Search Results (6,935)

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

Lane detection is a critical component of autonomous driving systems, requiring both high accuracy and real-time performance under complex driving scenarios. Unlike current methods that rely on predefined lane counts, instance segmentation methods can handle an arbitrary number of lanes, making them more adaptable in real-world applications. However, this flexibility typically relies on dense pixel-level predictions, which necessitate large-scale networks and result in prohibitively high computational costs, hindering deployment on embedded platforms. To address these challenges, we present Fast-CenLaneNet, a lightweight architecture that improves inference efficiency while maintaining detection accuracy. Specifically, we design a lightweight backbone to reduce model parameters and computational cost, propose a learnable spatial similarity attention module to capture spatial dependencies within lane regions and enhance feature discriminability, and construct multi-branch output heads with Ghost convolutions to refine lane-related features with low computational overhead. Experiments on the TuSimple and CULane benchmarks demonstrate that Fast-CenLaneNet achieves a favorable accuracy–efficiency trade-off. On TuSimple, Fast-CenLaneNet obtains 96.40 ± 0.06% accuracy and 162.7 ± 6.8 FPS with 4.7 M parameters and 9.9 GFLOPs. Compared with CenLaneNet, it reduces the number of parameters by 89.1% and improves forward inference speed by 107.5%, with an accuracy decrease of only 0.08 percentage points. Full article

In 3D integrated circuits, a placement decision that looks acceptable from a 2D wirelength view can still create a local thermal or stress problem after stacking. This issue becomes more visible as the number of tiers and the density of vertical interconnects increase. We propose ThermIC, a placement framework that brings thermal and mechanical risk estimates into the placement loop rather than treating them only as post-layout checks. The novelty of ThermIC does not lie in treating graph neural networks, reinforcement learning, uncertainty-aware learning, or physics-informed regularization as individually new techniques. Instead, ThermIC contributes a placement-time coupling mechanism in which physically typed graph propagation, dense multi-constraint risk prediction, and action-level reinforcement learning feedback are jointly organized for stacked 3D-IC placement. ThermIC uses a heterogeneous graph encoder to carry thermal, stress, timing, and congestion information through the netlist; a constraint head to estimate local hotspot, stress-risk, timing-violation, and congestion probabilities; and a sequential placement policy trained with physics-informed penalties. We evaluate the method on ThermIC-Bench, a simulated corpus with more than 30,000 finite-element samples from 18 heterogeneous 3D-IC designs with 4–8 tiers. Because the present study does not include proprietary industrial circuits, silicon measurements, or a tape-out case, the experimental results are interpreted as simulation-based benchmark evidence rather than final industrial qualification. ThermIC connects the heat-kernel branch to the discretized heat-conduction equation and the stress-filter branch to linear thermo-elastic equilibrium, providing a mechanism-level basis for physical interpretability. The analysis distinguishes offline simulation/training cost from online deployment cost and reports complexity, runtime, and memory scaling for practical large-scale use. Under joint DRC, thermo-mechanical stress, and thermally coupled timing checks, ThermIC obtains an $82.1\%$ physical verification pass rate. The peak-temperature error is $3.1$ °C, the hotspot localization IoU is 0.89, and the number of placement-closure iterations is reduced by $3.7\times$ relative to the heuristic baseline. Together, these benchmark results indicate that early, differentiable multi-physics feedback can make 3D placement less dependent on late correction cycles. Full article

