Search Results (26,173)

In industrial scenarios, strong background noise can easily overwhelm the weak impulsive signatures of gearbox faults, leading to time-domain waveform distortion and frequency-domain spectral aliasing, which in turn degrades the feature extraction capability of conventional diagnostic models and significantly reduces their diagnostic accuracy and robustness. To overcome this limitation, a dual-domain generative–discriminative fusion network (DDGF-Net) is proposed for robust gearbox fault diagnosis under strong noise interference. The proposed framework consists of three collaborative components. Firstly, an improved conditional variational autoencoder (CVAE) integrating soft-threshold shrinkage and spectral consistency constraints is designed to perform joint time–frequency denoising and signal reconstruction, thereby preserving subtle fault characteristics while effectively suppressing noise. Secondly, parallel time-domain and frequency-domain encoding branches are constructed to extract transient fault impulses and fault characteristic frequencies, respectively, compensating for the inadequacy of single-domain feature representations. Thirdly, a lightweight bidirectional cross-attention mechanism is introduced to overcome the limitations of conventional fixed-weight fusion strategies, enabling dynamic adjustment of the interaction weights between dual-domain features according to the instantaneous noise intensity, thus maximizing the complementary value of cross-domain features. Extensive comparative experiments conducted on the Southeast University(SEU) gearbox dataset demonstrate that DDGF-Net achieves superior diagnostic performance and noise robustness over eight representative methods, particularly under strong noise interference, thereby validating its effectiveness and superiority in harsh diagnostic scenarios. Full article

In recent years, numerous studies have reported on intelligent analytical applications for food quality and safety. To identify the underlying patterns and development trends in this field, this paper presents a comprehensive review from the perspectives of both data-driven and mechanism-driven paradigms. Under the data-driven paradigm, detection modalities may involve either single-modal or multimodal approaches. By integrating measured detection data with appropriate intelligent learning algorithms, specific tasks for food quality or safety assessment can be achieved. Research efforts in this area encompass the development of detection techniques, optimization of measurement parameters, construction of high-dimensional spectral features, design of feature extraction methods, selection and tuning of algorithms, and formulation of multimodal data fusion strategies. This paradigm is characterized by high computational speed and superior prediction or classification efficiency. Nevertheless, it is constrained by several limitations, including poor model interpretability, limited extrapolation and generalization capabilities, and a heavy reliance on high-quality annotated data. In contrast, the data–mechanism hybrid-driven paradigm integrates physical laws and other prior knowledge as constraints that are deeply embedded into neural network training. By combining data-driven mining capabilities with theoretical prior knowledge, this approach achieves improved predictive performance and decision-making reliability. This paradigm offers notable advantages, such as enhanced interpretability, greater trustworthiness, improved data efficiency, and reduced computational costs. It is particularly well-suited for small-sample or data-sparse scenarios, and thus represents a promising and important direction for future research in this domain. Full article

