Traditional manual inspection methods for tunnel lining leakage are subjective and inefficient, while existing models lack sufficient recognition accuracy in complex scenarios. An intelligent leakage identification model adaptable to complex backgrounds is therefore needed. To address these issues, a Vision Transformer (ViT) was integrated into the UNet architecture, forming an SE-TransUNet model by incorporating SE-Block modules at skip connections between the encoder-decoder and the ViT output. Using a hybrid leakage dataset partitioned by k-fold cross-validation, the roles of SE-Block and ViT modules were examined through ablation experiments, and the model’s attention mechanism for leakage features was analyzed via Score-CAM heatmaps. Results indicate: (1) SE-TransUNet achieved mean values of 0.8318 (IoU), 0.8304 (Dice), 0.9394 (Recall), 0.8480 (Precision), 0.9733 (AUC), 0.8562 (MCC), 0.9218 (F1-score), and 6.53 (FPS) on the hybrid dataset, demonstrating robust generalization in scenarios with dent shadows, stain interference, and faint leakage traces. (2) Ablation experiments confirmed both modules’ necessity: The baseline model’s IoU exceeded the variant without the SE module by 4.50% and the variant without both the SE and ViT modules by 7.04%. (3) Score-CAM heatmaps showed the SE module broadened the model’s attention coverage of leakage areas, enhanced feature continuity, and improved anti-interference capability in complex environments. This research may provide a reference for related fields.

Traditional methods for predicting surrounding rock grades ahead of tunnel faces encounter challenges: image-based approaches are susceptible to environmental interference, while parameter-based classification may disrupt construction. This study proposes an intelligent rock grade identification method by integrating longitudinal displacement profile (LDP) evolution patterns with deep learning. First, the numerical model was validated against V-D theoretical curves, and LDP evolution laws were systematically analyzed for three rock types (GSI = 15, 30, 50) under nine geological combinations. The results indicate that (1) homogeneous strata exhibit deformation peaks followed by declines; (2) GSI = 15 strata show significantly larger deformations; and (3) stratified schemes display pre-interface deformation peaks and post-interface deformation controlled by subsequent lithology. A novel hybrid neural network was developed to classify strata using LDP curves as input. The model achieved 93.25% training accuracy and 91.20% validation accuracy. Ablation experiments demonstrated their superiority over the other four models with partial module deletions, achieving improvements in test accuracy of 3.24%, 3.08%, 4.16%, and 6.48%, respectively, compared to those models. This lightweight solution effectively overcomes the limitations of manual expertise dependency in conventional models and environmental sensitivity in visual methods. By synergizing LDP evolution analysis with deep learning, this framework provides a reliable approach for real-time rock grade prediction during tunnel advancement.

Manual inspection methods traditionally used for tunnel lining leakage suffer from high subjectivity and low efficiency. At the same time, existing detection models do not perform well in terms of accuracy when faced with complex scenarios; this makes it essential to develop an intelligent leakage identification model that can adjust to varying background conditions. This study integrates a Vision Transformer (ViT) into UNet and constructs CBAM-TransUNet by embedding CBAMs into skip connections between the encoder-decoder structure and ViT outputs. Ablation experiments validate the efficacy of the CBAM and the ViT, while Score-CAM heatmaps analyze the model’s attention mechanism toward leakage features. The research results are as follows: (1) CBAM-TransUNet achieves average performance across metrics: 0.8143 (IoU), 0.8433 (Dice), 0.9518 (recall), 0.8482 (precision), 0.9837 (accuracy),0.9746 (AUC), 0.8568 (MCC), and 0.8970 (F1-score). These results indicate that the model performs excellently, even with dent shadows, stain interference, or faint traces. (2) Ablation experiments validate the pivotal roles of the CBAM and the ViT module: the IoU of the baseline model is 6.10% higher than that of the variant without the CBAM and 7.79% higher than that of the variant with both modules removed. (3) Through Score-CAM heatmap analysis, it is observed that the CBAM broadens the model’s attention coverage over leakage regions, strengthens feature continuity, and consequently enhances the model’s anti-interference performance in complex environments. This research could provide valuable reference insights for related fields.

Artificial Ground Freezing (AGF) is a promising method for controlling seepage in permeable strata. However, AGF faces challenges, including difficulties in achieving a frozen barrier in high-flow conditions and concerns about cost-effectiveness. This study optimizes freezing pipe placement in AGF using a simulated annealing algorithm and a coupled hydrothermal finite element model, focusing on AGF system responses under varying seepage velocities. The optimized layout significantly reduces freeze-ring formation time (by 2.5 days) and the overall freezing duration (by 12.5 days). Moreover, it substantially decreases the required frozen soil volume, facilitating drilling and excavation. Across different seepage velocities, the difference in freeze-ring formation time between the optimized and uniform layouts gradually increases with higher seepage velocity, reaching a maximum difference of 5.9 days. Finally, the relationship between freezing time and seepage velocity was quantitatively described using exponential functions. This study underscores the critical role of optimizing freezing pipe placement in AGF, providing a foundation for efficient and cost-effective geotechnical engineering practices.

Drill-and-blast tunnel construction continuously releases high-intensity dust during drilling, blasting, and shotcreting, while conventional forced ventilation is often insufficient to control dust migration and worker exposure. This study develops three-dimensional Euler–Lagrange gas–solid two-phase models for these three typical processes to clarify the spatiotemporal dispersion of polydisperse dust and to explore effective control strategies. The simulations show that all processes generate a persistent high-concentration dust belt near the tunnel face, and a low-velocity recirculation zone at the crown acts as a structural hotspot of dust accumulation that is difficult to purge by longitudinal ventilation. Particle size strongly affects dispersion behaviour: coarse particles rapidly settle near the source under gravity, whereas fine and medium-sized particles remain suspended for long periods and can be transported over long distances, particularly after blasting. Based on these findings, a rail-mounted purification system with a dynamically adjustable position along the tunnel is proposed, and its preferred deployment zones are determined to work synergistically with the main airflow. The system is designed to perform near-source and crown-targeted removal, providing an engineering-oriented “dynamic local purification plus overall ventilation dilution” pathway for improving air quality in drill-and-blast tunnel construction.

The newly constructed Luofengshan Tunnel obliquely underpasses the operating Hanyicun railway tunnel, requiring an integrated assessment of deformation response and service safety. This study combined field monitoring, ultrasonic shear-wave reflection imaging, and three-dimensional numerical simulation to evaluate track-bed settlement, lining deformation, floor integrity, lining stress, and structural safety. The complete third-party monitoring record showed that vertical deformation dominated the tunnel response. The final maximum cumulative values were −17.44 mm for manual lining settlement, −14.91 mm for automated lining settlement, and −11.30 mm for track-bed settlement; the corresponding maximum absolute values of horizontal displacement and convergence were 1.82 mm and 1.40 mm, respectively. Same-period comparisons showed that deformation increments decreased after breakthrough, and post-lining flood-season monitoring showed monthly rates below 1 mm/month. Ultrasonic imaging detected no evident voids or collapse within 2.0–2.2 m below the floor. Numerical simulation showed that incorporating measured initial deformation increased the maximum compressive stress from 4.95 MPa to 6.26 MPa, whereas subsequent underpass excavation and train loading increased it slightly to 6.28 MPa and 6.33 MPa, respectively. The final minimum safety factor was 3.18, indicating that the underpass impact remained controllable.