Industrial Internet of Things (IIoT) networks require continuous, uninterrupted sensing operations despite the finite battery capacity of deployed IoT nodes. Conventional reactive energy management, where nodes switch to charging mode only after residual energy falls below a fixed threshold, cannot prevent depletion events and compromises network uptime. We propose a digital twin (DT)-enabled predictive scheduling framework in which a DT layer co-located with a multi-access edge computing (MEC) control center continuously mirrors the physical network state and generates H-slot look-ahead scheduling decisions before depletion can occur. The framework operates over a 5G network-sliced infrastructure with dedicated URLLC, eMBB, and mMTC slices. Two coupled integer programming problems are formulated, namely a predictive IoT node scheduling problem and a predictive energy transmitter scheduling problem. Optimal solutions are obtained via branch-and-bound with reliability branching (DT-PBB), and a low-complexity DT-Aware Greedy Priority Heuristic (DT-GPH) is also proposed. Evaluated against Earliest-Deadline-First (EDF-WPT), No-WPT (a baseline that disables wireless charging entirely), and Random baselines across three parameter configurations with K up to 200 nodes, DT-PBB achieves the highest sensing utility and the fewest energy depletion events in all scenarios. DT-GPH provides near-optimal depletion performance at substantially lower computation cost. EDF-WPT, the strongest reactive policy, incurs 2-4 times more depletion events than DT-PBB. Proactive DT-enabled look-ahead decisively outperforms reactive urgency-based scheduling, validating the zero-downtime paradigm for large-scale IIoT networks. Full article

With the emergence of data-intensive computing, which is due to the growth of the data produced and generated each day, it became necessary to store and manage big data. Cloud data storage is actually the best choice for large distributed systems. Successful Cloud Computing cannot be achieved without a reliable data-management system to store and handle the enormous volume of data. Management of the available storage system at large scale becomes progressively more complicated, and we face many challenges, such as scalability, data availability, fault tolerance, etc. Also, data storage is faced with specific access patterns: highly concurrent reads of data from the same file, many overwrites, and very concurrent appends to the same file. Most of the existing storage systems use versioning to bring and enhance data access parallelism and this enables better performance levels under concurrency; but, generally, these systems use one component (version manager), which is responsible for generating new versions of each file stored. When we speak in the context of big data, the requests for read, write and append increase. If these requests are managed by a single component, then we have a performance bottleneck and an overloaded version manager. To avoid this drawback, we proposed and designed a new architecture of storage systems that uses versioning; the new architecture uses multi-version managers to support better the scalability and provide partial fault tolerance. To illustrate the practicability of our approach, we assessed it on the BlobSeer data-management system. The experimental results demonstrate that our architecture achieves near-linear scalability for CREATE operations (495 ops/sec per additional version manager), reduces WRITE execution time by up to 66%, and maintains 67% availability under single-node failures, all while introducing minimal resource overhead (3% aggregate CPU increase). These results confirm that the proposed multi-version manager architecture offers a practical, scalable, and partially fault-tolerant solution for Cloud data-storage systems. Full article

The paper suggests a distributed cross-layer IoT architecture that combines LoRaWAN (Long Range Wide Area Network) with federated learning (FL) to improve reliability, scalability, and fault tolerance in multi-layer vertical farming systems in dense and dynamic environments. Unlike the traditional frameworks that rely on independent measures of QoS (Quality of Service), the proposed framework directly represents the inter-layer relationships, such as heterogeneity of latencies, robustness of connectivity, and propagation of faults. One of the contributions is the development of a cohesive cross-layer evaluation framework with six strictly defined metrics: MLDC (Multi-Layer Deployment Capacity), C-LCRI (Cross-Layer Connectivity Robustness Index), C-LFCI (Cross-Layer Fault Containment Index), SART (Smart Adaptive Recovery Time), and AIRSM (AI Resilience Score Metric), which allows for quantitatively characterizing latency differences, network resilience, fault containment, recovery efficiency, AI robustness, and energy-performance trade-offs. The experimental results show that the proposed Smart Distributed LoRaWAN–Federated Learning architecture operates reliably in high-density and multi-layer vertical farming environments, and is scalable to handle larger amounts of data. The proposed system guarantees a packet delivery ratio (PDR) of around 95% under a large-scale deployment with up to 1050 IoT nodes spread across seven cultivation layers, with a latency reduction of nearly 60%, less than 1.6 J/msg on average energy consumption, and a fault recovery time of less than 0.3 s in case of network disruptions. The proposed framework was validated using large-scale simulation scenarios developed based on experimentally reported LoRaWAN communication characteristics and agricultural IoT deployments, and operational conditions at the edge intelligence. This evaluation included up to 1050 sensing nodes in 7 vertical farming layers to approximate a realistic deployment of smart farming in a large-scale environment while keeping consistency with the recorded communication and reliability profile. Full article

