Search Results (11,628)

Conveyor belts constitute critical components of bulk material handling systems, and their reliable operation directly affects process continuity, operational safety, and maintenance costs in industrial environments. Increasing requirements regarding system reliability and predictive maintenance have stimulated the development of advanced diagnostic methods for conveyor belt condition monitoring. This review presents a comprehensive analysis of conveyor belt damage detection and diagnostic approaches, with particular emphasis on sensing technologies and signal-based methodologies. The paper discusses major conveyor belt degradation mechanisms and analyzes their representation in diagnostic data obtained using different sensing modalities. Current developments in machine vision systems, magnetic methods based on magnetic flux leakage, ultrasonic techniques, and X-ray imaging are critically reviewed together with signal preprocessing procedures, feature extraction strategies, and damage classification approaches. Particular attention is devoted to the transition from conventional signal processing techniques toward machine learning and deep learning methods enabling automated feature representation and fault identification. The analysis indicates that despite substantial progress in sensing technologies and artificial intelligence, most existing solutions remain strongly sensor-specific and limited to individual data modalities. Key research gaps include the lack of unified damage representation frameworks, limited benchmark datasets, and the insufficient integration of multimodal sensing information. Future progress will likely depend on the development of integrated diagnostic ecosystems combining heterogeneous sensing technologies, advanced feature representation methods, and intelligent decision-support systems. Full article

The assembly quality of scaffolding systems directly governs the safety of personnel on construction sites. According to construction safety statistics, scaffolding-related accidents account for approximately 30–40% of construction fatalities globally, with geometric assembly deviations being a contributing factor in over 60% of scaffold collapse incidents. Traditional scaffolding inspections rely heavily on manual measurements, which are inherently inefficient, hazardous, and difficult to scale comprehensively. This study presents an automated evaluation framework that integrates computer vision with structural mechanics simulations. First, an object detection model based on the SegFormer encoder architecture is developed to precisely identify scaffolding standards, ledgers, and couplers against complex site backgrounds. Its hierarchical Transformer encoder and global self-attention mechanism enable the model to capture long-range topological relationships, achieving a mean Average Precision (mAP@0.5) of 95.2% on a custom dataset with an inference speed of 45 FPS per 640 × 640 image patch. For complete high-resolution frame processing including tiling and geometric extraction, the end-to-end pipeline requires approximately 8–12 s per frame. Second, a simplified Hough transform with a restricted parameter domain is introduced. Integrated with a dual-track image processing workflow, this algorithm performs sub-pixel centerline fitting to automatically extract critical geometric parameters, including lift height and bay width, maintaining a relative measurement error within 3.5% compared to manual ground truth. Finally, a parameterized finite element model is established. An automated mapping middleware dynamically injects the extracted as-built parameters into the simulation environment. Comparative simulation analysis indicates that a 14.7% deviation in standard lift height, coupled with an initial tilt defect of 1/150, precipitates a 22.4% reduction in the predicted structural stability factor, illustrating the framework’s capability for assessing relative capacity degradation between design intent and as-built conditions. This framework establishes a robust, closed-loop pipeline spanning visual perception and structural safety assessment, indicating potential for automated construction site safety management. Full article

Valve leakage in marine oil and gas pipelines is a critical failure mode that threatens operational safety, ecological integrity and production economic benefits, creating an urgent demand for accurate, real-time and robust fault diagnosis systems. Acoustic Emission (AE) technology captures transient acoustic signatures generated by leakage to enable non-intrusive online monitoring, while deep learning supports intelligent analysis through automatic signal feature extraction. Nevertheless, traditional AE-based leakage diagnosis methods rely heavily on manual feature engineering and fixed signal processing rules. Existing AE-driven deep learning methods fail to simultaneously deliver high detection accuracy, low inference latency and strong noise immunity, hindering their practical deployment on offshore platforms. To address these limitations, this paper proposes a Parameter-free Star-shaped Attention Fusion Network (SAFNet) for lightweight valve leakage localization using AE signals. Centered on the Temporal Pyramid Encoder (TPE) and Progressive Lightweight Star-shaped Attention (PLSA) module, SAFNet integrates Dual Bilinear Star Mapping (DBSM), Energy-Driven Feature Refiner (EDFR) and Multi-Scale Gated Attention Fusion (MS-GAF) modules. This architecture achieves efficient multi-scale temporal feature extraction, parameter-free nonlinear enhancement, noise-resistant refined feature processing and adaptive hierarchical feature fusion. The proposed method is applicable to valve leakage diagnosis of marine oil and gas pipelines under variable pressure and complex marine noise conditions. Comprehensive experiments are conducted on a dataset constructed by combining laboratory controlled leakage signals with real marine background noise recorded from the Liwan 3−1 offshore platform. The experimental results reveal that SAFNet balances high detection accuracy, compact model size and low inference latency simultaneously. Specifically, the network maintains a stable detection accuracy above 95% under pipeline pressures ranging from 2 MPa to 5 MPa, and exhibits excellent stability under extreme heavy noise environments. Ablation experiments further validate the synergistic performance gain brought by all core modules. The presented network delivers an efficient lightweight solution for valve leakage localization under simulated marine acoustic conditions, promotes the development of intelligent monitoring technologies for marine pipeline systems, and comprehensively improves offshore operational safety and marine ecological protection capacity. Full article

