Search Results (61)

Accurate estimation of battery state of health is essential for ensuring safety, supporting fault diagnosis, and optimizing the lifetime of electric vehicles. This study proposes a compact dual-path architecture that combines Convolutional Neural Networks with Convolutional Long Short-Term Memory (ConvLSTM) units to jointly extract spatial and temporal degradation features from charge-cycle voltage and current measurements. Residual and inter-path connections enhance gradient flow and feature fusion, while a three-channel preprocessing strategy aligns cycle lengths and isolates padded regions, improving learning stability. Operating end-to-end, the model eliminates the need for handcrafted features and does not rely on discharge data or temperature measurements, enabling practical deployment in minimally instrumented environments. The model is evaluated on the NASA battery aging dataset under two scenarios: Same-Battery Evaluation and Leave-One-Battery-Out Cross-Battery Generalization. It achieves average RMSE values of 1.26% and 2.14%, converging within 816 and 395 epochs, respectively. An ablation study demonstrates that the dual-path design, ConvLSTM units, residual shortcuts, inter-path exchange, and preprocessing pipeline each contribute to accuracy, stability, and reduced training cost. With only 4913 parameters, the architecture remains robust to variations in initial capacity, cutoff voltage, and degradation behavior. Edge deployment on an NVIDIA Jetson AGX Orin confirms real-time feasibility, achieving 2.24 ms latency, 8.24 MB memory usage, and 12.9 W active power, supporting use in resource-constrained battery management systems. Full article

For runoff-generated debris flow continuum mechanics-based early warning models, the computational unit must satisfy the homogeneity assumption of continuum mechanics. Although traditional grid cells meet the homogeneity assumption as computational units, they segment channel geomorphological functional reaches, weaken the clustered mobilization of sediment sources, and constrain efficiency due to grid-by-grid calculations. To address these limitations, we construct a Froude number ($Fr$) calculation model constrained by key factors such as the channel cross-sectional geometry and topographic parameters. The absolute deviation of $Fr$ is used as a criterion for homogeneity within the computational unit. By combining critical shear stress theory and velocity perturbation, physical thresholds for the criteria are derived. A physical model-based method for automatically delineating homogeneous channel units (${CU}_j$) is proposed, ensuring that the geometric features and hydrodynamic parameters within ${CU}_j$ are homogeneous, while ensuring heterogeneity between adjacent ${CU}_j$. Comprehensive multi-scale validation in Yeniu Gully, a typical debris flow catchment in Wenchuan County, demonstrates that parameters such as longitudinal gradient, cross-sectional area, flow depth, and shear stress remain relatively homogeneous within each ${CU}_j$ but differ significantly between adjacent ${CU}_j$. Furthermore, the proposed method can stably characterize key channel geomorphological functional units, such as bends, confluences, abrupt width changes, longitudinal gradient changes, erosion segments, and deposition segments. Sensitivity analysis demonstrates that the method satisfies both robustness and universality under various conditions of rainfall intensity, runoff coefficient, and Manning’s roughness coefficient. Even under the most unfavorable extreme conditions, the accuracy of ${CU}_j$ delineation exceeds 88.64%, indicating high reliability and suitability for deployment in various debris flow catchments. The proposed framework for defining ${CU}_j$ resolves the conflict in traditional computational units between the “continuum model homogeneity requirement” and “geomorphological functional unit continuity,” providing a more rational and efficient computational environment for runoff-generated debris flow continuum mechanics-based early warning models. Full article