Background/Objectives: Cerebral small vessel disease (SVD) is a heterogeneous condition in which similar conventional MRI findings may be associated with different clinical manifestations and pathogenetic mechanisms. Previously, hierarchical clustering of structural MRI features in patients with severe white matter hyperintensities (Fazekas 3) identified two MRI phenotypes, designated MRI Type 1 and MRI Type 2. Diffusion MRI (dMRI) may provide additional information about the microstructural differences between these phenotypes. To compare white matter microstructure between MRI Type 1 and MRI Type 2 of sporadic age-related SVD using signal-based and biophysical dMRI models. Methods: This cross-sectional study included 75 patients with SVD and 36 age- and sex-matched healthy controls. Among the patients with SVD, 43 had MRI Type 1 and 32 had MRI Type 2. All participants underwent structural and multi-shell dMRI on a 3 Tesla MRI scanner. Diffusion metrics were derived using multiple models: Diffusion Tensor Imaging (DTI), Diffusion Kurtosis Imaging (DKI), Neurite Orientation Dispersion and Density Imaging (NODDI), White Matter Tract Integrity (WMTI), and the Multi-compartment Spherical Mean Technique (MC-SMT). Tract-profile analysis was performed in three corpus callosum segments: the forceps major, forceps minor, and body. Group differences were assessed using age- and sex-adjusted general linear models with correction for multiple comparisons. The combined discriminative value of dMRI metrics was evaluated using regularized Elastic Net logistic regression with repeated nested five-fold cross-validation. Results: After adjustment for age and sex, the overall group effect remained significant for 45 of 48 global dMRI measures following Benjamini–Hochberg correction. Compared with MRI Type 2, MRI Type 1 showed lower fractional anisotropy (FA), neurite density index (NDI), intra-axonal volume fraction (INTRA), axonal water fraction (AWF), mean kurtosis (MK), axial kurtosis (AK), and radial kurtosis (RK), and higher mean diffusivity (MD), radial diffusivity (RD), extra-axonal mean diffusivity (EXTRA_MD), extra-axonal transverse diffusivity (EXTRA_TRANS), and extra-axonal radial diffusivity (radEAD). These differences were generally most pronounced in the body of the corpus callosum. In the segmental analysis, 131 of 144 values showed a significant overall group effect after correction, and 108 demonstrated significant differences between MRI Type 1 and MRI Type 2. The largest effects were observed in the 60–80% interval of the corpus callosum body, particularly for AWF, MK, INTRA, EXTRA_TRANS, RK, FA, RD, radEAD, and MD. An Elastic Net model combining age, sex, and 48 global dMRI measures discriminated MRI Type 1 from MRI Type 2 with an internally validated area under the curve of 0.866 (95% CI, 0.762–0.953), accuracy of 86.7%, sensitivity of 75.0%, and specificity of 95.3%. Ten dMRI features showed a selection frequency of at least 70% across repeated model construction. Conclusions: MRI Type 1 is characterized by more severe and spatially extensive corpus callosum microstructural abnormalities than MRI Type 2, despite broadly similar vascular risk-factor profiles. The findings support the heterogeneity of sporadic age-related SVD and indicate that combined signal-based and biophysical dMRI metrics may improve MRI phenotyping. The observed associations should be interpreted as indirect markers of tissue microstructure and require confirmation in larger, independent, and longitudinal cohorts. Full article

Microbiota dysbiosis is closely associated with a wide range of human diseases, yet wet-lab validation remains costly and time-consuming. Therefore, this study aims to develop an efficient framework for predicting potential microbe–disease associations. We propose a novel predictive model, NNGCFCAE, which integrates Nuclear Norm Minimization (NNM), an enhanced Graph Convolutional Network (GCF) with an energy-based Conditional Random Field (CRF) smoothing mechanism, and a multi-channel convolutional autoencoder (CAE) with residual connections to effectively infer latent microbe–disease associations. First, we construct a heterogeneous network by integrating known microbe–disease associations with Gaussian Interaction Profile (GIP) kernels and Hamming Interaction Profile (HIP) features. Subsequently, nuclear norm minimization is applied to complete the initial association matrix, yielding a preliminary prediction score matrix. The GCF module then extracts spatial structural features of microbe and disease nodes from the network, while the CAE module further learns attribute-based representations of these nodes. Finally, the prediction score matrix, topological features, attribute features, and multi-source information are fused to form a joint representation matrix, which is used to compute the final association scores between microbes and diseases. Experiments conducted on datasets such as HMDAD and Disbiome demonstrate that NNGCFCAE significantly outperforms several state-of-the-art methods in terms of AUC and AUPR. Ablation studies and case analyses on obesity, asthma, and ulcerative colitis further demonstrate its biological plausibility, highlighting its potential for uncovering latent microbe–disease associations. Full article

Osteoporosis requires long-term management, yet current pharmacological therapies are limited by safety concerns. Calcium carbonate is a biocompatible and widely used calcium supplement; however, its low absorption efficiency restricts therapeutic effectiveness. Herein, a biomimetic calcium delivery system was constructed by depositing an ultrathin (~10 nm) tannic acid/fish collagen (TA/FC) nanolayer onto CaCO₃ nanoparticles via coordination- and hydrogen bonding-mediated self-assembly. The TA/FC nanocoating modulates cellular internalization by activating multiple endocytic pathways, thereby enhancing nanoparticle uptake and intracellular calcium delivery. As a result, cellular calcium uptake increased by 5.6-fold, and the apparent absorption rate reached 93.2%, 4.9 times higher than that of medical-grade calcium carbonate. In vivo, CaCO₃@TA/FC nanoparticles restored bone metabolic homeostasis, as indicated by increased serum calcium, decreased phosphate and alkaline phosphatase levels, and elevated osteoprotegerin expression. This was accompanied by significant improvements in bone microarchitecture, including increased bone mineral density, bone volume fraction, trabecular number and thickness, as well as recovery of mechanical strength. Overall, this work demonstrates that interfacial engineering enhances calcium bioavailability and improves the therapeutic performance of calcium carbonate. Full article