Marine oil spills pose serious threats to coastal ecosystems and maritime activities, and synthetic aperture radar (SAR) has become an important tool for all-weather marine monitoring. However, SAR oil spill detection remains challenging because oil spills usually appear as weak dark anomalies with blurred boundaries, elongated or fragmented shapes, and strong interference from lookalike phenomena such as low-wind areas and internal waves. To address these issues, we propose RGCNet, a lightweight radiometric–geometric–contextual detection framework based on YOLOv11n. Firstly, the H_SPDRFF module is incorporated into the backbone to enhance weak radiometric responses through constrained feature amplification, thereby reducing missed detections caused by low-contrast oil slicks. Secondly, the C3k2_GSR module is designed in the neck to strengthen anisotropic geometric refinement and preserve the continuity of elongated and fragmented oil spill regions during multi-scale feature fusion. Finally, a SAR-adapted large selective kernel block (LSKBlock) is embedded in the high-level backbone to improve contextual discrimination between true oil spills and lookalike dark formations. Experiments on DeepSAR show that RGCNet increases mAP@0.5 and mAP@0.5:0.95 by 3.6 and 3.0 percentage points over the YOLOv11n baseline, respectively. Cross-dataset evaluation on SAR-Oil-Spill demonstrates a 3.9-point mAP@0.5 gain, indicating strong transferability. Furthermore, with a compact model size of 2.67 M parameters and 6.4 G FLOPs, RGCNet achieves an inference speed of 162.5 FPS on an RTX A4000 GPU, demonstrating its efficiency and potential for real-time maritime surveillance. Nevertheless, the current bounding-box formulation cannot precisely delineate irregular oil-spill boundaries. Future work will therefore investigate fine-grained segmentation and cross-sensor adaptation. Full article

To address the challenges in multi-scale defect detection on railway track surfaces—such as the high likelihood of missing tiny defects, weak anti-interference capability in complex environments, and poor scale adaptability—this paper proposes a WTConv-YOLOv11 detection model based on wavelet convolution and scale dynamic loss, specifically tailored for embedded scenarios in intelligent inspection robots. By embedding a wavelet convolution module, the model leverages multi-frequency decomposition characteristics to enhance multi-scale defect feature extraction, effectively compensating for the shortcomings of traditional convolution in detail extraction and limited receptive fields. Meanwhile, a Scale Dynamic Loss (SD Loss) function is introduced to adaptively adjust regression weights according to defect scales, significantly reducing multi-scale target localization deviations and Intersection over Union (IoU) fluctuations. Experiments conducted on a real-world railway dataset comprising 2396 track defect images demonstrate that the proposed model achieves mean Average Precision (mAP)@0.5 of 82.56%, which is 12.16 percentage points higher than the original YOLOv11. With an inference speed of 99 FPS, the model balances high accuracy with real-time performance. Real-world testing further verifies the model’s robustness under strong light, shadows, and water stains, providing effective technical support for intelligent unmanned railway inspection. Full article

The premature fracture failure of polycrystalline α-Fe poses lots of hidden safety problems due to hydrogen absorption during human activities. A key challenge for the failure process is understanding the effects of hydrogen on grain boundaries (GBs). The study here demonstrates that the rapid diffusion of hydrogen leads to the formation of hydrogen-induced defects in a very short time. Specifically, hydrogen segregation results in void formation and even aggregation at GBs, which plays a critical role in crack initiation and propagation. The mechanical response of GBs with varying hydrogen levels is investigated using large-scale molecular dynamics (MD) simulations. The analysis shows that hydrogen increases the yield stress, thereby inhibiting dislocation emission from GBs. Additionally, GB damage alters the fracture mode from a mix of intergranular and intragranular fracture without hydrogen to a fully intergranular fracture with multi-site crack nucleation at high hydrogen concentrations (e.g., C_h = 3 at.%). This shift is driven by hydrogen-induced void formation at GBs and hydrogen’s rapid diffusion, which accelerates crack propagation along the grain boundaries. Full article