Ship detection plays a pivotal role in safeguarding maritime security, regulating vessel traffic, and bolstering national maritime defense. While contemporary lightweight models predominantly emphasize parameter reduction, efforts to curtail computational demands remain underexplored. In this study, we propose a lightweight multi-feature channel convolution module (MFC-Conv) to create an efficient backbone network. This module adeptly propagates multi-scale feature information, yielding a holistic representation while approximating residual architectures in a computationally frugal manner, thereby promoting seamless gradient flow during optimization. Notably, MFC-Conv can be re-parameterized into a streamlined two-layer convolutional structure devoid of branching or partitioning, streamlining deployment on resource-constrained edge devices. Complementing this, a multi-feature attention module (MFA) is proposed to augment localization and classification efficacy with negligible overhead. Furthermore, leveraging the inherent resolution traits of satellite SAR imagery, the decoder is refined to minimize redundant computations. Empirical evaluations across diverse datasets reveal that our framework outperforms the baseline by slashing parameters by 57.8% and FLOPs by 42.7%. Relative to two leading lightweight state-of-the-art (SOTA) models, it achieves computational reductions of 51.4% and 25.0%, respectively, thereby enabling viable onboard satellite deployment for ship detection. Full article

The growing demand for renewable energy in space-constrained environments highlights the need for compact, high-efficiency wind energy systems. Conventional bare wind turbine (BWT) arrays suffer from severe wake interactions and performance degradation when operated in tandem or closely spaced configurations. To address these limitations, this study investigates the aerodynamic performance and near-wake dynamics of a novel multi-ducted wind turbine (MDWT) system that integrates passive flow-control technique (PFCT) into an innovative fixed-duct design. The objective is to evaluate how tandem ducted arrangements with this integrated mechanism influence wake recovery, vortex dynamics, and power generation compared with multi-bare wind turbine (MBWT) system. A numerical approach is employed using the Unsteady Reynolds-Averaged Navier–Stokes (URANS) formulation with the k–ω SST turbulence model, validated against experimental data. The analysis focuses on two identical, fixed-orientation ducts arranged in tandem without lateral offset, tested under three spacing configurations. The results reveal that the ducted system accelerates the near-wake flow and displaces velocity-deficit regions downward due to the passive flow-control sheets, producing stronger inflow fluctuations and enhanced turbulence mixing. These effects improve wake recovery and mitigate energy losses behind the first turbine. Quantitatively, the MDWT array achieves total power outputs 1.99, 1.90, and 1.81 times greater than those of the MBWT array for Configurations No. 1, No. 2, and No. 3, respectively. In particular, the second duct in Configuration No. 1 demonstrates a 3.46-fold increase in power coefficient compared with its bare counterpart. These substantial gains arise because the upstream duct–PFCT assembly generates a favorable pressure gradient that entrains ambient air into the wake, while coherent tip vortices and redirected shear flows enhance mixing and channel high-momentum fluid toward the downstream rotor plane. The consistent performance across spacings further confirms that duct-induced flow acceleration and organized vortex structures dominate over natural wake recovery effects, maintaining efficient energy transfer between turbines. The study concludes that closely spaced MDWT systems provide a compact and modular solution for maximizing energy extraction in constrained environments. Full article

Water and sand inrush is frequently accompanied by surface subsidence, which severely constrains the sustainable development of coordinated coal mining and ecological environment. This study investigated four key influencing factors based on a water and sand inrush test system: fracture width, aquifer thickness, sand particle size composition and stratigraphic sedimentary structure. It obtained the morphological evolution characteristics of collapse funnels and revealed the evolution mechanism of collapse funnels induced by water and sand inrush. The results indicate that fracture width and aquifer thickness mainly affect the range of collapse funnel, and both show a positive correlation with the radius of collapse funnels. Sandy particle size composition plays a dominant role in the morphology of collapse funnels induced by disasters: as the size of the soil skeleton particles increases, the morphology of collapse funnels changes sequentially from a bowl shape to an inverted cone shape and then to a funnel shape with a sunken center and raised slopes. The stratigraphic sedimentary structure has a significant impact on the morphology and damage induced by disasters in collapse funnels. The upper clay layer of the underlying aquifer inhibits the water and sand inrush processes to some extent. An increase in the thickness and number of clay layers effectively prevents the water and sand mixture from flowing into the fracture channel from the lateral direction. This reduces the damage range of collapse funnels and decreases the rate of water and sand inrush. This study clarifies the formation mechanism of surface collapse funnels under the influence of the disaster-causing factors of water and sand inrush, and provides theoretical guidance for the prevention and control of such disasters. Full article

