Search Results (48)

The aerodynamic behaviour of buildings equipped with porous outer envelopes is governed by the interaction between millimetre-scale geometric features and building-scale flow structures. Explicitly resolving these scales in numerical simulations is computationally prohibitive, making homogenised porous-medium formulations a practical alternative. Among them, the Darcy–Forchheimer (D–F) model is widely adopted; however, the reliability of building-scale predictions critically depends on how its resistance coefficients are identified and validated. This study proposes and assesses a consistent procedure for the determination and application of D–F coefficients for porous screens used in double-skin façade systems. Porous elements are first characterised at the element scale through an analytical derivation based on aerodynamic force coefficients, from fully resolved CFD simulations of representative periodic modules. The resulting D–F coefficients are cross-compared and validated against available wind tunnel data at local Reynolds numbers $R{e}_H>3000$. Secondly, the calibrated homogenised model is applied to a building-scale double-skin façade configuration. The porous layer is represented as a finite-thickness porous region governed by the identified D–F parameters and analysed through unsteady Reynolds-averaged Navier–Stokes simulations. The model’s capability to reproduce global aerodynamic loads, local pressure distributions, and wake characteristics is evaluated against experimental data. The results demonstrate that a properly calibrated D–F formulation provides an accurate and computationally efficient representation of porous façade systems, bridging element-scale characterisation and structural-scale aerodynamic performance. Full article

Accurate prediction of store trajectories at the point of release from an unmanned/manned aircraft is an essential requirement for safety and precision. Captive Trajectory System (CTS) is a well-known feature of wind-tunnel testing to simulate the dynamics of store separation. To accurately replicate real-world aerodynamic conditions based on measured forces and moments, it utilizes a six-degree-of-freedom (6-DOF) robotic arm controlled by a closed-loop control system that solves the store’s equations of motion. In this study, a wing–pylon–store configuration is used as a sample case, and published experimental trajectories are used as input. A 6-DOF robotic arm named ROBO-S is designed to follow these trajectories in a CTS setup. The kinematic analysis of ROBO-S is performed in this study. The Denavit–Hartenberg (DH) method is used for the calculation of forward kinematics, whereas geometric techniques are used for inverse kinematics calculations. A simulation of kinematic analysis is performed in MATLAB R2021a. The mechanical design of ROBO-S is carried out in PTC CREO 9.0. MATLAB simulations confirm that the robotic arm can follow the trajectory obtained from published experimental results. To demonstrate the feasibility of the design, the robotic arm is fabricated using 3D printing. The results demonstrate the potential of the developed system in accurately following trajectories for wind-tunnel testing applications. Full article

With the development of various emerging structures, concrete-filled steel tubular (CFST) columns have become critical load-bearing components in key infrastructures such as subways and underground utility tunnels. Accurately predicting their ultimate bearing capacity (N_u) is essential for guaranteeing structural safety. To address the limitations of traditional empirical formulas and code-based calculation approaches, this paper proposes a prediction model for ultimate bearing capacity based on the CatBoost algorithm optimized by Random Search. Furthermore, the marginal contribution of each key feature to the prediction results is measured through interpretability analysis. First, a database containing 438 CFST column ultimate bearing capacity test cases was established, with key parameters such as geometric dimensions and material properties as input variables. Second, the predictive performance of six machine learning algorithms—CatBoost, LightGBM, Random Forest (RF), Gradient Boosting (GB), K-Nearest Neighbors (KNN), and XGBoost—was compared. A five-fold cross-validation integrated with a Random Search strategy was employed for joint hyperparameter optimization. The results show that the optimized CatBoost model significantly outperforms other algorithms and conventional design codes, achieving a coefficient of determination (R²) as high as 0.99 and a root mean square error (RMSE) of 174.29 kN. Furthermore, the SHAP (Shapley Additive exPlanations) method was used to perform global and local interpretability analyses of the prediction model. This not only quantified the individual contribution and interaction effects of each feature parameter on the bearing capacity but also revealed that geometric parameters are the primary influencing factor. This finding confirms a high degree of consistency between the prediction mechanism of the data-driven model and classical mechanical theories, effectively validating the model’s reliability. This study provides an efficient and reliable tool for the optimal design and rapid evaluation of CFST columns and establishes a new data-driven paradigm for the design and reinforcement of key components in underground structures. Full article

