Search Results (585)

Urban drainage pipelines are crucial for flood control, drainage, and environmental quality. However, fog within pipelines degrades image quality, hindering the identification of damage features such as cracks and leaks. Existing dehazing algorithms struggle with the unique challenges presented by drainage pipelines, such as their cylindrical structure, non-uniform lighting, and multi-scale particulate interference, leading to inadequate feature extraction and weak cross-channel dependency modeling. To address these issues, we propose a novel drainage pipeline image dehazing network based on a pyramid attention mechanism. Specifically, our proposed method incorporates a custom-designed multi-scale spatial pyramid attention (MSPA) module, which combines hierarchical pyramid convolution and spatial pyramid recalibration modules. This enables the dynamic adjustment of multi-scale feature weights and the effective modeling of cross-channel long-range dependencies. Extensive experiments demonstrate that our network achieves superior dehazing performance across diverse underground environments, particularly in synthetic foggy dataset under real pipeline conditions, outperforming state-of-the-art dehazing algorithms. This proposed approach provides a reliable solution for high-precision visual inspection in complex pipeline scenarios. Full article

Corrosion of reinforcing steel is a key cause of deterioration in reinforced concrete (RC) structures exposed to coastal environments with chloride presence. The loss of reinforcing steel cross-sectional area, cracking of the concrete cover, and reduction in confinement progressively decrease both strength and ductility of structural elements. This study provides a reproducible, open-access dataset, compiling input parameters and numerical results of the cyclic behaviour of isolated RC columns and RC frames, specifically addressing their nonlinear cyclic response under moderate corrosion (η < 25%), as well as in the non-corroded (baseline) conditions, generated through conventional nonlinear modelling. In terms of modelling, the methodology applies fibre-section modelling for columns and concentrated plastic hinges for beams. Furthermore, the corrosion effects are incorporated by reducing the steel area and ultimate strain, while also accounting for the decrease in compressive strength of the cracked concrete cover. Therefore, the cyclic response is represented by a Pivot-type hysteretic model. It is worth noting that the dataset provides model input information, such as material stress–strain relationships and backbone curves reflecting corrosion-induced deterioration. It also includes structural outputs, such as force–displacement relationships, and envelopes of quasi-static hysteretic cycles for the analyzed columns and frames. Overall, the dataset facilitates the calibration and validation of numerical models for RC structures affected by corrosion. In conclusion, the contribution enhances the reliability of computational simulations and supports the development of predictive tools for structural performance under degradation scenarios. Full article

The disposal of waste tyres presents a significant environmental challenge, necessitating sustainable, high-value recycling solutions. This study explores the incorporation of waste tyre metal fibre (WTMF) into hot mix asphalt (HMA) to enhance mechanical performance while reducing its electrical resistivity as well as the landfill burden. The primary goal of this research is to apply response surface methodology (RSM) to experimental data for modelling and optimizing WTMF-modified HMA mixes by capturing the coupled effects of fibre reinforcement and binder content on mechanical and functional performance. The microstructural characteristics of WTMF were examined using scanning electron microscopy (SEM), energy-dispersive X-ray spectroscopy (EDS), and X-ray diffraction (XRD). WTMF-modified mixes containing five WTMF dosages (from 0% to 1.50%) and bitumen contents from 4% to 6% were prepared and tested in the laboratory. The resulting dataset was used for RSM modelling, with WTMF and bitumen contents as input factors and Marshall stability, flow, porosity, and electrical resistivity as response variables. The central composite design (CCD) technique was employed to quantify interaction effects and to identify statistically significant trends. The developed models were validated using statistical indicators, and optimal mixture compositions were determined and experimentally verified. Microstructural analysis revealed WTMF’s irregular, rough surface with microcracks and pits, aiding crack-bridging and stress transfer. RSM results indicated 0.71% WTMF and 5.1% bitumen as an optimal combination of factors. Furthermore, high R² (>0.80) and adequate precision (>4.0) values from analysis of variance (ANOVA) underscore the significance of the proposed models, revealing a robust correlation between experimental and predicted data. This study demonstrated WTMF’s potential to be used in conventional HMA mixes, offering a sustainable recycling pathway for waste tyres. Full article