Floods are among the most frequent and destructive natural hazards worldwide, with increasingly severe socioeconomic consequences due to rapid urbanization, land use changes, and climate variability. While the combination of Geographic Information Systems (GIS) with models such as HEC-RAS has been extensively explored for flood risk management, many existing studies remain limited to one-dimensional (1D) models or use coarse-resolution terrain data, often underestimating flood risk and failing to produce critical multivariate flood characteristics in densely built urban areas. This study applies a two-dimensional (2D) hydraulic modeling framework in HEC-RAS combined with GIS-based spatial analysis, using a high-resolution (1 × 1 m) LiDAR-derived Digital Terrain Model (DTM) and a hybrid mesh refined between 2 × 2 m and 8 × 8 m, with the main contributions represented by the specific application context and methodological choices. A key methodological aspect is the direct integration of synthetic hydrographs with defined exceedance probabilities (10%, 1%, and 0.1%) into the 2D model, thereby reducing the need for extensive hydrological simulations and defining a data-driven approach for resource-constrained environments. The primary novelty is the application of this high-resolution urban modeling framework to a Romanian urban–peri-urban setting, where detailed hydrological observations are scarce. Unlike previous studies in Romania, this approach applies detailed channel and floodplain discretization at high spatial resolution, explicitly incorporating anthropogenic features like buildings and detailed land use roughness for the accurate representation of local hydraulic dynamics. The resulting outputs (inundation extents, depths, and velocities) support risk assessment and spatial planning in the Ungheni locality (Iași County, Romania), providing a practical, transferable workflow adapted to data-scarce regions. Scenario results quantify vulnerability: for the 0.1% exceedance probability scenario (with a calibration accuracy of ±15–30 min deviation for peak flow timing), the flood risk may affect 882 buildings, 42 land parcels, and 13.5 km of infrastructure. This framework contributes to evidence-based decision-making for climate adaptation and disaster risk reduction strategies, improving urban resilience. Full article

Fungal mycelial pellets (MPs) exhibit high biomass-loading capacity; however, their application in wastewater treatment is constrained by structural fragility and the risk of environmental dispersion. To overcome these limitations, a dual-crosslinked polyvinyl alcohol–alginate gel (10% PVA, 2% sodium alginate) embedding strategy was developed and stabilized using 2% CaCl₂ and saturated boric acid. This encapsulation enhanced the tensile strength of MPs by 499% (310.4 vs. 62.1 kPa) and improved their settling velocity by 2.3-fold (1.12 vs. 0.49 cm/s), which was critical for stability under turbulent bioreactor conditions. Following encapsulation, the specific oxygen uptake rates (SOURs) of three fungal strains (F557, Y3, and F507) decreased by 30.3%, 54.8%, and 48.3%, respectively, while maintaining metabolic functionality. SEM revealed tight adhesion between the gel layer and both surface and internal hyphae, with the preservation of porous channels conducive to microbial colonization. In sequential-batch reactors treating sulfamethoxazole (SMX)-contaminated wastewater, gel-encapsulated MPs combined with acclimated sludge consistently achieved 72–75% SMX removal efficiency over six cycles, outperforming uncoated MPs (efficiency decreased from 81.2% to 58.7%) and pure gel–sludge composites (34–39%). The gel coating inhibited hyphal dispersion by over 90% and resisted mechanical disintegration under 24 h agitation. This approach offers a scalable and environmentally sustainable means of enhancing MPs’ operational stability in continuous-flow systems while mitigating fungal dissemination risks. Full article