Chronic wounds are associated with long-standing inflammation, impaired angiogenesis, oxidative stress, microbial load and defective remodelling of the extracellular matrix, impairing tissue repair. Conventional dressings offer protection and moisture regulation but do not sufficiently address the biological failures. Electrospun nanofibrous wound dressings offer a more active regenerative platform due to their architecture, which resembles the extracellular matrix, allowing cell adhesion and migration and facilitating the localised delivery of therapeutic agents. Marine-derived polysaccharides, such as alginate, chitosan, carrageenan, fucoidan, glycosaminoglycans, and ulvan, are particularly attractive in this area due to their biocompatibility, biodegradability, sustainability, and intrinsic haemostatic, antimicrobial, anti-inflammatory, antioxidant, and immunomodulatory properties. This review critically discusses the mechanistic and translational relevance of marine polysaccharide-based nanofibres in wound healing with a focus on inflammation resolution, polarisation of macrophages, responses of keratinocytes and fibroblasts, angiogenesis, collagen deposition, redox balance and matrix remodelling. Biofabrication strategies, especially electrospinning and related nanofibre-forming strategies, are reviewed from the aspects of scaffold architecture, drug-loading capacity, controlled release, and wound microenvironment modulation. The review also discusses current shortcomings such as heterogeneity in the composition of marine polymers, mechanical fragility, sterilisation and storage issues, scalability, regulatory uncertainty and limited translation from preclinical models to clinical evidence. Overall, marine-derived polysaccharide nanofibers are a promising class of multifunctional wound dressings, but their clinical translation needs stronger standardisation, comparative in vivo evidence, safety validation and manufacturable designs. Full article

State estimation is a fundamental component of model-based Fault Detection and Diagnosis (FDD) in dynamic systems, underpinning real-time monitoring, predictive maintenance, and safety-critical operations across industries such as aerospace, power systems, robotics, and autonomous vehicles. Traditional estimators, including the Kalman Filter (KF) and its variants, provide physically interpretable residuals for fault detection but often fail to deliver reliable performance under nonlinear dynamics, modeling uncertainties, sensor faults, and non-Gaussian noise. This paper presents a comprehensive review of state estimation-based FDD approaches, with a particular focus on Artificial Intelligence (AI)-augmented Kalman filtering and hybrid frameworks that integrate Machine Learning (ML) models, including Neural Networks (NNs), Support Vector Machines (SVMs), and Gaussian Processes (GPs), with classical estimation theory. The review systematically evaluates model-based, data-driven, and hybrid methods, comparing their robustness, accuracy, computational efficiency, scalability, and interpretability in complex Cyber-Physical Systems (CPSs). Furthermore, emerging trends and open research challenges are identified, including online adaptation, fault-tolerant estimation, sensor fusion, explainable artificial intelligence (XAI), and deployment in Industry 4.0 and Internet of Things (IoT)-enabled environments. By bridging classical estimation theory with modern AI techniques, this review provides a roadmap for designing intelligent, adaptive, and resilient FDD systems capable of enhancing reliability, operational safety, and real-world applicability. Full article

