Search Results (588)

The double-shield TBM has been widely adopted in urban subway tunnel construction in China. TBM excavation inevitably induces ground vibrations, which may pose risks to adjacent structures and adversely affect human comfort. However, current vibration assessment methods rely heavily on field monitoring and lack a quantitative relationship with TBM excavation parameters. To address this gap, this study proposes a novel approach to predict vibrations based on thrust, torque, and monitoring distance. Based on field tests conducted in the double-shield TBM section of the Qingdao Metro, a test segment consisting of 1063 rings was selected for analysis. Excavation parameters were systematically adjusted, and both the parameter values and corresponding vibration accelerations were recorded. Using Spearman’s rank correlation coefficient, the relationship between the excavation parameters and the root mean square (RMS) value of the vertical vibration acceleration was examined. The results indicate that both thrust (r = 0.72, p < 0.01) and torque (r = 0.47, p < 0.01) are significantly correlated with the vertical vibration acceleration. Using the improved GA-BP algorithm, a prediction model for vibration acceleration was established based on tunnelling parameters and monitoring distance. The results indicate that the model relying on thrust and distance yields the best performance, achieving a mean squared error (MSE) of 0.92888. The single-point prediction error ranges from 0.02 to 1.63 mm/s². Compared with a model that uses distance alone, the proposed model reduces the single-point prediction error by 73.6%, representing a significant improvement in accuracy. The predictive model was further validated in the left tunnel, where the prediction error ranged from 0.03 to 1.07 mm/s², confirming its feasibility. This study provides a method for real-time prediction of TBM-induced construction vibrations and offers a basis for adjusting tunnelling parameters to mitigate vibrations during tunnel construction. Full article

The integration of wind energy into urban environments is constrained by low wind speeds, high turbulence, and the recurrent negative torque experienced by lift-driven vertical-axis wind turbines (VAWTs). This study specifically evaluates a straight-bladed H-Darrieus rotor equipped with a single upstream passive flat-plate deflector for the wind regime measured on the campus of the Universidad Nacional Mayor de San Marcos (Lima, Peru). A three-dimensional transient CFD model using the SST k–ω turbulence model was applied to compare the baseline rotor and the deflector-assisted configuration under identical operating conditions; DMST calculations were used only as a low-order cross-check for the bare rotor performance trend, not as a substitute for experimental validation. The deflector was selected after a geometric sensitivity assessment and positioned at 30° relative to the incoming flow, with a span equal to the rotor height and a length comparable to the rotor diameter. At TSR = 2.5, the maximum power coefficient increased from 0.4459 for the bare rotor to 0.6153 with the deflector, equivalent to an improvement of approximately 38%. Velocity and pressure fields show that the deflector accelerates the flow toward the advancing blade while shielding the returning blade, thereby reducing adverse torque and smoothing cyclic torque fluctuations. The results define the applicability of the proposed passive device for low-to-moderate urban wind environments with a dominant wind sector and provide a reproducible numerical basis for subsequent wind-tunnel and field validation. Full article

Water-soil gushing caused by tunnel leakage can induce severe ground disturbance and threaten the safety of shield tunnels, yet rapid prediction remains difficult because high-fidelity numerical simulations are computationally expensive. This study develops an interpretable machine-learning framework for predicting gushing-induced ground disturbance around shield tunnels based on a validated two-phase Material Point Method database. Six governing variables are considered, including the tunnel depth ratio, gushing location, soil friction angle, Young’s modulus, intrinsic permeability, and soil gushing mass. Three representative response variables were selected, namely the maximum ground settlement, flow-zone width, and flow-zone centroid angle. Five algorithms, including MLP, RF, XGBoost, SVR, and Ridge, were established and compared, with hyperparameters optimised using Optuna. The results show that nonlinear models consistently outperform the linear baseline, among which MLP, RF, and XGBoost achieve the best overall accuracy and robustness. Error-distribution analysis further indicates that MLP and RF yield the highest proportion of low-error predictions. SHAP interpretation shows that SGM is the dominant factor governing maximum settlement and flow-zone width, whereas gushing location primarily controls the flow-zone centroid angle. The proposed framework provides an efficient and physically interpretable surrogate for rapid hazard assessment of gushing-induced ground disturbance in shield tunnelling. Full article