In this paper, we propose a quantitative evaluation method for navigation safety in coastal waters based on unstructured grids. Initially, a comprehensive analysis was conducted on various factors affecting navigation safety, including natural conditions, traffic conditions, and marine hydro-meteorological conditions, to construct a multi-source fused spatiotemporal dataset. Subsequently, channel boundary extraction was performed using Constrained Delaunay Triangle–Alpha-Shapes, and the precise extraction of ship navigation areas was performed based on Constrained Delaunay Triangle–Voronoi diagrams. Additionally, temporal feature grids were constructed based on the spatiotemporal characteristics of marine hydro-meteorological data. Finally, unstructured grids for evaluating navigation safety were established through spatial overlay analysis. Based on this foundation, a quantitative analysis and evaluation model for comprehensive navigation safety assessment was developed using the fuzzy evaluation method. By calculating the fuzzy relation matrix and weight vectors, quantitative assessments were conducted for each grid cell, yielding safety risk levels from both spatial and temporal dimensions. An analysis was performed using maritime data within the geographic boundaries of lon.119.17–120.41° E and lat.34.40–35.47° N. The results indicated that the unstructured grid division and channel boundary extraction in the demonstrated sea area were closely related to parameters such as the ship traffic flow patterns and the spatiotemporal characteristics of the marine environmental factors. A quantitative evaluation and analysis of the 186 unstructured grid cells revealed that the high risk levels primarily corresponded to restricted navigation areas, the higher-risk grid cells were mainly anchorages, and the low to lower risk levels were primarily associated with channels and navigable areas for ships. Full article

Fish secondary production integrates multiple demographic parameters, including population density, growth, mortality, and recruitment, and thereby provides a comprehensive measure of ecological performance. It is also a valuable tool for assessing the ecological integrity of stream ecosystems and the responses of fish populations to habitat alteration, climatic variability, and anthropogenic pressures. Despite its relevance, empirical estimates of fish production remain limited due to methodological constraints. In this study, we quantified secondary production and production-to-biomass (P/B) ratios for Mediterranean brown trout (Salmo trutta complex) across six headwater stream reaches in the northeastern Iberian Peninsula, characterized by contrasting hydrological regimes, channel morphology, and water chemistry. Field sampling was conducted over two consecutive annual cycles (2008/2009 and 2009/2010) at all sites, with extended monitoring at two reaches until 2017 to assess long-term variability. Annual trout production, over the two consecutive annual cycles, ranged from 30.9 to 167.8 kg ha⁻¹ year⁻¹ (mean = 82.2 kg ha⁻¹ year⁻¹), and mean P/B ratios ranged from 0.61 to 1.13 (mean = 0.80). These values fall within the intermediate range reported for brown trout globally and reflect the constrained energy dynamics of Mediterranean streams. Higher production was generally associated with strong age-1 recruitment, elevated standing biomass, and greater water alkalinity. Long-term analyses revealed that interannual variation in trout production was significantly correlated with discharge variability, with higher production occurring under more stable flow conditions. However, in addition to flow variability other factors, such as habitat complexity, may modulate local productivity. Consequently, interannual fluctuations at the long-term sites revealed substantial demographic variability influenced by site-specific environmental conditions. These findings offer reference baselines for Mediterranean trout populations and contribute to the ecological basis for their conservation and management. Full article

(1) Background: Soccer action recognition (SAR) is essential in modern sports analytics, supporting automated performance evaluation, tactical strategy analysis, and detailed player behavior modeling. Although recent advances in deep learning and computer vision have enhanced SAR capabilities, many existing methods remain limited to coarse-grained classifications, grouping actions into broad categories such as attacking, defending, or goalkeeping. These models often fall short in capturing fine-grained distinctions, contextual nuances, and long-range temporal dependencies. Transformer-based approaches offer potential improvements but are typically constrained by the need for large-scale datasets and high computational demands, limiting their practical applicability. Moreover, current SAR systems frequently encounter difficulties in handling occlusions, background clutter, and variable camera angles, which contribute to misclassifications and reduced accuracy. (2) Methods: To overcome these challenges, we propose TAT-SARNet, a structured framework designed for accurate and fine-grained SAR. The model begins by applying Sparse Dilated Attention (SDA) to emphasize relevant spatial dependencies while mitigating background noise. Refined spatial features are then processed through the Split-Stream Feature Processing Module (SSFPM), which separately extracts appearance-based (RGB) and motion-based (optical flow) features using ResNet and 3D CNNs. These features are temporally refined by the Multi-Granular Temporal Processing (MGTP) module, which integrates ResIncept Patch Consolidation (RIPC) and Progressive Scale Construction Module (PSCM) to capture both short- and long-range temporal patterns. The output is then fused via the Context-Guided Dual Transformer (CGDT), which models spatiotemporal interactions through a Bi-Transformer Connector (BTC) and Channel–Spatial Attention Block (CSAB); (3) Results: Finally, the Cascaded Temporal Classification (CTC) module maps these features to fine-grained action categories, enabling robust recognition even under challenging conditions such as occlusions and rapid movements. (4) Conclusions: This end-to-end architecture ensures high precision in complex real-world soccer scenarios. Full article

