Search Results (4,460)

Accurate depth image inpainting in complex urban environments remains a critical challenge due to occlusions, reflections, and sensor limitations, which often result in significant data loss. We propose a hybrid deep learning framework that explicitly combines local and global modelling through Convolutional Neural Networks (CNNs) and Transformer modules. The model employs a multi-branch parallel architecture, where the CNN branch captures fine-grained local textures and edges, while the Transformer branch models global semantic structures and long-range dependencies. We introduce an optimized attention mechanism, Agent Attention, which differs from existing efficient/linear attention methods by using learnable proxy tokens tailored for urban scene categories (e.g., façades, sky, ground). A content-guided dynamic fusion module adaptively combines multi-scale features to enhance structural alignment and texture recovery. The frame-work is trained with a composite loss function incorporating pixel accuracy, perceptual similarity, adversarial realism, and structural consistency. Extensive experiments on the Paris StreetView dataset demonstrate that the proposed method achieves state-of-the-art performance, outperforming existing approaches in PSNR, SSIM, and LPIPS metrics. The study highlights the potential of multi-scale modeling for urban depth inpainting and discusses challenges in real-world deployment, ethical considerations, and future directions for multimodal integration. Full article

Current drone navigation systems primarily rely on Global Navigation Satellite Systems (GNSSs), but their signals are susceptible to interference, spoofing, or suppression in complex environments, leading to degraded positioning performance or even failure. To enhance the positioning accuracy and robustness of low-altitude drones in satellite-denied environments, this paper investigates an absolute visual localization solution. This method achieves precise localization by matching real-time images with reference images that have absolute position information. To address the issue of insufficient feature generalization capability due to the complex and variable nature of ground scenes, a visual-based image retrieval algorithm is proposed, which utilizes a fusion of shallow spatial features and deep semantic features, combined with generalized average pooling to enhance feature representation capabilities. To tackle the registration errors caused by differences in perspective and scale between images, an image registration algorithm based on cyclic consistency matching is designed, incorporating a reprojection error loss function, a multi-scale feature fusion mechanism, and a structural reparameterization strategy to improve matching accuracy and inference efficiency. Based on the above methods, a hierarchical absolute visual localization system is constructed, achieving coarse localization through image retrieval and fine localization through image registration, while also integrating IMU prior correction and a sliding window update strategy to mitigate the effects of scale and rotation differences. The system is implemented on the ROS platform and experimentally validated in a real-world environment. The results show that the localization success rates for the h, s, v, and w trajectories are 95.02%, 64.50%, 64.84%, and 91.09%, respectively. Compared to similar algorithms, it demonstrates higher accuracy and better adaptability to complex scenarios. These results indicate that the proposed technology can achieve high-precision and robust absolute visual localization without the need for initial conditions, highlighting its potential for application in GNSS-denied environments. Full article

Physics-Informed Neural Networks (PINNs) have emerged as a promising paradigm for solving partial differential equations (PDEs) by embedding physical laws into the learning process. However, standard PINNs often suffer from training instabilities and unbalanced optimization when handling multi-term loss functions, especially in problems involving singular perturbations, fractional operators, or multi-scale behaviors. To address these limitations, we propose a novel gradient variance weighting physics-informed neural network (GVW-PINN), which adaptively adjusts the loss weights based on the variance of gradient magnitudes during training. This mechanism balances the optimization dynamics across different loss terms, thereby enhancing both convergence stability and solution accuracy. We evaluate GVW-PINN on three representative PDE models and numerical experiments demonstrate that GVW-PINN consistently outperforms the conventional PINN in terms of training efficiency, loss convergence, and predictive accuracy. In particular, GVW-PINN achieves smoother and faster loss reduction, reduces relative errors by one to two orders of magnitude, and exhibits superior generalization to unseen domains. The proposed framework provides a robust and flexible strategy for applying PINNs to a wide range of integer- and fractional-order PDEs, highlighting its potential for advancing data-driven scientific computing in complex physical systems. Full article