Rapid urbanization has increased demand for safe and reliable energy infrastructure, with Liquefied Petroleum Gas (LPG) emerging as an important clean cooking fuel. In Nairobi, Kenya, the siting of LPG refill stations is critical to minimizing safety risks and supporting sustainable urban development. This study applied a GIS-based Multi-Criteria Decision Analysis (MCDA) framework to evaluate LPG station suitability by integrating land use, elevation, slope, geology, soil texture, and regulatory constraints. Two approaches were compared: a Boolean-only overlay model and a hybrid weighted overlay–Boolean model incorporating Analytic Hierarchy Process (AHP)-derived weights. The Boolean model produced an overly restrictive outcome, identifying no feasible locations under the combined exclusion criteria. In contrast, the hybrid model excluded 91.7% of the study area and identified 2779 potential candidate locations distributed across suitability classes. AHP results indicated that land-use compatibility and LPG proximity were the most influential criteria in determining suitability. Comparison with existing LPG stations revealed a spatial mismatch, with most facilities located in less suitable or unsuitable areas. The findings demonstrate that while Boolean approaches strictly enforce all constraints, hybrid GIS–MCDA models provide a more flexible and spatially differentiated basis for LPG infrastructure planning in rapidly growing urban environments. Full article

The complex, heterogeneous nature of many subsurface environments makes accurate Rate of Penetration (ROP) prediction both critical and challenging for achieving drilling efficiency, cost control, and operational safety. Although artificial intelligence has demonstrated strong potential in extracting nonlinear patterns from drilling and well-log data, its application to heterogeneous formations remains limited by: (i) overreliance on operational parameters that lack formation-physics context, (ii) rigid train–test splits that ignore geological variability, and (iii) heuristic hyperparameter selection practices that are not reproducible. This study presents a geomechanically augmented deep learning framework applied to two vertical wells in a Middle East carbonate-clastic field (Well A: 9375 records, 1000–3370 m; Well B: 4443 records, 1945–3131 m). Five contributions are introduced: (1) a physics-informed input space integrating lithology-specific geomechanical properties (UCS, CCS, Young’s modulus, shear modulus, friction angle), validated against core measurements (R² = 0.79–0.95); (2) a heterogeneity-adaptive train–test partitioning strategy demonstrating that formation complexity, rather than a fixed universal ratio, governs the optimal split; (3) a residual Fully Connected Neural Network (FCNN) with Swish activation and systematic hyperparameter sensitivity analysis; (4) a rigorous preprocessing pipeline comprising 99th-percentile Winsorization, interaction-term feature engineering (WOB × CCS, RPM × UCS), Lasso selection, Z-score normalization, and Gaussian noise augmentation, with all transforms fitted exclusively on training data to prevent leakage; and (5) a hybrid LSTM-FCNN that processes depth-ordered sequences via Savitzky–Golay denoising and a ten-step sliding window. The standalone FCNN achieved R² = 0.8641 (Well A) and R² = 0.9062 (Well B). The LSTM-FCNN improved intra-well accuracy to R² = 0.9877 and R² = 0.9551 and resolved a severe cross-well transfer asymmetry (B → A: R² = 0.0388 for FCNN versus R² = 0.8217 for LSTM-FCNN; A → B: R² = 0.8963), confirming that depth-sequential modeling captures transferable formation patterns across contrasting lithological profiles. Full article

Snow removal vehicles operate under severe working conditions, and the snowplow mounting frame is a critical structural component responsible for transmitting loads generated during snow-removal operations. To improve material utilization and reduce structural weight without compromising mechanical performance, a lightweight design methodology based on topology optimization was developed. The primary design objective was to achieve at least a 16% reduction in structural mass while maintaining acceptable stress, strain, deformation, and durability performance. First, a three-dimensional model of the mounting frame assembly was established, and finite element analysis was conducted using ANSYS under representative loading conditions. Topology optimization based on compliance minimization with a mass constraint was then performed to identify structurally inefficient regions and generate an optimized material distribution. Based on the optimization results, the mounting frame was reconstructed into a practical and manufacturable CAD model and subsequently re-evaluated through finite element analysis and fatigue assessment. The mass of the mounting frame was successfully reduced from 177.52 kg to 137.77 kg, corresponding to a weight reduction of 22.39%, significantly exceeding the initial design target. Despite this substantial reduction in weight, the maximum stress, strain, and deformation remained within allowable design limits. Furthermore, fatigue analysis predicted no fatigue failure within 1 × 10⁶ loading cycles, while the minimum fatigue safety factor remained greater than unity, confirming the durability and reliability of the redesigned structure. The results demonstrate that topology optimization provides an effective approach for improving material utilization, reducing structural weight, and enhancing the overall structural efficiency of snow-removal equipment. The successful reconstruction of the optimized topology into a manufacturable design further highlights the practical industrial applicability of the proposed methodology. Full article