To accommodate the integration of emerging energy sources such as wind and solar power, hydroelectric units are increasingly required to operate across a broader range of conditions. This operational expansion often leads to elevated pressure pulsations within turbines under non-design conditions, resulting in intensified hydraulic vibrations and, in some cases, structural damage and overall stability concerns. In this study, the Shear Stress Transport (SST) k-ω turbulence model is employed to perform unsteady numerical simulation calculation of a Francis-99 mixed-flow model turbine operating at a head of 400 m. Simulations are conducted for three operating regimes: low-flow and low-load conditions, optimal conditions, and high-flow and high-load conditions. Internal flow in the full flow channel of the turbine and pressure pulsation in the full flow channel components is systematically analyzed. The findings indicate that under low-flow and low-load conditions, the ability of the runner blades to constrain the water flow is significantly decreased. Across all three operational scenarios, the dominant pressure pulsation frequencies observed in both the stationary and guide vane are 30f_n, primarily influenced by dynamic and static disturbance caused by the rotation of the runner’s long and short blades. In low-flow and low-load conditions, a low-frequency component at 0.2f_n, due to the existence of vortices in the draft tube, exhibits the highest amplitude—up to 0.6%—in the straight cone section. Within the runner, pressure pulsation frequencies are predominantly associated with the rotation of the guide vane. Conversely, the draft tube region is characterized by frequency components related to both the runner’s dynamic-static interaction at 30f_n and vortex-induced pulsations at 0.2f_n. Full article

Flow past bluff bodies (e.g., circular cylinders) forms a canonical context for teaching external flow separation, vortex shedding, and the coupling between surface pressure and hydrodynamic forces in offshore engineering. Conventional laboratory implementations, however, often fragment local and global measurements, delay data feedback, and omit intelligent modeling components, thereby limiting the development of higher-order cognitive skills and data literacy. We present a low-cost, modular, data-enabled instructional hydrodynamics platform that integrates a transparent recirculating water channel, multi-point synchronous circumferential pressure measurements, global force acquisition, and an artificial neural network (ANN) surrogate. Using feature vectors composed of Reynolds number, angle of attack, and submergence depth, we train a lightweight AI model for rapid prediction of drag and lift coefficients, closing a loop of measurement, prediction, deviation diagnosis, and feature refinement. In the subcritical Reynolds regime, the measured circumferential pressure distribution for a circular cylinder and the drag and lift coefficients for a rectangular cylinder agree with empirical correlations and published benchmarks. The ANN surrogate attains a mean absolute percentage error of approximately 4% for both drag and lift coefficients, indicating stable, physically interpretable performance under limited feature inputs. This platform will facilitate students’ cross-domain transfer spanning flow physics mechanisms, signal processing, feature engineering, and model evaluation, thereby enhancing inquiry-driven and critical analytical competencies. Key contributions include the following: (i) a synchronized local pressure and global force dataset architecture; (ii) embedding a physics-interpretable lightweight ANN surrogate in a foundational hydrodynamics experiment; and (iii) an error-tracking, iteration-oriented instructional workflow. The platform provides a replicable pathway for transitioning offshore hydrodynamics laboratories toward an integrated intelligence-plus-data literacy paradigm and establishes a foundation for future extensions to higher Reynolds numbers, multiple body geometries, and physics-constrained neural networks. Full article