Magnesium potassium phosphate cement (MKPC) exhibits rapid setting and high early strength, but its long-term performance is limited by microstructural heterogeneity and pore structure defects. These microstructural defects can increase pore connectivity and facilitate the ingress of aggressive agents, thereby limiting the long-term durability and service reliability of MKPC-based repair and protective materials. Nanomaterials have been applied to improve MKPC performance; however, the differences between conventional nano-SiO₂ (NS) and nano-Fe₂O₃ (NF), particularly their effects on hydration regulation and microstructure evolution, remain insufficiently understood. In this study, the effects of NF and NS incorporation on the hydration behavior, phase evolution, pore structure, and mechanical properties of MKPC were comparatively investigated. Orthogonal experiments, mechanical testing, calorimetry, XRD, FTIR, Raman mapping, SEM/EDS, MIP, and nanoindentation were employed to establish the relationship between nano-modification, microstructural evolution, and mechanical performance. The results provide a basis for selecting suitable nanomodifiers for MKPC-based materials used in rapid repair, protective applications, and other construction scenarios requiring rapid strength development and improved microstructural compactness. Compared with pure MKPC and previously reported NS-MKPC results, NF-MKPC showed higher strength development, refined pore structure, and improved micromechanical uniformity. The observed performance enhancement of NF-MKPC is consistent with accelerated early hydration, possible heterogeneous nucleation, pore refinement, and matrix densification. In comparison, NS-MKPC exhibited a different hydration and pore-evolution behavior under the investigated conditions. These findings indicate that NF and NS may regulate hydration and microstructure development differently in MKPC and provide guidance for selecting suitable nano-modifiers for high-performance phosphate cement materials. Under the investigated conditions, NF modification shows potential for MKPC applications requiring rapid strength development and improved microstructural compactness, such as rapid pavement repair, concrete surface repair, and protective coating applications. Full article

High-precision manufacturing in unstructured factories imposes stringent requirements on real-time scene perception and end-effector positioning accuracy. Traditional single-sensor solutions suffer from perception blind spots in human-robot mixed environments with complex lighting, while chassis cumulative error often leads to rigid collisions during end-effector operations. To address this, this paper proposes and evaluates a decision-level multi-sensor coordination mechanism for robust navigation and high-precision planar positioning of industrial mobile robots. The mechanism assigns explicit sensor roles, distance-dependent trigger conditions, and deterministic safety priorities. At the navigation and obstacle avoidance level, a sequential decision policy is constructed: macroscopically, a lightweight You Only Look Once version 5 small (YOLOv5s) is utilized for the early detection of dynamic objects, providing bounding-box coordinates to trigger preemptive deceleration, while LiDAR independently provides geometric ranging for ROS local-costmap updating and detour replanning; microscopically, a low-level hardware interrupt strategy triggered by ultrasonic sensors is proposed to mitigate near-field blind spots and reduce communication latency. At the end-effector positioning level, under illumination conditions ranging from 200 to 1000 lux, an adaptive alignment algorithm combining hue-saturation-value color-space morphological processing and Kalman filtering is proposed to suppress measurement noise caused by illumination variations and mechanical vibrations. Experiments in the tested dynamic human-robot mixed scenarios showed no rigid collisions for the proposed system and an emergency response time of approximately 50 ms against sudden blind-spot intrusions. Simultaneously, the system achieves a 95% reliability rate in controlling the end-effector 2D planar positioning error (X-Y plane) within a ±2 mm tolerance under complex illumination interference. These results demonstrate improved navigation safety and planar-positioning reliability under the tested flexible-manufacturing conditions. Full article

