Search Results (13,935)

Autonomous task assignment in multi-unmanned aerial vehicle (UAV) systems operating in dynamic and safety-critical airspace environments is highly challenging due to complex spatial interactions and rapidly changing relative geometries. This paper proposes a hierarchical decision-making framework that bridges individual maneuvering behaviors with cooperative task allocation in multi-agent aerial systems. First, a high-fidelity single-agent maneuver model is learned using a physics-consistent simulation environment, where spatial advantage is evaluated based on relative distance and angular relationships within a kinematically feasible interaction zone (KIZ). Subsequently, a Geometry-Aware Graph Attention Network (GA-GAT) is developed to address scalable multi-agent assignment problems. Unlike conventional approaches that rely on flat feature representations, the proposed method explicitly incorporates kinematic feasibility constraints into the attention mechanism via a novel gating module, enabling efficient relational reasoning under dynamic conditions. The proposed framework is applicable to a range of civilian and safety-oriented scenarios, including UAV swarm coordination, emergency response monitoring, infrastructure inspection, and autonomous airspace management. Simulation results demonstrate that the GA-GAT-based approach significantly outperforms heuristic baselines in terms of coordination efficiency and overall system performance in complex multi-agent environments. This study highlights that decoupling maneuver-level control from high-level coordination provides a scalable and computationally efficient solution for real-time multi-UAV decision-making in safety-critical applications. The proposed framework is designed for general multi-agent coordination problems in civilian aerial applications. Full article

Ensuring the visibility of road markings is critical for traffic safety, yet current inspection methods remain either prohibitively expensive (retroreflectivity) or subjective (manual assessment). This article introduces the Random Generated Reference (RGR) method, a novel automated solution for quantifying marking degradation using a standard on-board camera. The proposed pipeline is a complete protocol from video acquisition to road marking inspection and validation of the inspection that combines deep learning with computer vision: YOLOv8 is employed for robust detection, while a unique algorithm generates a “perfect virtual reference” that dynamically replicates the real scene’s geometry and illumination conditions, including shadows. By computing pixel-level deviations between the observed marking and this ideal reference, the system assigns a continuous degradation score aligned with the UK CS126 standard. Experimental validation was conducted on a real-world circuit yielding over 20,000 detections. Verification via Cochran sampling demonstrates that 68% of the automated assessments fall within one class of human inspection. This proof-of-concept confirms the viability of an approach based on generating the ground truth and scene conditions—such as illumination, shadows, rain, traffic, etc.—for road marking inspection. Full article

Girth welds are susceptible to defects under high internal pressure and stress. While phased array ultrasonic testing (PAUT) is widely used for non-destructive evaluation, manual inspection remains inefficient and highly dependent on expertise. Furthermore, existing deep learning models often struggle with low accuracy and high complexity. This paper proposes a PAUT defect classification method based on YOLOv8. First, median filtering is employed for denoising, and the results show that noise is effectively reduced while preserving key features, achieving PSNR values of 35.132, 35.938, and 36.138 for slag inclusion, pores, and lack of fusion (LOF), respectively. Subsequently, the spatial enrichment algorithm (SEA) is applied to enhance image details without amplifying noise, yielding a PSNR of 33.71 and an SSIM of 0.96. Finally, the YOLOv8 model is implemented for defect recognition. Experimental results demonstrate that the proposed approach achieves a superior balance between precision and recall with high reliability. This method offers a robust and efficient solution for automated PAUT evaluation in practical engineering applications. Full article

The simultaneous analysis of geometric morphology and thermodynamic states from heterogeneous sensing modalities is essential for high-temperature industrial inspection. While supervoxel segmentation is effective for extracting fine structures, conventional fixed-weighting schemes often struggle with the inherent heterogeneity between spatial sensors and thermal sensors. This paper proposes a segmentation framework for thermo-geometric point clouds based on Pareto-optimal weight learning and gradient anisotropy. A multi-objective evolutionary optimization algorithm is employed for multi-modal Pareto weight learning to adaptively balance geometric and thermal constraints. The developed gradient-anisotropic supervoxel generation algorithm introduces a local saliency factor to achieve fine-grained thermodynamic segmentation. Furthermore, a gradient damping mechanism is implemented to ensure high thermal-boundary adherence even in geometrically planar regions by imposing anisotropic penalty forces. Finally, a region-growing method based on the optimized multi-sensor fusion weights is utilized to merge similar supervoxels. Experimental results demonstrate that our approach outperforms traditional baselines by achieving high-fidelity thermal segmentation and multi-modal boundary preservation, while accepting a modest and necessary compromise in geometric compactness to accommodate spatial–thermal inconsistencies. Full article