The construction of cascade dam systems profoundly reshapes river hydrological processes, yet the analysis of their spatial heterogeneity effects has long been constrained by the mechanistic deficiencies and interpretability limitations of traditional mechanistic models. Focusing on the middle-lower Han River (a 652 km reach regulated by seven dams) as a representative case, this study develops an LSTM-Attention-SHAP interpretable framework to achieve, for the first time, intelligent decoupling of dam-induced hydrological effects and mechanistic analysis of spatial differentiation. Key findings include the following: (1) The LSTM model demonstrates exceptional predictive performance of water level and flow rate in intensively regulated reaches (average Nash–Sutcliffe Efficiency, NSE = 0.935 at Xiangyang, Huangzhuang, and Xiantao stations; R² = 0.988 for discharge at Xiantao Station), while the attention mechanism effectively captures sensitive factors such as the abrupt threshold (>560 m³/s) in the Tangbai River tributary; (2) Shapley Additive exPlanations (SHAP) values reveal spatial heterogeneous dam contributions: the Cuijiaying Dam increases discharge at Xiangyang station (mean SHAP +0.22) but suppresses water level at Xiantao station (mean SHAP −0.15), whereas the Wangfuzhou Dam shows a stable negative correlation with Xiangyang water levels (mean SHAP −0.18); (3) dam operations induce cascade effects through altered channel storage capacity. These findings provide spatially adaptive strategies for flood risk zoning and ecological operations in globally intensively regulated rivers such as the Yangtze and Mekong. Full article

Automated defect detection for printed fabric manufacturing faces critical challenges in balancing industrial-grade accuracy with real-time deployment efficiency. To address this, we propose RT-DETR-FFD, a knowledge-distilled detector optimized for printed fabric defect inspection. Firstly, the student model integrates a Fourier cross-stage mixer (FCSM). This module disentangles defect features from periodic textile backgrounds through spectral decoupling. Secondly, we introduce FuseFlow-Net to enable dynamic multi-scale interaction, thereby enhancing discriminative feature representation. Additionally, a learnable positional encoding (LPE) module transcends rigid geometric constraints, strengthening contextual awareness. Furthermore, we design a dynamic correlation-guided loss (DCGLoss) for distillation optimization. Our loss leverages masked frequency-channel alignment and cross-domain fusion mechanisms to streamline knowledge transfer. Experiments demonstrate that the distilled model achieves an mAP@0.5 of 82.1%, surpassing the baseline RT-DETR-R18 by 6.3% while reducing parameters by 11.7%. This work establishes an effective paradigm for deploying high-precision defect detectors in resource-constrained industrial scenarios, advancing real-time quality control in textile manufacturing. Full article

Family structure has long been regarded as an important determinant of household saving, yet the empirical evidence for developing economies remains limited. Using the 2018–2022 panels of the China Family Panel Studies (CFPS), a nationwide survey that follows 16,519 households across three waves, the present study investigates how family size, the elderly share, and the child share jointly shape saving behavior. A household fixed effects framework is employed to control for time-invariant heterogeneity, followed by a sequential endogeneity strategy: external-shock instruments are tested and rejected, lagged two-stage least squares implement internal instruments, and a dynamic System-GMM model is estimated to capture saving persistence. Robustness checks include province-by-year fixed effects, inverse probability weighting for attrition, balanced-panel replication, alternative variable definitions, lag structures, and sample filters. Family size raises the saving rate by 4.6 percentage points in the preferred dynamic specification (p < 0.01). The elderly ratio remains insignificant throughout, whereas the child ratio exerts a negative but model-sensitive association. A three-path mediation analysis indicates that approximately 26 percent of the total family size effect operates through scale economy savings on quasi-fixed expenses, 19 percent is offset by resource dilution pressure, and less than 1 percent flows through a precautionary saving channel linked to income volatility. These findings extend the resource dilution literature by quantifying the relative strength of competing mechanisms in a middle-income context and showing that cost-sharing economies dominate child-related dilution for most households. Policy discussion highlights the importance of public childcare subsidies and targeted credit access for rural parents, whose saving capacity is the most constrained by additional children. The study also demonstrates that fixed effects estimates of family structure can be upward-biased unless dynamic saving behavior and internal instruments are considered. Full article