Point cloud technology, characterized by its high-precision 3D geometric acquisition in complex railway environments, has become a cornerstone for the intelligent detection, monitoring, and maintenance of railway infrastructure. This paper provides a systematic review of point cloud applications across critical railway scenarios, encompassing track geometry extraction, infrastructure component identification, tunnel and bridge modeling, clearance and encroachment analysis, and structural condition monitoring. We evaluate various mobile and stationary acquisition platforms alongside their typical data processing workflows. Furthermore, this review synthesizes cutting-edge advancements in processing algorithms, with a focus on feature extraction, semantic segmentation, and the transformative impact of deep learning and artificial intelligence on data fusion. Notably, the paper explores the synergy between point clouds and computational mechanics, specifically the construction of high-fidelity digital twins through multi-physics coupling to enable real-time simulation of structural stress distribution and damage evolution. We critically analyze persistent technical bottlenecks, such as acquisition efficiency, monitoring precision, data fragmentation, environmental interference, and the complexities of multi-modal data fusion. Finally, the paper outlines future research trajectories, focusing on autonomous intelligent sensing, multi-sensor integration, and the comprehensive digital transformation of railway infrastructure management, aiming to provide a robust theoretical framework and technical roadmap for the sustainable intelligentization of global railway systems. Full article

Tunnel point cloud semantic segmentation is a critical step in achieving refined perception and intelligent management of tunnel structures. Addressing common challenges including indistinct boundaries and fine-grained category discrimination, this paper proposes MFPNet, a multi-scale feature perception network specifically designed for tunnel scenarios. This approach employs kernel convolution to effectively model local point cloud geometries within continuous spaces. Building upon this foundation, an error-feedback-based local-global feature fusion mechanism is designed. Through bidirectional information exchange, higher-level semantic information compensates for and constrains lower-level geometric features, thereby mitigating information fragmentation across semantic hierarchies. Furthermore, an adaptive feature re-calibration and cross-scale contextual correlation mechanism is introduced to dynamically modulate multi-scale feature responses. This explicitly models contextual dependencies across scales, enabling collaborative aggregation and discriminative enhancement of multi-scale semantic information. Experimental results on tunnel point cloud datasets demonstrate that the proposed MFPNet has achieved significant improvements in both overall segmentation accuracy and category balance, with mIoU reaching 87.5%, which is 5.1% to 33.0% higher than mainstream methods such as PointNet++ and RandLA-Net, and the overall classification accuracy reaching 96.3%. These results validate the method’s efficacy in achieving high-precision three-dimensional semantic understanding within complex tunnel environments, providing robust technical support for tunnel digital twin and intelligent detection applications. Full article

High-reliability localization is essential for underground mining autonomous vehicle, as inaccurate positioning triggers collision risks and limits deployment in safety-critical environments. Underground mining localization faces unique challenges: kilometer-scale signal-free tunnels restrict traditional technologies, while wheel slippage-induced non-Gaussian noise and geometric-degraded tunnel localization failures further reduce accuracy—issues existing methods cannot address simultaneously. To resolve these bottlenecks, this study develops a scenario-adapted, self-correcting positioning system for underground autonomous vehicles, fusing multi-source onboard sensor data to suppress slip noise and ensure feature-deficient environment robustness. We propose a three-stage cascaded filtering system: it first fuses LiDAR, IMU, wheel speed, and steering angle data for a self-contained framework, then adds two dedicated modules for core challenges. For wheel slippage noise, an anti-slip prior estimation algorithm integrates kinematic models with IMU data, plus a low-adhesion mine surface-tailored slip compensation mechanism to ensure reliable state estimation and eliminate slip deviations. For geometrically degraded tunnel failures, an anti-degradation algorithm uses point cloud degradation-derived regularization constraints and regularized Kalman filtering to enable stable positioning updates. Experiments show that the system achieves sub-meter accuracy and full-area coverage underground, with improved performance under severe wheel slip and in feature-deprived zones. This work fills the gap in high-reliability, self-contained localization for kilometer-scale underground mining vehicles and provides a safety-oriented paradigm for autonomous vehicle scaling, aligning with critical scenario driving safety demands. Full article