Under long-term marine environmental loading, deep-water risers are highly susceptible to fatigue damage, and the accumulation of local damage may lead to global structural failure. In this study, the fatigue damage mechanism and crack growth behavior of a girth-welded riser are systematically investigated. Full-scale radial fatigue test results of risers are referenced, and the experimental process is reproduced through numerical simulation. A finite element model of a girth-welded riser is established. The fatigue crack growth process is subsequently simulated, yielding the crack propagation path and crack growth rate curves. By comparison with experimental results, the characteristics of the crack growth process are analyzed, and the feasibility and accuracy of numerical simulations in predicting fatigue crack growth in riser girth welds are verified. A relatively accurate prediction model for fatigue crack growth in risers is proposed. To further improve the accuracy of crack growth prediction, a machine learning-based correction model is developed. On the basis of available in-service inspection data, a correction strategy is proposed in which the predicted crack growth process is dynamically updated with measured crack growth data. The proposed approach establishes a theoretical foundation for accurate and forward prediction of fatigue fracture damage in riser structures. Full article

The mechanical properties of stone masonry and its behavior under monotonic and cyclic loading depend significantly on the local properties of the masonry and the wall typology. This paper presents preliminary results from in situ inspection of stone masonry typologies at several locations in the Kvarner Littoral of Croatia, which revealed the use of earth mortar in a building over 200 years old instead of the commonly used lime mortar. This finding prompted the selection of this building as a case study, for which a detailed visual survey was conducted and laboratory testing employed to characterize the masonry components. The visual inspection showed that the walls of the case study building are constructed from non-degraded stones, with wedges between the blocks and larger corner blocks. The earth mortar is degraded on the wall surface, so non-destructive testing was unsuccessful. Laboratory tests on stone specimens confirmed high compressive strength (over 135 MPa), while laboratory tests on earth mortar specimens indicated compressive strength between 2.22 and 2.65 MPa. The stone compressive strength is comparable to that of high-quality Croatian limestones, while the compressive strength of the earth mortar is comparable to that of historic lime mortars. Microscopic analysis and FTIR spectroscopy of the earth mortar revealed that it does not contain sand or gravel, what distinguishes it from commonly used historic earth mortars, where clay minerals serve as a binder for sand and silt particles. This study presents the first comprehensive research on the material properties of an earth mortar in Croatia. Full article

This study conducts multi-scale numerical simulations spanning atomic to macroscopic scales (i.e., from nanometer to millimeter scale) to investigate the fatigue crack propagation behavior in the welded heat-affected zone (HAZ) of AH36 shipbuilding steel. A coupled molecular dynamics–finite element method (MD-FEM) was employed to establish a multi-scale model. Through the transfer of boundary displacements, equivalent mapping of crack morphology, and crack-tip tracking, an iterative multi-scale simulation of 600 tension–tension fatigue cycles was achieved. The results indicate that the crack propagation rate is significantly influenced by crack tip morphology (blunting/sharpening) and growth direction. Notably, the peak strain at the boundary is not the sole determining factor. Periodic blunting of the crack tip occurs during cyclic loading, accompanied by a decrease in the propagation rate. Additionally, the stress field near the crack tip induces microscopic defects such as voids in the nearby area, affecting the crack propagation. This study, based on multi-scale analysis, reveals the microscopic mechanism and evolution law of fatigue crack propagation in the heat-affected zone of AH36 steel welds. Full article

Automated detection of defects in welds are inevitable in the assurance of structural integrity, but this faces serious challenges due to the microscopic characteristics of the discontinuities, low visual contrast and infrequent occurrence of defect samples. Conventional deep learning methods, while accurate, often lack interpretability and exhibit low recall for rare defects. This paper proposes a novel hybrid system combining a Generative Adversarial Network (GAN), a Convolutional Neural Network (CNN), and Extreme Gradient Boosting (XGBoost 2.0.0) to enhance weld defect classification performance and transparency. Firstly, a Deep Convolutional GAN (DCGAN) creates synthetic images of the minority classes; thus, the problem of class imbalance is resolved. Then, a pretrained ResNet50V2 CNN is used to extract features of the deep layers from the original images as well as from the generated ones. After that, these features are fed into an XGBoost classifier, which uses tree-based learning to optimize classification results and make the process more understandable to the user. Furthermore, interpretation is also facilitated by Grad-CAM rendering of the CNN regions of interest and SHAP analysis to measure the involvement of the features in XGBoost. Experiments using the available LoHi-WELD datasets show that the overall accuracy is significantly improved, the per-class recall of the rare defects is also enhanced, and the robustness is also improved. The proposed hybrid method not only achieves better results but also generates visual/explainable output, which is very valuable when the system is implemented in industrial welding inspection systems. This paper serves as a liaison between the latest AI technology and the practical interpretability requirements of the mechanical and welding engineering fields. Full article