As urbanization accelerates in China, existing multi-story residential buildings constructed between 1980 and 2000 face increasing fire risks due to high occupant density and outdated fire safety codes. This study develops a multi-factor coupling simulation framework integrating BIM, PyroSim (2020), and Pathfinder (2020) to evaluate fire evacuation safety. Results suggest that kitchens located farther from stairwell entrances tend to impose greater smoke temperature and visibility hazards. Alternating evacuations may outperform uniform platform-based strategies. Concentrating slow-moving occupants on lower floors may improve evacuation efficiency, while counterflow and returning behaviors tend to cause the greatest obstruction on middle floors (5th–7th stories). Multi-factor coupling analysis indicates nonlinear thresholds: maximum safe occupancy decreases from 6.0 to below 4.0 persons per household as building height increases from seven to nine stories; exit widths beyond 0.95 m yield diminishing returns; and critical stairwell obstacle sizes decrease from 0.6 m to 0.3 m as household density increases. Three retrofit strategies were examined: adding outdoor stairs achieved a safety margin of 71.2 s; adding evacuation platforms raised safe occupancy from 3.5 to 4.5 persons per household; and installing kitchen sprinklers reduced the smoke concentration in stairwells. These findings may provide a useful reference for fire safety retrofitting in existing multi-story residential buildings. Full article

Ni–Co γ/γ′-strengthened superalloys are key structural materials for modern energy and flow turbomachinery systems due to their exceptional high-temperature strength, creep resistance, as well as hydrogen and corrosion stability. However, operation in gaseous hydrogen environments typical of hydrogen-cooled generators, cooled gas-turbine blades, and emerging hydrogen-energy technologies can significantly affect their microstructural stability and fracture behavior. This study presents a comprehensive multiscale review of hydrogen-induced nanoscale degradation and crack initiation mechanisms in Ni–Co superalloys produced by wrought, powder metallurgy, and additive manufacturing routes. Transmission electron microscopy combined with quantitative morphometric analysis was employed to characterize the size, morphology, and spatial distribution of γ′ precipitates, revealing a dense population of coherent particles predominantly in the 40–120 nm range, governed by a log-normal distribution. Correlations between precipitate size, aspect ratio, and circularity indicate the onset of partial loss of coherency and coarsening for particles exceeding ~80 nm, creating favorable sites for hydrogen localization. The presence of TCP phases (η, σ, μ, Laves) and carbides at grain boundaries and within grains was shown to enhance microstructural heterogeneity and act as effective hydrogen traps, promoting interfacial decohesion and microcrack initiation. To support microstructural interpretation, convolutional neural network analysis with Grad-CAM visualization was applied to SEM images, enabling the identification of the structural regions most sensitive to hydrogen-assisted damage, particularly γ/γ′ interfaces and defect clusters. The results demonstrate that hydrogen-induced degradation in Ni–Co superalloys is governed by the coupled interactions among microstructure, hydrogen distribution, and local stress state. The findings provide a physically grounded basis for optimizing alloy chemistry, heat treatment, and additive manufacturing parameters, as well as for developing AI-assisted predictive models for the durability of critical components in hydrogen-energy and high-temperature power-generation systems to increase hydrogen safety. Full article

Skin diseases represent a growing global health challenge and continue to stimulate interest in safe, sustainable, and evidence-based dermatological interventions. In the present review, Cabo Verde is used as an ethnobotanical and biogeographical framework rather than as a source of strictly endemic dermatological plants. We focused on selected edible plant species occurring in and utilized throughout Cabo Verde, including native, naturalized, and cultivated taxa that are integrated into local food systems and traditional healthcare practices. Species were included only when they fulfilled the following criteria: a documented occurrence in Cabo Verde, recognized edible use, available phytochemical characterization, and at least one peer-reviewed study reporting dermatologically relevant biological activity. Literature identified through structured searches of PubMed, Scopus, and Web of Science were critically evaluated, with emphasis placed on phytochemistry, biological activity, safety considerations, evidence level, and translational relevance. The reviewed species, mainly from the genera Psidium, Syzygium, Eugenia, Artocarpus, Ficus, Morus, and Passiflora, have been associated with wound-healing, anti-inflammatory, antioxidant, antimicrobial, photoprotective, anti-aging, and skin-regenerative effects. Nevertheless, the available evidence remains dominated by in vitro and animal studies, whereas controlled human investigations are scarce. Accordingly, these species should be regarded as promising sources of dermatologically relevant compounds rather than as clinically validated dermatological therapies. Full article