Photovoltaic (PV) power stations are pivotal for the renewable energy transition, yet their operational efficiency is often compromised by defects such as surface dust accumulation and cracks. Traditional manual inspections are labor-intensive and subjective, while conventional monitoring methods struggle with environmental interference. This study proposes YOLO-MSG, a lightweight framework specifically designed for the automated detection of PV module defects during system operation, including normal panels as well as defective conditions such as dusty and cracked panels. The methodology integrates a Multi-Scale Grouped Convolution (MSGC) module for enhanced feature extraction and a Group-Stem Decoupled Head (GSD-Head) to reduce parameter redundancy. Furthermore, a joint optimization strategy involving LAMP and logits-based knowledge distillation is employed to facilitate edge deployment. Experimental results on a specialized PV defect dataset demonstrate that YOLO-MSG achieves a superior balance between detection accuracy and computational cost. Compared to state-of-the-art models like YOLO11 and YOLOv12, YOLO-MSG significantly reduces GFLOPs and parameter count while maintaining highly competitive mean Average Precision (mAP), with improvements of 1.35% in mAP and 2.37% in mAP50-95 over the baseline models. Specifically, the model achieves an average inference speed of 90.30 FPS on the NVIDIA Jetson AGX platform. These findings confirm the algorithm’s industrial viability, providing a robust and efficient solution for the real-time automated maintenance of photovoltaic infrastructures. Full article

To address the issues of difficult heterogeneous image registration and low segmentation accuracy caused by the severe lack of illumination and significant modal differences in concrete cracks in extremely dark environments, this paper proposes a two-stage processing framework of registration–fusion first, and decoupling–segmentation later. In the registration and fusion stage, a registration algorithm based on morphological priors and multi-level quadtree spatial constraints is designed. This approach transforms the problem from pixel grayscale matching to spatial topological matching, achieving a feature fusion of high infrared saliency and high visible light sharpness. In the segmentation stage, a Latent Frequency-Decoupled Topological Network (LFDT-Net) is proposed. It utilizes Discrete Wavelet Transform (DWT) to achieve high-fidelity frequency decoupling of the low-frequency infrared backbone and the high-frequency visible light edges. Furthermore, a Cross-Frequency Guidance Module is utilized to eliminate double-edged artifacts, and a skeleton-aware topological loss function is introduced to constrain the topological integrity of the cracks. Experimental results on a self-built heterogeneous multi-modal crack dataset demonstrate that the proposed method significantly outperforms existing mainstream methods in registration accuracy, fusion quality, and segmentation accuracy. Achieving a mean Intersection over Union (mIoU) of 81.7%, the method effectively suppresses background noise in dark environments and precisely restores the microscopic edges and continuous topological structures of faint cracks. Full article

While convolutional neural networks (CNNs) excel at image classification, their generalization across domains and robustness to nonlinear degradation remain challenges in art media classification (AMC). To address these challenges, this article presents a dual-stage analytical framework: first, an evaluation of seven discrete CNN architectures—ranging from VGG16 to ConvNeXt—subjected to domain shift using the New Spain (Mexico) Art Media Dataset; and second, a formal robustness analysis using an artistic corruption benchmark (Art-C). This benchmark simulates nonlinear degradations, including cracking, oxidized varnish, and pictorial abstraction. Our results demonstrate that while deep convolutional representations maintain acceptable transferability (accuracy $>70\%$), significant variability exists in architectural stability (mean 0.0607) under progressive stochastic degradation. Notably, Xception exhibited the highest robustness (Art-mCE = 0.8039), whereas VGG16 showed the greatest relative performance decay. Severity analysis further indicates that structural perturbations induce higher error rates than chromatic shifts, suggesting that CNNs are more sensitive to topological features (depth and residual connections) than color-space distributions. We provide quantitative evidence characterizing the relationship between architectural topology and empirical stability in non-natural image domains. Full article