Al-Zn-Mg-Cu alloys are widely used as heat-treatable ultra-high-strength materials in aerospace structural applications. While conventional single-stage aging enables high strength, advanced performance demands call for precise microstructural control via multi-stage aging. In this study, we employ a combination of scanning transmission electron microscopy (STEM), energy-dispersive X-ray spectroscopy (EDS), and X-ray diffraction (XRD) to investigate the microstructural evolution and its correlation with mechanical properties of AA7150 aluminum alloy subjected to two-step aging treatments, following a 6 h pre-aging at 120 °C. Through atomic-scale STEM imaging along the [110]_Al zone axis, we systematically characterize the precipitation behavior of GPII zones, η′ phases, and equilibrium η phases both within the grains and at grain boundaries under varying secondary aging (SA) conditions. Our results reveal that increasing the SA temperature from 140 °C to 180 °C leads to coarsening and reduced number density of intragranular precipitates, while promoting the continuous and coarse precipitation of η phases along grain boundaries, accompanied by a widening of the precipitation-free zone (PFZ). Notably, SA at 160 °C induces the formation of fine, uniformly dispersed nanoscale η′ precipitates in the alloy, as confirmed by XRD phase analysis. Aging at this temperature markedly enhances the mechanical properties, achieving an ultimate tensile strength (UTS) of 613 MPa and a yield strength (YS) of 598 MPa, while presenting an exceptionally broad peak-aging plateau. Owing to this feature, a moderate extension of the SA duration does not reduce strength and can further improve ductility, increasing the elongation (EL) to 14.26%. These results demonstrate a novel two-step heat-treatment strategy that simultaneously achieves ultra-high strength and excellent ductility, highlighting the critical role of advanced electron microscopy in elucidating phase-transformation pathways that inform microstructure-guided alloy design and processing. Full article

The applicability of the first-order Fermi mechanism—a cornerstone of the diffusive shock acceleration (DSA) model—in explaining the cosmic ray spectrum is reexamined in light of recent observations from the Magnetospheric Multiscale (MMS) mission at Earth’s bow shock. It is demonstrated that the Fermi and DSA mechanisms lack physical justification and should be replaced by the physically correct ballistic surfing acceleration (BSA) mechanism. The results show that cosmic rays are energized by the convection electric field during ballistic surfing upstream of quasi-perpendicular shocks, independently of internal shock processes. The spectral index of cosmic rays is determined by the magnetic field compression and shock geometry: the acceleration is strongest in perpendicular shocks and vanishes in parallel shocks. The BSA mechanism reproduces the observed spectral indices, with $s=-2.7$ below the knee at ${10}^{16}$ eV and $s=-3$ above it. It is suggested that the spectral knee may correspond to particles whose gyroradii are comparable to the characteristic size of shocks in supernova remnants. The acceleration time to reach the knee energy, as predicted by the BSA, is in the order of 500 years. Full article

Pipeline leak detection through acoustic signal measurement faces critical challenges, including insufficient utilization of time-frequency domain features, poor adaptability to noisy environments, and inadequate exploitation of frequency-domain prior knowledge in existing deep learning approaches. This paper proposes a Multi-Scale Frequency-Aware Transformer (MSFAT) architecture that integrates measurement-based acoustic signal analysis with artificial intelligence techniques. The MSFAT framework consists of four core components: a frequency-aware embedding layer that achieves joint representation learning of time-frequency dual-domain features through parallel temporal convolution and frequency transformation, a multi-head frequency attention mechanism that dynamically adjusts attention weights based on spectral distribution using frequency features as modulation signals, an adaptive noise filtering module that integrates noise detection, signal enhancement, and adaptive fusion functions through end-to-end joint optimization, and a multi-scale feature aggregation mechanism that extracts discriminative global representations through complementary pooling strategies. The proposed method addresses the fundamental limitations of traditional measurement-based detection systems by incorporating domain-specific prior knowledge into neural network architecture design. Experimental validation demonstrates that MSFAT achieves 97.2% accuracy and an F1-score, representing improvements of 10.5% and 10.9%, respectively, compared to standard Transformer approaches. The model maintains robust detection performance across signal-to-noise ratio conditions ranging from 5 to 30 dB, demonstrating superior adaptability to complex industrial measurement environments. Ablation studies confirm the effectiveness of each innovative module, with frequency-aware mechanisms contributing most significantly to the enhanced measurement precision and reliability in pipeline leak detection applications. Full article