With the rapid development of the electric vehicle (EV) industry, large-scale integration of EVs into the power grid has led to increasingly prominent problems such as low charging efficiency, intensified load fluctuations, and reduced economic benefits for users. To address these issues, an optimization model is constructed with charging time, load fluctuation, and user charging cost as the objectives, comprehensively considering uncertainties including renewable energy output, user charging behavior, and electricity price fluctuations. An uncertainty-aware multi-objective scheduling strategy based on an improved chaotic Lévy flight multi-objective particle swarm optimization (CLM-MOPSO) algorithm is proposed. Specifically, Weibull and Beta distributions are adopted to generate scenarios for wind and photovoltaic power output, while Poisson and normal distributions are used to characterize the uncertainty of user charging behavior. In addition, a stochastic electricity price process and load uncertainty sets are introduced to establish a robust optimization framework based on multi-scenario stochastic programming. On this basis, an improved CLM-MOPSO algorithm is designed, in which Tent chaotic mapping is utilized for high-quality population initialization, Lévy flight mutation is introduced to enhance the global search capability, and adaptive parameter adjustment together with an external archive mechanism is incorporated to improve the search efficiency while maintaining good convergence and diversity of the Pareto solution set. Finally, simulation studies based on real road network and power grid operation data are conducted, and the results verify the effectiveness of the proposed method. The results demonstrate that the proposed method significantly reduces charging time, mitigates load fluctuations, and lowers user charging costs, while also exhibiting strong robustness and potential for practical engineering applications. Full article

Background: Obstructive sleep apnea syndrome (OSA) is a significant disorder characterized by recurrent upper airway obstruction. Cervical vertebral alignment and lordosis angles may influence airway cross-sectional area. This study aimed to investigate the relationship between cervical lordosis angles and disease severity in patients with OSA. Methods: The study included 30 patients with OSA (mild n = 6, moderate n = 11, severe n = 13 based on Apnea–Hypopnea Index [AHI]) and 30 non-OSA controls presenting with mechanical neck pain. C1–C2, C1–C7, and C2–C7 angles were measured using the Cobb method on lateral cervical cephalometric radiographs. Additional soft tissue and airway parameters — prevertebral soft-tissue thickness at C2 (PST-C2) and C4 (PST-C4), posterior airway space (PAS), and mandibular plane–hyoid distance (MP-H)— were measured as anatomical surrogates given the unavailability of BMI data. Multiple linear regression (ANCOVA) models adjusting for age and sex were constructed for each cervical angle. Results: All cervical angles were significantly reduced in patients with OSA compared to controls (C1–C2: 25.51 ± 6.47° vs 33.3 ± 4.44°; C1–C7: 35.0 ± 11.9° vs 51.2 ± 7.34°; C2–C7: 9.19 ± 10.6° vs 19.9 ± 5.05°; all p < 0.001). Within the OSA group, a significant moderate negative correlation was found between AHI and the C2–C7 angle (ρ = − 0.522, p = 0.003), while the C1–C7 angle showed a borderline association (ρ = −0.361, p = 0.050) and C1–C2 did not reach significance (ρ = +0.118, p = 0.534). After adjustment for age and sex, group membership (OSA vs. control) remained a strong, independent predictor of all three cervical angles (all p < 0.001), whereas neither age nor sex was a significant predictor (all p > 0.34). PST-C2 was significantly higher in the OSA group (4.93 ± 1.06 mm vs. 4.30 ± 0.70 mm, p = 0.017), whereas PST-C4, PAS, and MP-H did not differ significantly between groups (all p > 0.05), and none of these parameters correlated significantly with the C2–C7 angle. Conclusions: Significant cervical lordosis loss was observed in patients with OSA compared to non-OSA controls, with the C2–C7 angle showing a significant negative correlation with AHI within the OSA group; this association remained robust after adjustment for age and sex. Supplementary soft tissue and airway measurements showed no significant correlation with cervical alignment or AHI, suggesting the observed association is not simply attributable to regional soft-tissue thickness or airway narrowing; however, without direct BMI data, a confounding role of systemic adiposity cannot be excluded. These findings suggest a potential association between cervical posture and upper airway dynamics; however, larger prospective studies are required to confirm clinical utility. Full article