The Magnetic Suspension Balance System (MSBS) serves as a core apparatus for interference-free aerodynamic testing in wind tunnels, where its high-precision levitation control performance directly determines the reliability of aerodynamic force measurements. This paper addresses the strong coupling issues induced by rigid-body motion in the MSBS vertical suspension system and proposes a decoupling control framework integrating classical decoupling methods with geometric feature transformation. First, a nonlinear dynamic model of the six-degree-of-freedom MSBS is established. Through linearization analysis of the vertical suspension system, the intrinsic mechanism of displacement-pitch coupling is revealed. Building upon this foundation, a state feedback decoupling controller is designed to achieve decoupling among dynamic channels. Simulation results demonstrate favorable control performance under ideal linear conditions. To further overcome its dependency on model parameters, a decoupling strategy based on geometric feature transformation is proposed, which significantly enhances system robustness in nonlinear operating conditions through state-space reconstruction. Finally, the effectiveness of the proposed method in vertical suspension control is validated through both numerical simulations and a physical MSBS experimental platform. Full article

This paper proposes a multi-sensor data-fusion-based method for real-scene 3D reconstruction and digital twin visualization of coal mine tunnels, aiming to address issues such as low accuracy in non-photorealistic modeling and difficulties in feature object recognition during traditional coal mine digitization processes. The research employs cubemap-based mapping technology to project acquired real-time tunnel images onto six faces of a cube, combined with navigation information, pose data, and synchronously acquired point cloud data to achieve spatial alignment and data fusion. On this basis, inner/outer corner detection algorithms are utilized for precise image segmentation, and a point cloud region growing algorithm integrated with information entropy optimization is proposed to realize complete recognition and segmentation of tunnel planes (e.g., roof, floor, left/right sidewalls) and high-curvature feature objects (e.g., ventilation ducts). Furthermore, geometric dimensions extracted from segmentation results are used to construct 3D models, and real-scene images are mapped onto model surfaces via UV (U and V axes of texture coordinate) texture mapping technology, generating digital twin models with authentic texture details. Experimental validation demonstrates that the method performs excellently in both simulated and real coal mine environments, with models capable of faithfully reproducing tunnel spatial layouts and detailed features while supporting multi-view visualization (e.g., bottom view, left/right rotated views, front view). This approach provides efficient and precise technical support for digital twin construction, fine-grained structural modeling, and safety monitoring of coal mine tunnels, significantly enhancing the accuracy and practicality of photorealistic 3D modeling in intelligent mining applications. Full article

Simultaneous Localization and Mapping (SLAM) is a critical technology for robot intelligence. Compared to cameras, Light Detection and Ranging (LiDAR) sensors achieve higher accuracy and stability in indoor environments. However, LiDAR can only capture the geometric structure of the environment, and LiDAR-based SLAM often fails in scenarios with insufficient geometric features or highly similar structures. Furthermore, low-cost mechanical LiDARs, constrained by sparse point cloud density, are particularly prone to odometry drift along the Z-axis, especially in environments such as tunnels or long corridors. To address the localization issues in such scenarios, we propose a forward-enhanced SLAM algorithm. Utilizing a 16-line LiDAR and a monocular camera, we construct a dense colored point cloud input and apply an efficient multi-modal feature extraction algorithm based on centroid distance to extract a set of feature points with significant geometric and color features. These points are then optimized in the back end based on constraints from points, lines, and planes. We compare our method with several classic SLAM algorithms in terms of feature extraction, localization, and elevation constraint. Experimental results demonstrate that our method achieves high-precision real-time operation and exhibits excellent adaptability to indoor environments with similar structures. Full article