Background: Root-knot nematodes (RKNs) are destructive parasites affecting both agricultural and natural plants. Fagopyrum tataricum, a phenolic-rich edible and medicinal plant, has antidiabetic, anti-inflammatory, and anticancer properties, yet the impact of RKN infection on its rhizosphere microbiome remains unclear. Methods: We employed full-length 16S rRNA gene sequencing (FL16S) to profile bacterial communities in the rhizosphere of healthy and RKN-infected F. tataricum plants. Results: FL16S classified 78.41% of operational taxonomic units (OTUs) at the genus level and 69.18% at the species level. Healthy plants showed higher richness, diversity, and evenness, while principal co-ordinate analysis (PCoA) and PERMANOVA indicated significant RKN-associated shifts in community composition. Dominant phyla included Bacteroidota, Proteobacteria, Patescibacteria, Verrucomicrobiota, Actinobacteriota, Acidobacteriota, and Chloroflexi, with Abditibacteriota enriched in healthy and Acidobacteriota in diseased rhizospheres. At the OTU level, 66 differentially abundant taxa were identified, including nine hub OTUs in healthy plants, suggesting keystone roles in network stability. Network analyses revealed reduced diversity, interactions, and altered intra- and inter-phylum dynamics under RKN infection. Conclusions: These findings provide insight into rhizosphere microbial responses to RKN parasitism in F. tataricum and identify potential microbial biomarkers and biocontrol targets, supporting microbiome-based management strategies. Full article

The steam generator is a core component of nuclear power plants that facilitates heat exchange between the primary and secondary circuits, directly impacting the overall operation of the plant in terms of safety and reliability. During prolonged operation, the heat transfer tubes of the steam generator are subjected to erosion, corrosion, and cracking due to high-temperature, high-pressure fluid impact and vibration. Existing in-service inspection strategies for heat transfer tubes generally employ fixed intervals and coverage, failing to effectively differentiate the actual risk of tubes in various regions, leading to wasted inspection resources or safety hazards. This paper proposes a dynamic inspection and plugging management strategy based on flow-induced vibration (FIV) analysis, specifically utilizing the flow stability ratio (FSR). By calculating the FSR of heat transfer tubes, the strategy categorizes them into high-risk, medium-risk, and low-risk regions, and dynamically adjusts inspection frequency and coverage based on these risk levels. Theoretical analysis and validation with actual data demonstrate that this strategy can improve inspection efficiency and ensure the safety of the steam generator. Full article

Digital electricity meters display readings via digits, but accurate image-based recognition faces a key challenge: the frequent omission of decimal points creates a critical asymmetry between the visual image and its true semantic meaning. To address this visual-semantic asymmetry, we propose an improved YOLOv10n approach incorporating cascaded Visual-Semantic processing. We introduce a Reparameterized Convolution Single-Shot Aggregation (RCSOSA) module and a SimAM attention mechanism to enhance feature extraction, and employ Normalized Wasserstein Distance (NWD) Loss to boost small-target detection. To rectify the visual-semantic asymmetry, we introduce domain-specific format rules based on power industry standards (taking GB/T 17215-2018 as an example) to provide structural constraints for digit recognition. Experimental results show superior performance with 0.870 precision, 0.932 mAP50, and 116 FPS inference speed, outperforming reference models in both precision and efficiency for real-time meter inspection. Full article

Communication latency is one of the main factors limiting the practical scalability of unmanned aerial vehicle (UAV) swarms operating with distributed formation control. In real-time UAV missions, such as coordinated swarm navigation, autonomous inspection, and aerial monitoring, delayed information exchange directly affects formation stability and operational safety. In practical aerial networks, inter-UAV communication latency is influenced by stochastic effects including jitter, burst delays, and multi-hop propagation, which are rarely captured by the simplified deterministic delay assumptions commonly adopted in analytical formation-control studies. This paper introduces a measurement-informed stochastic delay model and a communication–control delay-feasibility framework that jointly account for per-link latency behavior, multi-hop delay accumulation, and controller-level delay tolerance. The proposed framework is evaluated using an attractive–repulsive distance-based potential field (ARD–PF) formation controller, for which the maximum admissible end-to-end delay is quantified as a function of swarm size and inter-UAV separation. The delay model is calibrated and validated using more than 15,000 in-flight communication delay samples collected from a multi-UAV LoRa platform operating under realistic flight conditions. The results show that different mechanisms limit swarm operation under different operating scenarios. In some configurations, stochastic communication latency becomes the dominant constraint, whereas in others, formation geometry or network load determines the feasible operating region. Based on these elements, the proposed framework characterizes delay-feasible operating regions and predicts the maximum feasible swarm size under distributed formation control and realistic multi-hop communication latency. Full article