Urban pluvial flooding shows clear temporal accumulation, delayed response, and spatial heterogeneity. Better flood-depth prediction from a spatiotemporal coupling perspective can support urban flood risk identification and refined management. This study develops a spatiotemporal prediction model that integrates a Transformer and graph neural network (GNN). The Transformer module captures temporal dependencies in rainfall processes and flood-depth evolution. The graph attention network (GAT) represents spatial associations constrained by terrain, drainage networks, and neighboring spatial relationships. A fusion attention mechanism then adaptively couples temporal and spatial features. This study uses multi-source data, including hourly meteorological observations, terrain, land cover, drainage networks, and water-system data. It selects the heavy rainfall event caused by Typhoon In-Fa in Huai’an City in July 2021 as a typical case. The study analyzes the temporal evolution of regional average flood depth and the spatial differentiation of inundated grid cells at the municipal scale. The results show three main findings. First, during the typical heavy rainfall event, regional average flood depth follows a continuous process of low-level stability, sustained rise, rapid increase, delayed peak, slow recession at a high level, and rapid recession. The flood peak lags behind the rainfall peak by about 3 h. This result indicates clear accumulation and delayed response in urban pluvial flooding. Second, at the municipal scale, inundated grid cells show a pattern of concentrated distribution in urban built-up areas, secondary distribution in county-level built-up areas, and scattered distribution in non-construction land. Different depth grades also show clear hierarchical differentiation. Mild and moderate inundation covers a wider area. Medium-high inundation concentrates locally. High-grade inundation appears as a small number of nested high-value cells. Third, the spatial differentiation of medium- and high-grade inundated grid cells does not result from low-lying terrain or construction land alone. It forms under the combined effects of low-lying terrain, local relative depressions, and impervious surfaces in construction land. This pattern shows clear built-up-area clustering, grade differentiation, and land-cover correspondence. The results provide methodological support and decision references for urban flood risk identification, grid-based risk management, and emergency dispatch during extreme rainfall. Full article

Within digital green evaluation environments, both social visibility (SV) and experimentally constructed evaluative-feedback conditions (EFCs) may shape green purchase intention (GPI). Prior research has emphasized observability and social signaling, while paying less attention to how the evaluative direction of feedback is translated into self-conscious emotions. Drawing on the stimulus–organism–response framework, this study examines how EFCs and SV relate to GPI in association with shame (SH) and pride (PR). A 2 × 3 between-subjects experiment (N = 270) manipulated SV (public versus private) and EFC (negative, neutral, positive). EFC showed significant differences in SH, PR, and GPI, whereas SV showed no significant main effects and operated conditionally. Multicategorical relative indirect-effect analyses, using neutral feedback as the reference condition and controlling for SV, showed significant PR-related relative indirect effects for both the negative versus neutral and positive versus neutral contrasts; the corresponding SH-related relative indirect effects were not significant. Exploratory EFC × SE interactions were significant for both emotional responses, but SE was measured post-stimulus and differed across EFCs; these results are therefore treated as post-stimulus conditional associations. Under the present experimental operationalization, differences across the bundled EFCs were more consistent than SV effects. Because the EFCs jointly varied product choice, score, evaluative message, and interface cues, the findings do not isolate pure valence effects; the relative indirect effects are interpreted as statistical patterns consistent with possible emotional pathways rather than as a complete causal mechanism. Full article

To address the limitation of traditional cellular automata models in effectively integrating temporal and spatial information, this study extends the previously developed Land use Simulation and Decision-Support system (LandSDS). By incorporating a graph attention network (GAT), a transformer, and an agent-based model (ABM) into a cellular automata framework informed by remote sensing time series, GT-LandSDS is constructed. Specifically, GAT dynamically captures higher-order spatial dependencies among land parcels; the self-attention mechanism of the transformer extracts land use change characteristics from multi-period observations; and ABM captures human behavioral decisions of three types, namely traffic, resident, and government. Based on this framework, GT-LandSDS derives CA transition rules from multiple dimensions and enhances the dynamic exploration of land use change across space and time. Using Guangxi Zhuang Autonomous Region as a case study, the model was validated with remote sensing land use data from six periods (2000, 2005, 2010, 2015, 2020, and 2023), and scenario-based future predictions were generated. The results show that: (1) The overall accuracy reaches 0.926, while the Kappa coefficient is 0.820, and the figure of merit (FoM) for change simulation is 0.034, indicating a relative advantage over ANN-CA, LSTM-CA, and UESP in overall pattern simulation, although fine-scale change reproduction remains limited; (2) Three development scenarios were then assessed: continuing historical trends, theoretical high-intensity urban expansion, and karst landform conservation under a green transformation development policy. The land use pattern of the area from 2023 to 2035 was predicted. The findings reveal that accelerating urbanization leads to rapid expansion of construction land, increasing by more than 88% compared with 2023, and causes substantial cropland loss. In contrast, intervention through the green transformation development policy limits construction land growth to 26.5%, effectively curbing urban sprawl while protecting forest, grassland, and cropland resources in the karst landscape. This study offers new insights into land use change simulation in ecologically fragile regions subject to strong policy interventions. It provides a scientific basis for coordinating ecological conservation and high-quality development in karst areas. Full article