The steel–concrete interface in steel–concrete composite structures is susceptible to interfacial void defects during both casting and service, posing a significant threat to structural load-bearing capacity. For early-stage micro-voids exceeding 2 mm in height, signal variations are weak and exhibit response characteristics similar to dense states, leading to feature ambiguity when using conventional criteria based on time-domain amplitude and attenuation or frequency-domain peak values and resulting in a high risk of missed detections. To address this limitation for early warning purposes, this study proposes a high-sensitivity identification method integrating an impact elastic wave response feature system with a feature-attention gated multi-layer perceptron (Feature-attention MLP). Based on full-scale model experiments from an engineering project, the temporal and spectral evolution patterns of impact elastic wave responses under varying dense conditions were analyzed. A comprehensive feature system, including time-domain statistical descriptors, spectral peaks, and sub-band energy distributions, was constructed, with Random Forest used for feature importance ranking and Top-K selection. An MLP classifier was then developed for automatic discrimination of dense states. A feature-level attention gating mechanism was introduced to enable adaptive weighting across feature dimensions, enhancing sensitive features while suppressing noise and structural variability. The final lightweight classifier contains 4052 trainable parameters, enabling rapid execution with an average CPU inference time of approximately 1.24 ms per sample. The average CPU inference time was approximately 1.24 ms per sample. Under the original train–validation split, the recall-prioritized operating point achieved a Void recall of 0.978 and a weighted F1-score of 0.780, accompanied by a non-negligible false-positive screening burden. Stratified five-fold internal validation yielded a balanced accuracy of 0.682 ± 0.021 and a Void recall of 0.845 ± 0.035 under the inner-validation-optimized threshold. These results demonstrate the preliminary potential of the proposed lightweight framework for engineering-oriented micro-void screening under the investigated full-scale conditions. Full article

Vehicle theft and vandalism remain significant urban security challenges commonly addressed through reactive, post-incident forensic measures. This paper proposes a proactive, real-time computer vision system designed to detect potentially suspicious behavior around parked vehicles, with a specific focus on unauthorized proximity and loitering. The proposed architecture integrates state-of-the-art object detection using YOLOv11 (You Only Look Once version 11), multi-object tracking via a lightweight custom association tracker inspired by the ByteTrack/StrongSORT/OC-SORT paradigm, and monocular depth estimation based on the Intel DPT-Large framework.A key contribution is the identification and mitigation of the Perspective Challenge: the two-dimensional (2D) scale ambiguity that causes distant background pedestrians to appear falsely proximate to foreground vehicles in monocular camera feeds. To address this, three spatial analysis strategies are implemented and evaluated: (A) fixed Euclidean thresholding, (B) adaptive perspective thresholding, and (C) three-dimensional (3D) depth injection. Experimental results on real-world urban surveillance footage (27,000 annotated frames across two datasets) demonstrate that Strategy C achieves the highest precision (0.95) with an F1-score of 0.92, while Strategy B provides the best balance between accuracy (precision 0.88, recall 0.91, F1 0.89) and computational efficiency (32.7 frames per second, FPS). Compared to naive 2D thresholding (Strategy A), Strategy B reduces false alarms by approximately 80%, while Strategy C further improves precision to 0.95 through depth-plane verification. The system maintains real-time performance exceeding 30 FPS under Strategy B, making it a strong candidate for practical urban vehicle monitoring, subject to further large-scale validation across diverse environments. Full article

This paper investigates secure self-triggered time-varying formation control for quadrotor swarm systems against sequential multi-link scaling attacks, which can be implemented in a self-triggered and fully distributed manner. Firstly, based on the outer-loop position and velocity control model of quadrotors, a fully distributed secure time-varying formation control protocol is constructed under sequential multi-link scaling attacks with three characteristics: distributed, sequential, and scalable, and the design criteria for fully distributed secure time-varying formation control are provided. Then, combining the inner and outer-loop control principles of quadrotors, by constructing Euler angle loop controllers and angular velocity controllers, the conversion of the control input of the outer-loop position and velocity to the inner-loop attitude control is achieved, and fully distributed secure time-varying formation control algorithms for quadrotor UAV swarm systems under attacks are proposed. Finally, the effectiveness and applicability of the fully distributed secure consensus method in the formation control of quadrotor UAV swarms is verified through flight experiments using a quadrotor UAV swarm flight test platform. The research results provide a useful reference for the practical application of the fully distributed secure cooperative control theory. Full article

