset was reserved as unseen data to assess the model’s generalization capabilities. Upon evaluation, the model achieved an R² value of 89%, an MAE of 0.01, and a root mean squared error (RMSE) of 0.01. The xNN empowers operators to optimize operational parameters and promote more efficient and sustainable tunneling practices by identifying influential factors affecting energy consumption through its interpretable nature. This research has significant implications for the future of underground construction, paving the way for improved resource management.

Data-driven rock mechanics has long been constrained by a chronic deficit: coordinated laboratory measurements of uniaxial compressive strength (UCS) and its physically related properties are not only limited in number but also unevenly distributed across rock types. To address this constraint, the present study proposes a diversity-tuned physics-informed generative adversarial network—termed PI-GAN—designed to produce synthetic UCS, porosity, and bulk-density data that preserve the fundamental mechanical relationships inherent to rock materials. The framework integrates adversarial learning with an intact-rock strength-envelope constraint, category-specific UCS–porosity–density correlation losses, moment and covariance matching, feature-envelope penalties, and a pairwise-distance diversity term. The model was calibrated on 944 complete records drawn from the P³ petrophysical database, grouped into dense crystalline, volcanic, pyroclastic, and sedimentary rock categories. The trained PI-GAN generated 944 synthetic samples, increasing the usable dataset to 1,888 records. The synthetic data preserved the dominant correlation structure, with the overall UCS–porosity correlation shifting from − 0.598 to − 0.675 and the UCS–density correlation changing from 0.566 to 0.650. Category-specific Fisher z-tests showed non-significant differences for 11 of 12 correlation pairs, with an average absolute correlation difference of 0.036. Distributional validation yielded a mean Kolmogorov–Smirnov statistic of 0.181, while diversity diagnostics produced a mean pairwise-distance ratio of 0.703 and a near-duplicate rate of 0.0%. Strength-envelope sensitivity checks returned zero violations across tolerance levels from 10% to 50% of category mean UCS. The results indicate that the proposed PI-GAN can provide physics-consistent augmentation data for machine-learning development in data-scarce geotechnical applications, while serving as a complement to, rather than a replacement for, site-specific laboratory testing.