In recent years, forest fires have occurred frequently, and extremely high temperatures can easily cause plastic deformation of buried pipelines. To clarify the temperature-stress variation law of natural gas pipelines under wildfire action, this study, based on heat transfer theory and using the finite element method, constructs a numerical model of a buried pipeline and analyzes the thermo-mechanical sequential coupling behavior of the pipe–soil system. It elucidates the influence patterns of key factors such as burial depth, outer diameter, internal fluid pressure, soil thermal conductivity, and fire duration on the temperature-stress fields of the pipe and surrounding soil and investigates pipeline deformation under fire. The results show that burial depth is the most sensitive factor: when it increases from 0.2 m to 0.8 m, the maximum pipe temperature decreases from 291.4 °C to 32.4 °C, and the maximum von Mises stress decreases from 507 MPa to 236 MPa. Furthermore, increasing pipe outer diameter and soil thermal conductivity both exacerbate pipe temperature rise and stress accumulation. Meanwhile, the longer the duration, the more pronounced the soil heat storage lag. Additionally, when internal pressure increases from 2 MPa to 8 MPa, the pipe’s maximum stress increases by up to 10.8%. The analysis results can provide a theoretical basis for identifying high-risk pipeline sections and guiding route selection and protective measure optimization for pipelines crossing forested areas. Full article

Bearings are core components of rotating machinery, and the development of precise and efficient fault diagnosis technologies is of paramount importance for realizing early warning and accurate localization of faults. This paper briefly analyzes bearing fault mechanisms and provides a comprehensive review and critical commentary on the research progress of bearing fault diagnosis methods, outlining future development trends. Specifically, this study begins by introducing common bearing fault types and reviewing the advancements in fault signal acquisition techniques. Subsequently, it categorizes fault diagnosis methods based on vibration signals and critically evaluates their respective research methodologies. Furthermore, focusing on non-contact acoustic signal diagnosis, the paper summarizes mainstream technical pathways for acoustic signal denoising and highlights innovative applications of deep-learning models tailored to acoustic characteristics. Finally, addressing the urgent demands for industrial deployment, future research directions are projected from three perspectives: the deep integration of physics-driven and data-driven multi-modal fusion, interpretable diagnosis assisted by Large Language Models (LLMs), and lightweight engineering deployment. This work aims to provide a reference for constructing an all-scenario intelligent monitoring system. Full article

The construction sector contributes significantly to global carbon emissions, prompting a shift toward sustainable engineered timber. However, European hardwood species remain underutilised because current design standards are largely based on research conducted on softwood species. This paper outlines the fundamental principles for designing mechanical timber connections, specifically dowel-type fasteners, by reviewing the European Yield Model and fracture-mechanics approaches for ductile and brittle failure. Through a synthesis of recent experimental investigations on species like European beech, the work identifies critical gaps in current Eurocode 5 (EC5) provisions. The findings demonstrate that EC5 tends to underestimate the load-carrying capacity of many hardwood connections by 33% to 46% and does not explicitly account for brittle mechanisms such as splitting and row shear. Furthermore, the results highlight that connection performance may be significantly increased by factors like dowel-surface roughness, the “rope effect,” and specific assembly requirements such as precise predrilling diameters. This study concludes that existing design frameworks require calibration with hardwood-specific data and improved predictive models to differentiate failure modes. Such adjustments are essential to fully exploit the superior mechanical potential of hardwood species in modern timber construction. Full article