Detecting leakage using a point cloud acquired by mobile laser scanning (MLS) presents significant challenges, particularly from within three-dimensional space. These challenges primarily arise from the prevalence of noise in tunnel point clouds and the difficulty in accurately capturing the three-dimensional morphological characteristics of leakage patterns. To address these limitations, this study proposes a classification method based on XGBoost classifier, integrating both intensity and geometric features. The proposed methodology comprises the following steps: First, a RANSAC algorithm is employed to filter out noise from tunnel objects, such as facilities, tracks, and bolt holes, which exhibit intensity values similar to leakage. Next, intensity features are extracted to facilitate the initial separation of leakage regions from the tunnel lining. Subsequently, geometric features derived from the k neighborhood are incorporated to complement the intensity features, enabling more effective segmentation of leakage from the lining structures. The optimal neighborhood scale is determined by selecting the scale that yields the highest F_1-score for leakage across various multiple evaluated scales. Finally, the XGBoost classifier is applied to the binary classification to distinguish leakage from tunnel lining. Experimental results demonstrate that the integration of geometric features significantly enhances leakage detection accuracy, achieving an F_1-score of 91.18% and 97.84% on two evaluated datasets, respectively. The consistent performance across four heterogeneous datasets indicates the robust generalization capability of the proposed methodology. Comparative analysis further shows that XGBoost outperforms other classifiers, such as Random Forest, AdaBoost, LightGBM, and CatBoost, in terms of balance of accuracy and computational efficiency. Moreover, compared to deep learning models, including PointNet, PointNet++, and DGCNN, the proposed method demonstrates superior performance in both detection accuracy and computational efficiency. Full article

When facing geometrically similar environments such as subway tunnels, Scan-Map registration is highly dependent on the correct initial value of the pose, otherwise mismatching is prone to occur, which limits the application of SLAM (Simultaneous Localization and Mapping) in tunnels. We propose a novel coarse-to-fine registration strategy that includes geometric feature extraction and a keyframe-based pose optimization model. The method involves initial feature point set acquisition through point distance calculations, followed by the extraction of line and plane features, and convex hull features based on the normal vector’s change rate. Coarse registration is achieved through rotation and translation using three types of feature sets, with the resulting pose serving as the initial value for fine registration via Point-Plane ICP. The algorithm’s accuracy and efficiency are validated using Innovusion lidar scans of a subway tunnel, achieving a single-frame point cloud registration accuracy of 3 cm within 0.7 s, significantly improving upon traditional registration algorithms. The study concludes that the proposed method effectively enhances SLAM’s applicability in challenging tunnel environments, ensuring high registration accuracy and efficiency. Full article

The prompt and accurate detection of tunnel lining cracks is essential for maintaining the safety and reliability of tunnels. Deep learning-based approaches have significantly advanced automated crack detection, delivering improved efficiency and precision in tunnel inspection. Nevertheless, the intricate characteristics of cracks, manifesting as fine, elongated, and irregular structures, pose substantial challenges for deep learning-based semantic segmentation networks, hindering their ability to achieve comprehensive and accurate identification. Aiming to tackle these challenges, this paper proposes a novel dual-view snake Unet (DSUnet) model, which integrates a hybrid snake cascading (HSC) module and a Haar wavelet downsampling (HWD) operation. The HSC module enhances the network’s capability of extracting tunnel lining cracks by synergistically combining features derived from standard convolutions and bidirectional dynamic snake convolutions, thereby capturing intricate geometric and contextual information. Meanwhile, the HWD operation facilitates the preservation of critical spatial information by performing multi-scale feature refinement, which effectively reduces segmentation uncertainty. Experimental results demonstrate the proposed DSUnet achieves a mean Dice coefficient (MDice) of 71.8% and a mean intersection over union (MIoU) of 77.4%. Compared to the baseline Unet model, DSUnet delivers improvements of 1.3% in MDice and 0.6% in MIoU, respectively. Additionally, the proposed model consistently outperforms several state-of-the-art semantic segmentation networks, highlighting its robustness and accuracy in detecting tunnel lining cracks. These findings position DSUnet as a promising tool for automated tunnel inspection, contributing to improved safety and operational reliability. Full article

