In some projects, a lack of data causes problems for presenting an accurate prediction model for surface settlement caused by shield tunneling. Existing models often rely on large volumes of data and struggle to maintain accuracy and reliability in shield tunneling. In particular, the spatial dependency between adjacent rings is overlooked. To address these limitations, this study presents a small-sample prediction framework for settlement induced by shield tunneling, using an adjacent-ring graph convolutional network (GCN-SSPM). Gaussian smoothing, empirical mode decomposition (EMD), and principal component analysis (PCA) are integrated into the model, which incorporates spatial topological priors by constructing a ring-based adjacency graph to extract essential features. A dynamic ensemble strategy is further employed to enhance robustness across layered geological conditions. Monitoring data from the Wuhan Metro project is used to demonstrate that GCN-SSPM yields accurate and stable predictions, particularly in zones facing abrupt settlement shifts. Compared to LSTM+GRU+Attention and XGBoost, the proposed model reduces RMSE by over 90% (LSTM) and 75% (XGBoost), respectively, while achieving an R² of about 0.71. Notably, the ensemble assigns over 70% of predictive weight to GCN-SSPM in disturbance-sensitive zones, emphasizing its effectiveness in capturing spatially coupled and nonlinear settlement behavior. The prediction error remains within ±1.2 mm, indicating strong potential for practical applications in intelligent construction and early risk mitigation in complex geological conditions.

Abrasive waterjet technology is a promising sustainable and green technology for cutting underground structures. Abrasive waterjet usage in demolition promotes sustainable and green construction practices by reduction of noise, dust, secondary waste, and disturbances to the surrounding infrastructure. In this study, a numerical framework based on a coupled Smoothed Particle Hydrodynamics (SPH)–Finite Element Method (FEM) algorithm incorporating the Riedel–Hiermaier–Thoma (RHT) constitutive model is proposed to investigate the damage mechanism of concrete subjected to abrasive waterjet. Numerical simulation results show a stratified damage observation in the concrete, consisting of a crushing zone (plastic damage), crack formation zone (plastic and brittle damage), and crack propagation zone (brittle damage). Furthermore, concrete undergoes plastic failure when the shear stress on an element exceeds 5 MPa. Brittle failure due to tensile stress occurs only when both the maximum principal stress (σ₁) and the minimum principal stress (σ₃) are greater than zero at the same time. The damage degree ($\chi$) of the concrete is observed to increase with jet diameter, concentration of abrasive particles, and velocity of jet. A series of orthogonal tests are performed to analyze the influence of velocity of jet, concentration of abrasive particles, and jet diameter on the damage degree and impact depth (h). The parametric numerical studies indicates that jet diameter has the most significant influence on damage degree, followed by abrasive concentration and jet velocity, respectively, whereas the primary determinant of impact depth is the abrasive concentration followed by jet velocity and jet diameter. Based on the parametric analysis, two optimized abrasive waterjet configurations are proposed: one tailored for rock fragmentation in tunnel boring machine (TBM) operations; and another for cutting reinforced concrete piles in shield tunneling applications. These configurations aim to enhance the efficiency and sustainability of excavation and tunneling processes through improved material removal performance and reduced mechanical wear.

This study aimed to develop a monocular vision-based tennis serve analysis system and evaluate its effectiveness in beginner training. The system uses MediaPipe Pose to extract 33 body landmarks from monocular video, calculates joint angles using three-dimensional vector operations, identifies serve phases through threshold-based rules, constructs an approximate 3D pose representation using anthropometric constraints, and generates corrective feedback through a rule-based expert system. In a quasi-experimental study, 90 beginner tennis players (final n = 82) completed an 8-week intervention and were allocated to a high-frequency feedback group, a moderate-frequency feedback group, or a conventional training group. All groups showed significant improvements in Serve Quality Mastery (SQM) scores (p < 0.001). The high-frequency feedback group showed the greatest SQM improvement (SQM: +30.5 points), followed by the moderate-frequency feedback group (+24.2 points) and the conventional training group (+15.5 points). Between-group differences were significant F(2, 79) = 74.30, p < 0.001, η² = 0.65. These findings indicate a graded pattern across the feedback-frequency groups, with more frequent system-generated feedback being associated with greater improvements in training performance. The findings support the potential use of the monocular pose-based, rule-driven feedback system as a supplementary tool for beginner tennis serve instruction.