Robust monocular distance estimation under varying illumination conditions is critical for autonomous driving safety. While state-of-the-art monocular 3D detection models achieve high accuracy in daylight conditions, they rely on computationally heavy architectures and degrade significantly in low-light environments. Lightweight 2D detectors (e.g., YOLO variants) offer real-time performance but lack the geometric constraints required for accurate depth estimation. To address this limitation, we propose the Anisotropic Geometry Loss (AGL) framework. This lightweight framework enforces ground-plane consistency through an anisotropic bottom-edge constraint derived from the pinhole camera model. In addition, a luminance-channel contrast enhancement module (CLAHE) is applied at inference to improve low-light visibility. Experimental results on the Dark-KITTI dataset show that the proposed method achieves an RMSE of 10.91 ± 0.68 m, improving over YOLOv10n (11.53 ± 0.56 m) and YOLOv26n (11.99 ± 0.58 m), while maintaining a 2.71 M-parameter footprint and real-time inference (>160 FPS). With CLAHE, RMSE is further reduced to 10.55 ± 0.72 m. Stratified by kinematic safety zone, the proposed method achieves 2.42 ± 0.03 m in the Near range (0–15 m), 5.94 ± 0.19 m in the Medium range (15–30 m), and 17.41 ± 1.25 m in the Far range (>30 m), corresponding to Euro NCAP AEB (Autonomous Emergency Braking) stopping distances. AGL provides its largest measurable accuracy improvement in the medium-distance range while maintaining comparable performance in the far-distance range. A complementary luminance-channel CLAHE preprocessor recovers bottom-edge gradients in synthetic and real low-light frames; zero-shot generalization is qualitatively corroborated on the ExDark dataset. These results demonstrate that explicit geometric constraints provide an effective and efficient solution for robust cross-illumination resistance in monocular distance estimation. The framework also shows practical potential for camera-only AEB systems deployed on edge-computing platforms aligned with Euro NCAP safety protocols. Full article

Battery pack fires remain a critical safety concern for lithium-ion battery systems. This study presents a comprehensive application of Fault Tree Analysis (FTA) to identify and structure the sequences of failures that may lead to a battery pack fire. A detailed fault tree is developed for a cell–module–pack architecture equipped with a thermal management system, enabling a clear representation of failure pathways. The analysis highlights four main origins of battery pack fire. Each intermediate scenario is described through dedicated branches of the fault tree to enhance clarity and facilitate its adoption for other battery pack designs and use-cases. As most failure modes involved in battery pack fire do not have reliable probability data available or exhibit strong dependency on usage conditions, a fuzzy logic-based expert approach is employed. Probabilistic data are collected through a questionnaire, allowing the assignment of probabilities to undocumented failure events. A quantified use-case is presented for an electric vehicle, illustrating the practical application of the methodology. The objective of this work is to demonstrate a structured and adaptable methodology for applying FTA to lithium-ion battery pack fire risk analysis. The resulting fault tree, provided as open-access supplementary material, aims to support safety analysis, highlight critical protection failures, and identify current limitations in battery pack safety systems. It can also help identify critical components in order to support the development of rapid and targeted diagnostic strategies for battery packs throughout their lifetime. Full article

Electric power systems are expanding toward higher voltage levels, larger renewable-energy bases, denser urban substations, and increasingly complex transmission corridors. These trends make inspection more frequent and more demanding, while conventional manual patrols and single-robot deployments remain constrained by safety risks, limited coverage, endurance, and fragmented situational awareness. Multi-robot systems offer a promising pathway for electric power inspection by combining heterogeneous platforms, distributed sensing, coordinated planning, and human-supervised autonomy. This review synthesizes recent progress in multi-robot inspection for power transmission lines, substations, distribution networks, and related grid assets, with particular attention to transmission corridors and substations where heterogeneous cooperation is operationally valuable. Following a Sense–Think–Act framework, we organize the literature into three interconnected components: cooperative perception for spatial and semantic understanding of grid assets; collaborative planning and task allocation for large-scale, risk-aware inspection; and coordinated execution with human oversight in safety-critical, often energized environments. We highlight how unmanned aerial vehicles (UAVs), unmanned ground vehicles (UGVs), climbing robots, and fixed robotic stations can complement one another in inspection workflows, from wide-area patrol and defect localization to close-range verification and maintenance support. We also discuss persistent challenges, including electromagnetic compatibility, reliable localization near metallic structures, multimodal data fusion, battery endurance, communication robustness, minimum approach distances, cybersecurity, benchmark scarcity, and the need for assurance mechanisms that allow operators to understand, trust, and intervene in multi-robot decisions. Finally, we outline a roadmap for moving from isolated demonstrations toward deployable, human-centered, and grid-integrated multi-robot inspection systems. Full article