Deicing salt effectively melts ice and snow to maintain traffic flow in seasonal freezing zones, but its erosion effect compromises the water stability and structural integrity of asphalt pavements. To comprehensively explore the impacts of salt erosion on the interfacial behaviors of rubber asphalt–aggregate systems, this study developed a multiscale characterization method integrating a macroscopic mechanical test, microscopic tests, and molecular dynamics (MD) simulations. Firstly, laboratory-controlled salt–freeze–thaw cycles were employed to simulate field conditions, followed by quantitative evaluation of interfacial bonding properties through pull-out tests. Subsequently, the atomic force microscopy (AFM) and Fourier transform infrared spectrometer (FTIR) tests were conducted to characterize the microscopic morphology evolution and chemical functional group transformations, respectively. Moreover, by combining the diffusion coefficients of water molecules, salt solution ions, and asphalt components, the mechanism of interfacial salt erosion was elucidated. The results demonstrate that increasing NaCl concentration and freeze–thaw cycles progressively reduces interfacial pull-out strength and fracture energy, with NaCl-induced damage becoming limited after twelve salt–freeze–thaw cycles. In detail, with exposure to 15 freeze–thaw cycles in 6% NaCl solution, the pull-out strength and fracture energy of the rubber asphalt–limestone aggregate decrease by 50.47% and 51.57%, respectively. At this stage, rubber asphalt exhibits 65.42% and 52.34% increases in carbonyl and sulfoxide indexes, respectively, contrasted by 49.24% and 42.5% decreases in aromatic and aliphatic indexes. Long-term exposure to salt–freeze–thaw conditions promotes phase homogenization, ultimately reducing surface roughness and causing rubber asphalt to resemble matrix asphalt morphologically. At the rubber asphalt–NaCl solution–aggregate interface, the diffusion of Na⁺ is faster than that of Cl⁻. Meanwhile, compared with other asphalt components, saturates exhibit notably enhanced mobility under salt erosion conditions. The synergistic effects of accelerated aging, salt crystallization pressure, and enhanced ionic diffusion jointly induce the deterioration of interfacial bonding, which accounts for the decrease in macroscopic pull-out strength. This multiscale investigation advances understanding of salt-induced deterioration while providing practical insights for developing durable asphalt mixtures in cold regions. Full article

Partition walls are widely used in engineering structures, and their thermomechanical performance has a significant influence on overall safety and durability. Under extreme conditions, such as high temperatures, these walls are subjected to complex thermal expansion, stress development, and deformation, which may compromise structural stability. Analyzing full-field deformation of parathion walls with high accuracy is a burden for classical fine-scale finite element methods. To address these challenges, this study applies a multiscale finite element method to investigate the coupled thermomechanical behavior of partition walls, providing a more computationally efficient alternative to conventional single-scale models. The method effectively captures thermal–mechanical interactions in walls composed of solid steel, porous steel, and composite plates. Numerical simulations confirm the accuracy and efficiency of the proposed approach, demonstrating its suitability for practical engineering applications. The results offer a reliable basis for optimizing partition wall design, improving energy performance, and ensuring structural integrity under demanding operating conditions. Full article

With the acceleration of global urbanization, polychlorinated dibenzo-p-dioxins/dibenzofurans (PCDD/Fs), as a by-product of solid waste incineration, have attracted more and more attention for their environmental pollution and health hazards. By describing the generation and transformation mechanism of PCDD/Fs, this review focuses on the methods to control the generation of PCDD/Fs and reduce their environmental pollution. Initially, the study analyzes the formation mechanisms of PCDD/Fs, and it emphasizes that variations in incineration conditions, feedstock compositions, and technological approaches substantially influence PCDD/F formation. Subsequently, the review examines existing PCDD/F control technologies—including optimization technology of high-temperature pyrolysis and incineration, photocatalytic degradation technology, supercritical water oxidation technology and biodegradation—and evaluates their respective advantages and limitations. The current challenges and future research directions, such as the development of novel monitoring technologies, the development of industry standards, and the enhancement of policy support, are finally presented. Effective PCDD/F control requires advanced real-time monitoring (e.g., AI-enhanced mass spectrometry), unified global standards, and policy support (e.g., subsidies, phased regulations). Future solutions lie in multiscale modeling, international collaboration, and adaptive technologies for sustainable risk reduction. Full article