Three-dimensional numerical simulation of subsurface flow dynamics in karst conduits at dam sites represents a pivotal component of hydrogeological research, essential for unraveling the intricate behavior of water movement within karstified terrains. This study introduces a novel approach for accounting for the presence of karst conduits and presents a comprehensive three-dimensional flow simulation for the dam site of the Jingxian Pumped Storage Hydropower Plant. This method reduces mesh division, simplifies calculations, and improves model convergence. The findings reveal that the numerical model adeptly captures the declining groundwater levels within the study area, with enhanced precision achieved through the utilization of COMSOL’s Line Mass Source feature. By representing leakage tunnel cylinders as edges, the model significantly improves meshing efficiency, circumventing the computational burden associated with the explicit resolution of intricate geometric details. In the absence of remedial measures, the simulation predicts that groundwater will preferentially drain downstream via two distinct leakage pathways at the dam’s base, presenting a potential threat to the structural integrity and operational stability of the project. To address this risk, the implementation of robust seepage control measures is imperative. Once these measures are established, the dam is expected to function as an effective hydraulic barrier, ensuring the long-term stability and operational efficacy of the hydropower plant. Full article

Asymmetric cove-edged graphene nano-ribbons were employed as metallic electrodes in a hybrid gap device structure with zig-zag graphene nano-ribbons terminations for amino acid recognition and peptide sequencing. On a theoretical basis, amino acid recognition is attained by calculating, using the non equilibrium Green function scheme based on density functional theory, the transversal tunnelling current flowing across the gap device during the peptide translocation through the device. The reliability and robustness of this sequencing method versus relevant operations parameters, such as the bias, the gap size, and small perturbations of the atomistic structures, are studied for the paradigmatic case of Pro-Ser model peptide. I evidence that the main features of the tunnelling signal, that allow the recognition, survive for all of the operational conditions explored. I also evidence a sort of geometrical selective sensitivity of the hybrid cove-edged graphene nano-ribbons versus the bias that should be carefully considered for recognition. Full article

Automatically identifying mine and tunnel infrastructure elements, such as rock bolts, from point cloud data improves deformation and quality control analyses and could ultimately contribute to improved safety on engineering projects. However, we hypothesize that existing methods are sensitive to small changes in object characteristics across datasets if trained insufficiently, and previous studies have only investigated single datasets. In this study, we present a cross-site training (generalization) investigation for a multi-class tunnel infrastructure classification task on terrestrial laser scanning data. In contrast to previous work, the novelty of this work is that the models are trained and tested across multiple datasets collected in different tunnels. We used two random forest (RF) implementations and one neural network (NN), as proposed in recent studies, on four datasets collected in different mines and tunnels in the US and Canada. We labeled points as belonging to one of four classes—rock, bolt, mesh, and other—and performed cross-site training experiments to evaluate accuracy differences between sites. In general, we found that the NN and RF models had similar performance to each other, and that same-site classification was generally successful, but cross-site performance was much lower and judged as not practically useful. Thus, our results indicate that standard geometric features are often insufficient for generalized classification of tunnel infrastructure, and these types of methods are most successful when applied to specific individual sites using interactive software for classification. Possible future research directions to improve generalized performance are discussed, including domain adaptation and deep learning methods. Full article