Detecting small targets in UAV aerial imagery is inherently difficult because these objects occupy only a small number of pixels and are highly susceptible to cluttered backgrounds, dense spatial arrangements, and pronounced scale variation. To address this problem, we propose CASA-Net (Context-Aware Small-object Adaptation Network), a context-aware detector built on a [d=R2]YOLOv26sYOLOv26 baseline with three coordinated improvements: an Enhanced Small-Target-Aware Label Assignment mechanism for stronger supervision of tiny instances, a Multi-scale Feature Enhancement Module for richer contextual representation and spatial discrimination, and an aerial-specific augmentation pipeline for improved robustness to viewpoint, scale, and motion blur. Experiments on the VisDrone and RSOD benchmarks demonstrate that CASA-Net consistently outperforms the baseline and competing methods. On VisDrone, it achieves 47.0% mAP${}_{0.5}$ and 25.2% small-object mAP${}_{0.5}$, while on RSOD it reaches 78.3% mAP${}_{0.5}$. In addition, the model achieves real-time inference speeds above 100 FPS on both datasets using an RTX 3090, with 13.9 M parameters and 26.2 GFLOPs. Taken together, these findings show that CASA-Net is an accurate and efficient framework for UAV small-object detection through the joint improvement of supervision, feature representation, and data adaptation. Full article

The large-scale integration of wind and solar power has significantly intensified peak-shaving pressure and operational risk in provincial power grids. Effectively leveraging the flexible regulation capability of hydropower to mitigate the uncertainty of wind and solar output is a promising approach to enhancing grid security and stability. To simultaneously improve the peak-shaving performance and risk resilience of hydro-wind-solar systems for a provincial power grid, this paper proposes a multi-objective short-term scheduling model that jointly minimizes the peak value of net load and the Conditional Value-at-Risk (CVaR) of flexibility shortage. Specifically, the residual peak load is used to quantify the system’s peak-shaving burden, while the average CVaR of upward/downward ramping deficits across all time periods characterizes the tail risk associated with insufficient flexibility. Historical wind and solar forecast error data are employed to generate representative uncertainty scenarios via Gaussian mixture model, and the Rockafellar–Uryasev formulation is adopted to accurately embed CVaR into a mixed-integer linear programming (MILP) framework. Furthermore, the normalized normal constraint (NNC) method is introduced to compute a well-distributed Pareto front. Numerical simulations based on a real-world hydro-wind-solar system in a provincial grid in Southwest China demonstrate that the proposed model can significantly reduce the peak load while effectively mitigating flexibility shortfall risk. The resulting Pareto front clearly reveals the trade-off between peak-shaving effectiveness and risk control, providing a scientific basis for day-ahead generation scheduling and coordinated dispatch of flexible resources. Full article

Unmanned aerial vehicles (UAVs) are increasingly being used for early wildfire monitoring in remote areas, but UAV endurance is fundamentally constrained by the battery capacity. This work presents an energy-aware edge-vision framework for UAV fire detection that jointly models neural inference and wireless communication and optimizes the operating point of the complete onboard pipeline. Five you only look once (YOLO)v5 scales were fine-tuned on a YOLO-formatted version of the FLAME aerial fire dataset, which was extended with multi-frame fire tracking to enable event-level evaluations. We jointly optimized the model scale, detection confidence threshold, and inference stride using theoretical and empirical estimators that balance energy consumption against the probability of detecting fire events. The results showed that compact YOLOv5 models provide the best trade-off between energy and accuracy for this UAV application: larger variants increase the inference cost without consistent recall gains on the evaluated dataset. In addition, temporal subsampling reduces the total energy approximately in proportion to the stride while preserving near-perfect event-level detection for fires of a moderate duration. The optimized configuration lowers energy consumption by up to 4.4 times with only a 0.03% reduction in recall, supporting longer-endurance UAV missions for wildfire monitoring. Full article