The automated production of large-scale labeled datasets from concrete X-ray computed tomography (CT) images is a fundamental prerequisite for training and validating deep learning-based segmentation models. However, existing methods either require extensive manual annotation or rely on domain-specific deep learning models that themselves demand labeled data—a circular dependency. This paper presents a parameter-driven three-class segmentation framework that automatically classifies each pixel in a concrete CT slice into one of three material phases: void (air pores and cracks), coarse aggregate, and mortar matrix, generating annotation masks suitable for large-scale dataset production without manual labeling. The proposed method combines: (1) fixed-threshold void detection calibrated to concrete CT grayscale characteristics; (2) adaptive percentile-based initial segmentation responsive to image-specific statistics; (3) multi-criteria connected component scoring based on area, shape descriptors (circularity, solidity, compactness, extent, aspect ratio), intensity distribution, and boundary gradient; (4) material science-informed size constraints aligned with concrete phase volume fractions; and (5) a material continuity enforcement module that applies topological hole-filling and conditional convex-hull consolidation to eliminate internal contamination within accepted aggregate regions, reducing boundary roughness by 7.6% and recovering misclassified boundary pixels. All parameters are centralized in a configuration file, enabling reproducible batch processing of 224 × 224 pixel CT slices at 0.07–1.12 s per image. Evaluated on 1007 224 × 224 concrete CT patches cropped from 200 representative scan frames, the framework produces three-class segmentation masks with physically consistent void fractions (mean 3.2%), aggregate fractions (mean 32.4%), and mortar fractions (mean 64.4%), all within ranges reported in the concrete CT literature (used as a dataset-scale QC screen, not a validation metric). Primary outputs and the archived image–mask pairs for this work are provided as an 8-bit patch archive. For pixel-wise validation, we report IoU, Dice, and pixel accuracy on an independently labeled subset that can be unambiguously paired with the released predictions: averaged over 57 matched patches, mean pixel accuracy is 88.6%, macro-mean IoU is 74.7%, and macro-mean Dice is 84.9%. The framework provides a fully automated annotation pipeline for dataset production, eliminating manual labeling costs for concrete CT image collections. The generated datasets are suitable for training semantic segmentation networks such as U-Net and its variants. Full article

To improve the accuracy and efficiency of road crack detection, this paper proposes an enhanced model based on You Only Look Once version 8 (YOLOv8). The Cross Stage Partial DarkNet (CSPDarkNet) backbone network is replaced with TransXNet, which integrates a Transformer-based self-attention mechanism with convolutional operations to better capture local features. By embedding the attention mechanism into its core module, namely the dual dynamic token mixer (D-Mixer), the TransXNet architecture is further optimized, thereby enabling coordinated attention-based feature selection and enhancement across both global and local dimensions. In addition, the Gaussian Error Linear Unit (GELU) is employed to enhance nonlinear representation capability and training stability. Experiments were conducted on the public Road Damage Dataset 2022 (RDD2022), which contains approximately 47,000 road images. The results demonstrate that, compared with the baseline model, the precision, recall, and mean Average Precision (mAP) of the proposed method are improved by 9.6, 11.7, and 8.2 percentage points, respectively; moreover, the detection accuracy and computational efficiency also outperform those of other methods. Full article

Accurate prediction of corrosion-fatigue crack growth rate in aluminum alloys is critical for the safety assessment of aerospace structures. Conventional empirical fracture-mechanic models often struggle to capture multiphysics coupling effects, whereas purely data-driven machine-learning models may lack physical interpretability and generalize poorly beyond the training distribution. To address this challenge, this study proposes a physics-guided knowledge-based XGBoost (KBXGB) model. Based on a comprehensive dataset comprising 2786 experimental records, Permutation Feature Importance was utilized to identify 11 key features, including the stress intensity factor range, stress ratio, frequency, and environmental parameters. The KBXGB framework learns the residual between physics-based empirical models (e.g., the Paris and Walker laws) and measured experimental data, recasting the complex nonlinear mapping into a correction of the systematic deviations of the physical models, thereby achieving deep integration of domain knowledge and data-driven learning. Test results demonstrate that the KBXGB model achieves a coefficient of determination (R²) of 0.9545 and a reduced Mean Relative Error (MRE) of 1.61% on the test set, outperforming standard XGBoost and traditional regression models. Crucially, in independent extrapolation validation, the standard XGBoost model failed (R² = 0.2858) with non-physical staircase artifacts, whereas the KBXGB model maintained high predictive fidelity (R² = 0.8646) and successfully reproduced physical crack growth trends. The proposed approach effectively mitigates the “black-box” limitations of machine learning in sparse data regions, offering a high-precision and physically robust tool for corrosion fatigue-life prediction under complex service conditions. Full article