The extensive application of unmanned aerial vehicles (UAVs) in power inspection, military operations and environmental monitoring demands stronger robustness and adaptability for autonomous decision-making systems. Existing methods suffer from heavy map dependence, high computational complexity and insufficient exploration and generalization. Traditional approaches based on expert rules and planning algorithms only suit fixed scenarios and degrade severely in complex dynamic environments. To address these problems, this paper proposes a complex-scene-oriented autonomous decision-making method for UAVs (CADU). It builds a closed-loop decision chain by integrating perception, strategy and execution modules, and adopts curiosity mechanism and contrastive learning to enhance exploration and adaptability. Experimental results show that the proposed CADU achieves an average reward of 0.85, a trajectory smoothness of 0.87, a flight stability of 0.85, and a cumulative collision count of $8\pm 1.2$, which significantly outperforms DDPG, PPO and SAC baselines. It provides a reliable and efficient scheme for UAV autonomous decision-making in complex scenarios. Full article

Estimating in a stream’s cross-section the depth-averaged velocity, V, from the free-surface velocity, v_surf, is an efficient, non-invasive hydrometric method. The ratio f_v = V/v_surf is typically assumed constant at f_v = 0.86 in field applications, despite observations to the contrary. Guidance is, therefore, needed in estimating actual f_v-ratios when velocity profile data are absent. This work provides field-verified guidance based on the hydromechanics of the logarithmic velocity law, which shows that f_v depends on the scaled resistance measure ‘friction length/depth’, y_o/h, with the y_o(k) function of the equivalent sand grain roughness, k. The mean-to-surface-velocity ratio in rough-bed streams is estimated from the bed roughness and stream morphology by modifying Nikuradze’s equation, y_o = k/30, to y_o = ck, with c(h/k) ≥ 1/30, and k ≈ D₈₄—data fit: c ≈ 8.61(h/k)^−1.821, ~5 ≤ h/k < ~30. Field-verification of the ratio’s modified hydromechanics, f_v = f$\left(h/y_o\right),$ with y_o(h/k) evaluated from bed roughness estimated by inspection or sieve analysis shows this ratio holding within ~|10|% error for shallow streamflow over a coarse bed of gravels and rocks, giving submergences of ~5 ≤ h/D₈₄ ≤ ~30; y_o = k/30 suits large streams with smooth beds (h/k ≥ ~30, f_v ≥ ~0.86). Variable roughness-estimated f_v-ratios appear to be more reliable than the fixed default, f_v(h/y_o ≈ 1000) = 0.86. This flow-gauging concept is based on observable physical characteristics of a monitoring cross-section and facilitates the rating of hard-to-access streams draining small basins in ragged upland terrain. Full article

The rapid inspection of urban road hazards, such as subsurface voids and pipeline damage, demands high efficiency and precision in detection technology. Conventional Ground Penetrating Radar (GPR) systems often face limitations in urban environments, including slow survey speeds, poor channel scalability, and the trade-off between shallow resolution and deep penetration. The proposed system integrates a dual-band antenna array (200 MHz and 400 MHz) to resolve the classical resolution–penetration trade-off, simultaneously capturing high-resolution shallow data and achieving deep subsurface penetration in a single pass. To overcome the sampling rate bottleneck inherent in low-cost microcontrollers, a custom Time-Division Step Multiplexing (TDSM) protocol extends the equivalent sampling period to 0.38 µs across 24 parallel channels while maintaining a 200 kHz pulse repetition rate—enabling real-time data streaming at vehicle speeds up to 70 km/h with 5 cm trace spacing. This capability directly addresses the critical challenge of traffic disruption on urban arterials caused by conventional slow-speed GPR surveys. Complementing this, a master-slave FPGA-MCU hierarchical architecture provides seamless channel scalability from 24 to 36 channels, adapting to diverse swath width requirements without hardware redesign. Laboratory physics model experiments demonstrate a penetration depth exceeding 3 m after convolutional sparse fusion of the dual-band data, covering the typical burial depth of urban utilities. This study provides a deployable high-resolution underground detection solution for rapid urban infrastructure surveys and emergency disease detection by breaking the traditional constraints of channel number, sampling rate, and detection speed, significantly reducing interference with urban main traffic. Full article