Traditional mechanical processing techniques are confronted with significant challenges when machining advanced materials possessing excellent mechanical properties. Electrochemical machining (ECM), as a material removal technology based on the principle of anodic dissolution, demonstrates distinctive advantages including the absence of contact stress, independence from material hardness, and elimination of mechanical residual stress and recast layers. These characteristics render ECM particularly suitable for high-precision applications requiring superior surface quality. This review systematically summarizes the applications, recent progress, and current challenges of ECM in surface processing. According to diverse surface requirements, ECM technology is classified into two core directions based on primary objectives. The first direction focuses on surface quality enhancement, where nanoscale planarization, residual stress reduction, and uniform surface performance are achieved through precise regulation of anodic dissolution. The second direction concerns material shaping, which is subdivided into macro-scale and micro-scale processing. Macro-scale forming combines electrochemical dissolution with mechanical action to maintain high material removal rate (MRR) while achieving micron-level precision. Micro-scale forming employs nanosecond pulse power supplies and precision electrode/mask designs to overcome manufacturing limitations of micro-nano features on hard-brittle materials. Despite progress achieved, key technical bottlenecks persist, including unstable dynamic control of the inter-electrode gap, environmental concerns regarding electrolytes, and tooling degradation. Future research should prioritize the development of green processing technologies, intelligent control systems, multi-scale manufacturing strategies, and multi-energy field hybrid technologies to enhance the capability of ECM in meeting increasingly stringent surface requirements for advanced materials. Full article

Accurate diagnosis of myocardial infarction (MI) holds significant clinical importance for public health systems. Deep learning-based ECG, classification and localization methods can automatically extract features, thereby overcoming the dependence on manual feature extraction in traditional methods. However, these methods still face challenges such as insufficient utilization of dynamic information in cardiac cycles, inadequate ability to capture both global and local features, and data imbalance. To address these issues, this paper proposes a ResNet-Transformer cascaded network (RTCN) to process time frequency features of ECG signals generated by the S-transform. First, the S-transform is applied to adaptively extract global time frequency features from the time frequency domain of ECG signals. Its scalable Gaussian window and high phase resolution can effectively capture the dynamic changes in cardiac cycles that traditional methods often fail to extract. Then, we develop an architecture that combines the Transformer attention mechanism with ResNet to extract multi-scale local features and global temporal dependencies collaboratively. This compensates for the existing deep learning models’ insufficient ability to capture both global and local features simultaneously. To address the data imbalance problem, the Denoising Diffusion Probabilistic Model (DDPM) is applied to synthesize high-quality ECG samples for minority classes, increasing the inter-patient accuracy from 61.66% to 68.39%. Gradient-weighted Class Activation Mapping (Grad-CAM) visualization confirms that the model’s attention areas are highly consistent with pathological features, verifying its clinical interpretability. Full article

High-temperature vulcanized silicone rubber (HTV-SR), widely used in composite insulators, experiences performance degradation when subjected to combined stresses such as corona discharge, humidity and temperature fluctuations. This degradation poses significant risks to the reliability of power grid operation. To investigate the aging behavior and mechanisms of HTV-SR under the combined influences of corona, moisture and thermal cycling, a series of multi-factor accelerated aging tests are conducted. Comprehensive characterizations of surface morphology, structural, mechanical and electrical properties are performed before and after aging. The results reveal that corona discharge induces molecular chain scission and promotes oxidative crosslinking, leading to surface degradation. Increased humidity accelerates water diffusion and hydrolysis, enhancing crosslink density but reducing material flexibility, thereby further deteriorating structural integrity and electrical performance. Compared with constant temperature aging, thermal cycling introduces repetitive thermal stress, which significantly aggravates filler migration and leads to more severe mechanical and dielectric degradation. These findings elucidate the multi-scale degradation mechanisms of HTV-SR under the coupling effects of corona discharge, humidity and temperature cycling, providing theoretical support for the design of corona- and humidity-resistant silicone rubber for composite insulator applications. Full article