Early-age shrinkage is a critical factor governing the dimensional stability and cracking susceptibility of ultra-high-performance concrete (UHPC). However, accurate prediction of UHPC shrinkage remains challenging due to the strong nonlinear interactions among mixture parameters, curing conditions, and hydration-induced internal moisture evolution, particularly when only limited experimental data are available. In this study, a systematic experimental program was conducted to investigate the influence of the binder-to-sand ratio, water-to-binder ratio, polypropylene fiber dosage, and curing environment on both early drying shrinkage and autogenous shrinkage of UHPC. Based on the experimental results, a structured dataset covering all shrinkage test data was constructed to support data-driven modeling. To improve prediction reliability under small-sample conditions, a Bayesian-optimized Extreme Gradient Boosting (BO-XGBoost) framework was developed and benchmarked against several conventional machine learning models, including Backpropagation Neural Networks (BPNNs), Random Forest (RF), and Support Vector Machines (SVMs). Shrinkage test data from other literature validated the prediction accuracy of this model, demonstrating its rationality and practicality. In addition, the Shapley Additive Explanations (SHAP) method was employed to quantitatively interpret the contribution and interaction mechanisms of key variables affecting shrinkage behavior. The results show that the BO-XGBoost model achieves the highest prediction accuracy and stability among the evaluated algorithms. SHAP analysis further reveals that curing age and curing environment dominate drying shrinkage, whereas autogenous shrinkage is primarily governed by the curing age and water-to-binder ratio. The interaction analysis also identifies the coupled effects between low water-to-binder ratio and extended curing age. The proposed framework not only improves prediction robustness for UHPC shrinkage under limited data conditions but also provides interpretable insights into the mechanisms governing early-age deformation. These findings offer a data-driven basis for optimizing UHPC mixture design and mitigating early-age cracking risks in engineering applications. Full article

This study addresses the limited availability of unified experimental datasets comparing ribbed steel and smooth FRP bars embedded in the same hybrid-fiber high-performance concrete (HPC) matrix under identical conditions. It investigates the mechanical and bond behavior of a triple-fiber HPC combining hooked-end steel (ST), basalt (BA), and polypropylene (PP) fibers and reinforced with steel, GFRP, and CFRP bars of identical diameter and embedment. Under a uniform curing regime, the HFRC reached a compressive strength of approximately 82 MPa and exhibited a high fracture energy G_f approximately 3.7 kJ/m² with a stable post-peak response in a notched-beam test, demonstrating effective multi-scale crack bridging within a dense hybrid fiber network. Pull-out tests on 200 mm embedment revealed distinct interfacial mechanisms: ribbed steel developed a pronounced peak bond stress (τ_max = 13.05 MPa) and the largest bond energy (G_b = 146 N/mm) due to mechanical interlock, whereas smooth GFRP and CFRP showed low τ_max (=1.46 and 0.78 MPa) and smoothly decaying τ–s governed by adhesion–friction with G_b = 3–4 N/mm. A consistent experimental framework enabled direct mechanistic comparison of bond–slip behavior across reinforcement types without confounding matrix or curing variables. Simple constitutive laws calibrated to the experimental τ–s curves (ramp–softening for steel and ramp–plateau or exponential for FRP) captured the stiffness, strength, and energy hierarchy with low error. The main contribution of this study lies in providing a configuration-consistent reference dataset and calibrated bond–slip descriptions for hybrid-fiber HPC members reinforced with both steel and FRP bars. The results highlight the role of the hybrid fiber network in improving crack stability and provide design-oriented parameters for anchorage assessment and nonlinear bond–slip modeling. Although the results are based on a limited experimental program, they establish a mechanistically coherent basis for further optimization of hybrid HPC matrices and development of performance-based anchorage formulations in high-performance structural applications. Full article

Open-pit mining operations rely heavily on visual inspection to identify indicators of slope instability such as surface cracks. Early identification of these geotechnical hazards enables timely safety interventions to protect both workers and assets in the event of slope failures or landslides. While computer vision (CV) approaches offer a promising avenue for autonomous crack detection, their effectiveness remains constrained by the scarcity of labelled geotechnical datasets. Deep learning (DL)-based models, in particular, require large amounts of representative training data to generalize to unseen conditions; however, collecting such data from operational mine sites is limited by safety, cost, and data confidentiality constraints. To address this challenge, this study proposes a novel hybrid game engine–generative artificial intelligence (AI) framework for large-scale dataset generation without requiring real-world training data. Leveraging a parameterized virtual environment developed in Unreal Engine 5 (UE5), the framework generates realistic images of open-pit surface cracks and enhances their fidelity and diversity using StyleGAN2-ADA. The synthesized datasets were used to train the YOLOv11 real-time object detection model and evaluated on a held-out real-world dataset of open-pit slope imagery to assess the effectiveness of the proposed framework in improving model generalizability under extreme data scarcity. Experimental results demonstrated that models trained using the proposed framework consistently outperformed the UE5 baseline, with average precision (AP) at intersection over union (IoU) thresholds of 0.5 and [0.5:0.95] increasing from 0.792 to 0.922 (+16.4%) and 0.536 to 0.722 (+34.7%), respectively, across the best-performing configurations. These findings demonstrate the effectiveness of hybrid generative AI frameworks in mitigating data scarcity in CV applications and supporting the development of scalable automated slope monitoring systems for improved worker safety and operational efficiency in open-pit mining. Full article