Decision-making during shield tunneling remains challenging due to complex shield–ground interactions, and experience-driven adjustments to shield operating parameters often fail to balance tunneling efficiency and energy consumption. For this purpose, a rule-constrained multi-objective optimization framework for shield operating parameters is proposed and validated using field data from a slurry shield tunneling project in Changsha, China. Here, a comprehensive field dataset is established by integrating ground conditions, operating parameters, and energy consumption indicators. Association rule mining is employed to identify typical combination patterns of operating parameters under different ground conditions, which are included as feasibility constraints in the parameter optimization. The relationship between operating parameters, tunneling efficiency, and energy consumption is captured by a random forest model, which serves as a surrogate model for rapid evaluation of operating parameters. Therefore, the NSGA-II algorithm is employed to obtain Pareto-optimal parameter combinations under feasibility constraints. The results indicate that the proposed framework can provide adaptive optimization strategies under different ground conditions. The resulting Pareto solutions can be classified into three tunneling modes, including robust, balanced, and high-speed, facilitating practical decision-making for shield operators. Full article

High rock temperature (HRT) and its associated thermal hazards, alongside secondary mechanical risks such as swelling pressures induced in clay layers, pose severe threats to the construction safety of deep-buried tunnels. This study aims to quantitatively reveal the evolution laws of the surrounding rock temperature field under varying heat source conditions. A combined approach of physical model testing and numerical analysis was adopted. Utilizing an independently developed test system with a 1:13 geometric similarity ratio, the coupled rock-heat-ventilation environment was simulated. A transient conduction-convection 3D numerical model was established in COMSOL and verified against experimental data under benchmark conditions. The research confirms that under the influence of localized block heat sources, the temperature field in the far-field region follows a significant linear attenuation law rather than the traditional exponential distribution, with a prototype-equivalent gradient of approximately 0.69 °C/m. Furthermore, the study quantitatively identifies 8 m³ as the critical volume for heat source geometric saturation, beyond which the incremental temperature rise efficiency decreases by 25%. It is further revealed that the effective cooling depth of conventional ventilation is only approximately 0.35 m, indicating a significant “ventilation shielding effect” within the deep surrounding rock. Full article

In this paper, analytical and numerical analyses of the mechanical response of an ultra-large-diameter shield tunnel with a nonuniform convergence of axial symmetry are conducted. A nonuniform convergence of axial symmetry around the tunnel boundary is adopted. The bending moment and axial force of the tunnel liner with different diameters from 6 to 18 m are obtained and compared in detail. The theoretical analysis results show that at the same buried depth of the tunnel crown, both the maximum absolute bending moment and axial force of the shield tunnel liner grow as the diameter of the tunnel increases. Moreover, the distributions of the bending moments of the tunnel liner along the tunnel boundary present a “8” shape and are axially symmetric along the vertical axis, where the upper and lower parts are positive and the left and right sides are negative. The maximum absolute bending moment of the tunnel liner is at the axis of 280°. Furthermore, the axial force of the shield tunnel liner is always negative, and the maximum absolute axial forces of the tunnel liner are at the axis of 0° and 180°. Finally, it is worth pointing out that the maximum bending moment and axial force increase 26.99 times and 8.99 times, respectively, when the diameter increases only three times from 6 m to 18 m, which is of great guiding significance for the rational design of ultra-large-diameter shield tunnels. The results of the analytical solution are verified by a numerical analysis, which shows that the analytical solution has a higher computational efficiency than the numerical simulation while ensuring accuracy. Full article

Shield tunnel construction inevitably disturbs existing upper buildings. This paper takes the section from Zhongyi Road Station to Housihu Fourth Road Station of Wuhan Metro Line 12 as the engineering background, where twin shield tunnels pass beneath Zizhu Kindergarten. Based on field monitoring data, this paper systematically analyzes the development laws of surface settlement and building settlement. Numerical simulation is adopted and compared with measured data to verify the reliability of the model. With the validated numerical model, this paper investigates the influencing factors of building settlement. The results show that the maximum ground surface settlement during shield construction is approximately 6.84 mm, and the maximum building settlement is about 4.63 mm. The horizontal relative position between piles and tunnels changes the superposition mode of ground settlement troughs. Building settlement reaches the minimum when twin tunnels pass beneath symmetrically. Eccentric crossing aggravates building settlement to a certain extent. The maximum building settlement increases with the rise of tunnel buried depth. The research results can provide a reference for deformation control and construction optimization of similar twin shield tunnels crossing beneath buildings with piled-raft foundations. Full article