Under extreme operating conditions, the internal lubricating flow field of high-speed gear transmission systems exhibits a transient oil–gas multiphase flow, predominantly governed by cavitation-induced phase transitions and turbulent shear. This phenomenon involves complex mechanisms of nonlinear multi-physical coupling and energy dissipation. Traditional lubrication theories and single-phase flow simplified models show significant limitations in capturing microsecond-scale flow features, dynamic interface evolution, and turbulence modulation mechanisms. To address these challenges, this study developed a cross-scale coupled numerical framework based on the Lattice Boltzmann method and large eddy simulation (LBM-LES). By incorporating an adaptive time relaxation algorithm, the framework effectively enhances the computational accuracy and stability for high-speed rotational flow fields, enabling the precise characterization of lubricant splashing, distribution, and its interaction with air. The research systematically reveals the spatiotemporal evolution characteristics of the internal flow field within the gearbox and focuses on analyzing the nonlinear regulatory effect of baffle geometric parameters on the system’s energy transport and dissipation characteristics. Numerical results indicate that the baffle structure significantly influences the spatial distribution of the vorticity field and turbulence intensity by reconstructing the shear layer topology. Low-profile baffles optimize the energy transfer pathway, effectively reducing the flow enthalpy, whereas excessively tall baffles induce strong secondary recirculation flows, exacerbating vortex-induced energy losses. Simultaneously, appropriately increasing the spacing between double baffles helps enhance global lubricant transport efficiency and suppresses unsteady dissipation caused by localized momentum accumulation. Furthermore, the geometrically optimized double-baffle configuration can achieve synergistic improvements in lubrication performance, oil film stability, and system energy efficiency by guiding the main shear flow and mitigating localized high-momentum impacts. This study provides crucial theoretical foundations and design guidelines for developing the next generation of theory-driven, energy-efficient lubrication design strategies for gear transmissions. Full article

Chronickidney disease (CKD) poses a major global public health challenge, driven by a complex pathogenesis involving multiple interconnected processes—including metabolic disturbances, chronic inflammation, oxidative stress, endoplasmic reticulum stress, and ferroptosis—which collectively contribute to progressive and often irreversible loss of renal function. Although current standard therapies can ameliorate CKD progression, a substantial number of patients still advance to end-stage renal disease, highlighting the urgent need for innovative treatment strategies. Natural products have shown great promise in the prevention and management of CKD, largely attributable to their multi-target and multi-pathway synergistic effects. This review systematically outlines the core pathogenic mechanisms underlying CKD and elucidates the molecular mechanisms through which bioactive natural compounds exert renoprotective effects. Despite robust preclinical evidence, the clinical translation of these compounds remains hindered by limitations such as poor bioavailability and a lack of large-scale clinical trials. Moving forward, research should prioritize clinical translation of these compounds, aiming to provide novel therapeutic perspectives for CKD management. Full article

This study tackles the complex challenge of dynamic multi-objective vehicle routing optimization in large-scale equipment manufacturing, where routing operations significantly impact both economic performance and environmental sustainability. We develop an innovative Dynamic Multi-Objective Vehicle Routing Problem (DMOVRP) model that uniquely integrates three competing objectives: environmental impact reduction, delivery timeliness, and operational robustness. The proposed algorithm combines a dynamic event handler with the NSACOWDRL algorithm—an adaptive multi-objective optimization algorithm with dynamic event handling capability. The proposed system features adaptive mechanisms for handling real-time disruptions through specialized event classification and dynamic rescheduling protocols. Extensive computational experiments demonstrate the algorithm’s superior performance with statistically significant improvements using the Wilcoxon signed-rank test (p < 0.05, n = 30 runs per instance), achieving average relative gains of 15.2% in HV, 12.8% in IGD, and 8.9% in GD metrics compared to established methods. This research makes theoretical contributions through its feasibility quantification metric and practical advancements in routing schedule systems. By successfully reconciling traditionally conflicting objectives through dynamic JIT adjustments and robustness-aware optimization, this work provides manufacturers with a versatile decision-support tool that adapts to unpredictable workshop conditions while maintaining sustainable operations. Full article