The Welded Bead Bending Test (WBBT) assesses steel structures intended for construction in Germany in accordance with ZTV-ING Part 4 or DBS 918 002-02, as specified in Stahl-Eisen-Prüfblatt (SEP) 1390. Test outcomes are classified as passed (p) if the minimum bending angle $\alpha \ge {60}^{\circ }$ is achieved without fracture, not passed (n.p.) if fracture occurs beforehand, and invalid if no crack propagates into the base material. This study evaluates eight supervised machine learning models for classification regarding their suitability for predicting WBBT results: Decision Tree Classifier (DT), Random Forest Classifier (RF), Histogram-based Gradient Boosting Classifier (HGBC), k-Nearest-Neighbour (KNN), Bagging Classifiers based on DT (BCDT) and RF (BCRF), Generalized Learning Vector Quantizer (GLVQ), and Generalized Matrix Learning Vector Quantizer (GMLVQ). An industrial dataset of approximately 3600 samples was compiled in collaboration with Chemnitzer Werkstoff und Oberflächentechnik GmbH (CEWUS). Evaluation metrics included Balanced Accuracy, Recall, Specificity, computation time, and prediction stability. BCDT and BCRF achieved the highest Balanced Accuracy (70.6% and 70.3%, respectively), with BCRF excelling in Specificity (82.5%), thereby reliably detecting the n.p. class. GLVQ and GMLVQ demonstrated superior stability (maximum variability between training and testing dataset 0.14% and 3.17%, respectively), while BCRF and GMLVQ required the longest training times (BCRF: 10 s–20 s; GMLVQ: up to 80 s). KNN proved least suitable for WBBT outcome prediction. Full article

Urban underground sewage pipelines often suffer from defects such as cracks, irregular joint misalignment, and stratified sedimentation blockages, which may lead to pipeline bursts, sewage overflow, and water pollution. Timely detection of abnormal defects in sewage pipelines is critical to ensuring public health and environmental sustainability. Vision-based sewage pipeline defect detection plays a crucial role in modern urban wastewater treatment systems. However, it still faces challenges such as limited feature extraction capabilities, insufficient multi-scale defect characterization, and poor positioning stability when dealing with low-contrast images and in environments with severe background interference. To address this issue, this study proposes an enhanced SAW-YOLOv8l model that integrates RT-DETR (real-time detection Transformer) with CNN (convolutional neural network) architecture. First, a C2f_SCA module improves the long-distance feature extraction capability and localization precision. Second, an AIFI-PRBN module enhances global feature correlation through attention-mechanism-based intra-scale feature interaction and reduces computational complexity using lightweight techniques. Finally, an adaptive dynamic weighted loss function based on Wise-IoU (weighted intersection over union) further improves training convergence and robustness by balancing the gradient distribution of samples. Experiments on a mixed dataset comprising Sewer-ML and industrial images demonstrate that the SAW-YOLOv8l model achieved mAP@0.5 of 86.2% and precision of 84.4%, which were improvements of 2.4% and 6.6% respectively over the baseline model, significantly enhancing the detection performance of abnormal defects in sewage pipelines. Full article

As part of a NASA University Leadership Initiative (ULI) program, this work supports the continued development and evaluation of a fatigue-based process window for stress-relieved Ti-6Al-4V specimens produced via laser powder bed fusion (PBF-LB/M). Four-point bend and axial fatigue specimens were fabricated by NASA ULI collaborators across a range of scan velocities (800–2000 mm/s) at a constant power of 370 W using an EOS M290 system. All fatigue specimens were low-stress-ground by a commercial vendor and tested at Case Western Reserve University (CWRU) under load-controlled cyclic loading at a stress ratio of R = 0.1. This paper presents a curated dataset linking PBF-LB/M process parameters to fatigue outcomes across 175 specimens. Of these, 136 fractured and this study includes fatigue crack initiation site identification and defect morphology metrics derived from post mortem SEM analysis. Specimens that reached runout (10⁷ cycles) and did not fracture under subsequent fatigue testing are retained in the dataset, with fractographic fields marked as ‘NA’ to indicate non-applicability. The dataset includes specimen metadata, processing parameters, fatigue life data, fatigue initiation site classification (e.g., keyhole, gas-entrapped pore (GeP), lack-of-fusion (LoF), contamination), defect size and shape descriptors, and spatial location relative to the free surface. These data are intended to support defect-based fatigue life prediction, probabilistic modeling, process–structure–property studies, and machine learning frameworks linking process parameters to fatigue performance in PBF-LB/M Ti-6Al-4V. Full article