Tunnelling-induced safety risks from adjacent piles have become increasingly severe with the rapid development of urban underground space. Model tests have become essential for revealing the complex pile-tunnel interaction mechanism. This paper reviews the research progress of model tests on the influence of single-line tunnelling on adjacent piles, focusing on test soil materials, tunnel simulation methodologies, analysis of test results, and research prospects. However, current model test studies are constrained by several critical limitations, including insufficient similarity between soil materials and prototype conditions, and overly idealized simulation of tunnel excavation. This paper identifies a significant research gap: the inability of current volume-loss techniques to capture 3D dynamic factors (e.g., face pressure and grouting timing) and the lack of meso-scale observation at the pile-soil interface. This review provides a systematic synthesis of these methodological challenges and proposes future research prospects to provide a more scientific basis for engineering design and risk control. Full article

The penetration rate (PR) is a critical indicator affecting the safety and cost of shield tunnel construction. However, due to the complexity of geological conditions and the nonlinear nature of tunneling parameters, traditional prediction methods struggle to achieve high-accuracy predictions. To address this issue, six hybrid deep extreme learning machine models were developed for PR prediction. Normalized mutual information (NMI) was employed to select key features, and an isolation forest (IForest) algorithm was employed to remove outliers and construct a valid dataset. Subsequently, deep extreme learning machines optimized using six metaheuristic algorithms were applied to predict the penetration rate. Finally, the key factors influencing tunneling rate prediction were identified based on SHAP analysis. The experimental results demonstrate that among the six optimized algorithm models, along with the BP neural network, uniaxial compressive strength (UCS), rock quality designation (RQD), and cutterhead torque were identified as key factors influencing PR. For the first time, the CTCM-DELM model is applied to predict the advance rate of shield tunneling. Combined with SHAP analysis, it is quantitatively revealed that the contribution of geological parameters is greater than that of equipment parameters, which provides novel insight for engineering practice. Full article

To address the limited cross-domain generalization of single-algorithm models for shield attitude prediction, this study proposes a heterogeneous algorithm-fusion framework based on Stacking. The framework integrates multiple machine learning algorithms and uses the Spider Wasp Optimizer (SWO) for hyperparameter optimization, thereby overcoming the limitations of individual learners and reducing the need for laborious algorithm selection. Principal Component Analysis (PCA) is further used to reduce dimensionality and reconstruct high-dimensional features, which lowers computational complexity and improves prediction accuracy. The proposed PCA-SWO-Stacking algorithm was applied to shield attitude prediction using data from the Shanghai Beiheng Passageway project. The results show strong predictive performance, with all R² values exceeding 0.94 and all RMSE and MAE values remaining below 2. Comparative experiments with commonly used ensemble algorithms and ablation studies further confirm the effectiveness and robustness of the proposed method. Full article

The efficient treatment and resource utilization of shield tunnel spoil (STS) are important for sustainable underground construction in China. To improve the early mechanical performance and microstructural compactness of stabilized STS, this study investigated the solidification effect of a novel early-strength cementitious agent (ESCA) and compared it with ordinary Portland cement (P.O 42.5). Macroscopic mechanical tests, including unconfined compressive strength (UCS), stress–strain behavior, mass, and P-wave velocity measurements, were combined with scanning electron microscopy (SEM) and computed tomography (CT) analyses to reveal the mechanical response and microstructural mechanisms of stabilized STS. The results indicate that, compared with P.O 42.5, ESCA exhibits superior fluidity at lower water-to-solid (w/s) ratios, significantly shorter setting times, and higher compressive strength at all curing ages. The solidification efficiency of ESCA for STS is notably superior to that of P.O 42.5, with the peak strength, elastic modulus, mass, and P-wave velocity of ESCA-solidified specimens being higher than those of P.O 42.5-solidified specimens across the five dosages. Furthermore, ESCA material bonds more tightly with STS particles, resulting in lower porosity and a denser microstructure under the same stabilizer dosage. Overall, the combination of macroscopic mechanical properties and microstructural characterization demonstrates that ESCA material exhibits significant advantages in the efficient solidification and resource utilization of shield tunnel spoil. Full article

Based on the Zhengzhou–Xuchang Intercity Railway tunnel project passing beneath Terminal 1 of Xinzheng International Airport, this study employs a three-dimensional numerical analysis model to investigate the effects of tunnel depth and pile foundation structure on ground surface settlement and pile foundation response during twin-line shield tunnelling in typical cohesive soils under tunnel side-crossing and under-crossing conditions. The results indicate that during tunnel side-crossing, the ground surface settlement profiles evolved from V-shaped to W-shaped before and after twin-tunnel breakthrough. With increasing tunnel depth, the lateral displacement profiles of the left-row and right-row piles transformed from spindle-shaped to X-shaped. With increasing pile count, the maximum axial force per pile decreased from 320.1 kN in the single-pile configuration to 197.4 kN in the six-pile configuration, a reduction of 38.3%. During tunnel under-crossing, the lateral displacement profiles of both left-row and right-row piles exhibit X-shaped profiles at different tunnel depths, and the pile-top displacement varies slightly with a maximum of 1.1 mm. With increasing pile count, the maximum axial force per pile decreased from 202.2 kN to 132.1 kN, a reduction of 34.7%. The findings provide valuable reference for design and construction control of twin-line shield tunnels crossing existing airport pile foundations in cohesive soil. Full article

Accurate attitude deviation prediction is key to segment quality during shield tunnelling, yet existing data-driven approaches typically treat feature selection and predictive modelling as independent steps, limiting interpretability and accuracy. This study proposes TransFeatNet, a key-parameter identification framework integrating multi-source feature selection, Transformer-based temporal encoding, threshold adaptive optimisation and attention-guided feature analysis into a closed-loop process. On this basis, a TransFeatNet-guided multi-step prediction method is developed using the Temporal Convolutional Network (TCN), Gated Recurrent Unit (GRU) and Decomposition Linear (DLinear) as backbones under a unified input and data split. Validation on the Zheng–Yan section of Beijing Metro Line 22 shows that TransFeatNet compresses 31 candidate parameters to the top-10 key variables for both horizontal and vertical deviation tasks, with cumulative weights of 0.6544 and 0.6642, markedly higher than the 0.4704 and 0.4854 of a Transformer-only baseline. Compared with Transformer-guided inputs, TransFeatNet further reduces RMSE by 12.50–20.94% and raises R² by 0.045–0.057. The optimal TransFeatNet + TCN combination achieves R² of 0.9210 and 0.8930 on an independent section, indicating stable cross-section performance under the current engineering data conditions. The framework provides a compact, interpretable input representation and shows clear engineering potential for attitude early warning and assisted control. Full article

Shield tunneling in urban areas can generate ground vibrations that may threaten adjacent buildings, especially in hard rock strata. However, the effect of foundation type on the vibration response of multi-story buildings is not yet fully understood. This study investigates this issue through a combined approach of field monitoring and three-dimensional numerical simulation based on the Jinan Metro Line 4 project. Five-story frame buildings with pile, raft, and isolated footing foundations were analyzed, and the numerical model was validated against measured data to ensure reliability. The results show that vibration waves attenuate in an approximately symmetric elliptical pattern and are amplified by the presence of buildings. A significant vertical amplification effect is observed, with peak particle velocity at the top floor reaching up to 2.11 times that at the ground surface. Foundation type exerts a significant influence on vibration transmission. Raft foundations exhibit a more uniform vibration distribution, whereas isolated footings demonstrate a weaker attenuation capacity, with only 23.6% attenuation and a first-floor response approximately 3.3 times greater than that of pile foundations. Although the structural safety requirements are satisfied, the vibration levels at upper floors may still exceed the human comfort limit of 75 dB, with the pile-founded building reaching 85.38 dB. These findings improve the understanding of vibration transmission mechanisms under symmetric disturbance conditions and provide a scientific basis for foundation selection and vibration mitigation in urban tunneling projects. Full article

Unet, a deep learning architecture, has become one of the most widely used models for crack detection in the tunneling field. Although it performs well in overall crack image segmentation, it still has issues of limited feature expression capability and inaccurate segmentation. To address these problems, DTA-Unet was proposed based on dynamic convolution decomposition (DCD) and triple attention (TA). Firstly, the model used Unet as the baseline network and replaced traditional convolutions in the encoding-decoding process with DCD to enhance its feature extraction ability. Secondly, TA was combined with attention gate (AG) in the skip connections of the network, eliminating redundant information in spatial and channel dimensions to highlight the crack area. Finally, the proposed model was tested on crack datasets and compared with the conventional Unet model, image processing algorithms, and other deep neural network models in terms of detection performance on the datasets. The results show that it outperforms other advanced methods in crack detection performance. The proposed method is of significance to the maintenance of shield tunnel cracks. Full article