Search Results (1,340)

To solve common defects such as warpage deformation, interface debonding, and uneven filling during the two-color injection molding of medical goggles while meeting their multi-performance requirements, including high light transmittance, impact resistance, chemical corrosion resistance, and structural stability, this study conducts research on the process optimization of two-color injection molding. Firstly, based on the principle of material compatibility and Moldflow simulation, a suitable material combination was selected: the first-shot frame adopts Apec 1745 PC material, and the second-shot lens uses Makrolon 2858 PC material, which effectively avoids the risk of interface non-fusion. Subsequently, a high-precision 3D simulation model was established using Moldflow software, and the injection sequence of “frame first, lens second” was optimized and determined. A gating system with double-gate (for the frame) and single-gate side feeding (for the lens), as well as a cooling system with an 8 mm diameter, was designed, and all key indicators of mesh quality meet the simulation requirements. Taking the mold and melt temperatures, holding pressures, and holding times of the two shots as design variables and warpage deformation as the optimization objective, sample data were obtained through an L₃₂ (7⁴) orthogonal test. A BP neural network was constructed to describe the nonlinear relationship between parameters and quality, and the Sparrow Search Algorithm (SSA) was combined to optimize the weights and thresholds of the network, forming a BP-SSA intelligent optimization model. The results show that the mean absolute percentage error (MAPE) of the proposed model is only 2.28%, which is significantly better than that of the single BP neural network (14.36%). The optimal process parameters obtained by optimization are a mold temperature of 130 °C, first-shot melt temperature of 311 °C, second-shot melt temperature of 310 °C, first-shot holding pressure of 83 MPa, second-shot holding pressure of 70 MPa, first-shot holding time of 14 s, and second-shot holding time of 8 s. Simulation and mold test verification indicate that after optimization, the warpage deformation of the goggles is reduced to 0.8956 mm (simulation) and 0.944 mm (measured), with a relative error of only 5.4%, which is 67.9% lower than the initial simulation result. The integrated method of “material selection—CAE simulation—orthogonal test—BP-SSA intelligent optimization” proposed in this study provides technical support for the high-precision manufacturing of thin-walled transparent multi-material medical products. Full article

Reliable fault detection along transmission corridors is essential for preventing small defects from developing into long outages and costly emergency operations. This study aims to improve the field reliability of an open vocabulary vision language backbone without retraining the large model in an end-to-end manner. The work focuses on four operational fault classes in multi-region corridor imagery collected during routine inspections and uses a Florence-2 vision language model as the base recognizer. On top of this backbone, three domain-specific components are introduced. A subclass-aware fusion scheme keeps probability mass within the active parent concept so that insulator icing and conductor icing produce stable, action-oriented decisions. A Power-Line Focus Then Crop normalization uses an attention-guided corridor window together with isotropic resizing so that thin conductors and small fittings remain visible in the processed image. A corridor geo prior reduces scores as the distance from the mapped centerline increases and in this way suppresses detections that lie outside the corridor. All methods are evaluated under a shared preprocessing and scoring pipeline in training-free and parameter-efficient tuning modes. Experiments on unseen regions show higher accuracy for skinny and low-contrast faults, fewer false alarms outside the right-of-way, and improved score calibration in the confidence range used for triage, while keeping throughput and memory usage suitable for unmanned aerial vehicles and substation edge devices. Full article

Unmanned Aerial Vehicles provide a cost-effective solution for water environment monitoring, yet detecting floating litter remains challenging due to small target scales, complex geometries, and severe surface interferences. To bridge the data deficiency in this domain, this study introduces UAV-Flow, a multi-scenario benchmark dataset wherein small-scale targets constitute 78.9%. Building upon this foundation, we propose the Floating Litter Detection Network (FLD-Net), a lightweight, real-time detection framework tailored for edge deployment. Adopting a progressive optimization paradigm, FLD-Net integrates three cascaded enhancement modules to achieve holistic performance gains across feature extraction, cross-scale fusion, and noise suppression. Specifically, the Deformation Feature Extraction Module (DFEM) enhances backbone adaptability to small targets and non-rigid deformations; the Dynamic Cross-scale Fusion Network (DCFN) facilitates efficient cross-scale semantic fusion via content-aware upsampling and an asymmetric topology; and the Dual-domain Anti-noise Attention (DANA) mechanism achieves discriminative decoupling between target semantics and structural noise through spatial-channel interaction. Experimental results on UAV-Flow demonstrate that FLD-Net achieves an mAP${}_{50}$ of 80.47%. Compared to the YOLOv11s baseline, it improves Recall and mAP${}_{50}$ by 11.66% and 8.51%, respectively, with only 9.9 M parameters. Furthermore, deployment on the NVIDIA Jetson Xavier NX yields an inference latency of 14 ms and an energy efficiency of 4.80 FPS/W, confirming the system’s robustness and viability for automated pollution monitoring. Full article

This paper presents an orthogonal-heading wavelength-resolution SAR (WRSAR) target detection framework that fuses multi-heading image stacks for foliage-penetrating (FOPEN) vehicle detection. First, a low-rank–sparse decomposition is applied to very-high-frequency (VHF), ultra-wideband (UWB) WRSAR stacks to suppress vegetation clutter and enhance target contrast. The clutter-suppressed sparse stacks acquired from orthogonal headings are then fused to enrich target scattering characteristics. Finally, a Rayleigh-entropy statistic computed on the fused sparse stack is used to represent discontinuous positional changes. Based on the non-negative nature of WRSAR amplitudes for both clutter and FOPEN targets, we introduce a non-negative constrained tensor robust principal component analysis (NCTRPCA) to improve sparsity in the stack components. Furthermore, since Shannon differential entropy has no tunable parameter, we replace Shannon entropy with RE in this work and derive its closed-form expression for the proposed detector. Experiments on the publicly available multi-heading, multi-temporal CARABAS II dataset show that the proposed orthogonal-heading WRSAR fusion achieves higher FOPEN vehicle detection performance than recent state-of-the-art methods while maintaining moderate computational cost. Full article

Numerical weather prediction (NWP) models are essential for precipitation forecasting but are constrained by coarse spatial resolutions (10–50 km), which fail to capture fine-scale variations required for regional disaster prevention, particularly in complex terrain. While statistical and machine learning downscaling methods have been developed to bridge this resolution gap, they predominantly operate as “black boxes” without explicit physical guidance, leading to predictions that violate meteorological principles and systematic underestimation of extreme precipitation events. To address these limitations, this study aims to develop a Physics-Informed Machine Learning framework that explicitly integrates multi-scale topographic modulation and physical consistency constraints into precipitation downscaling. Specifically, a Random Forest model enhanced with Multi-Scale Structural Similarity (MS-SSIM) loss and Physical Constraint Enhancement (MSSSIM-PCE-RF) was constructed. The model introduces elevation gradient weights at low-resolution layers and micro-topographic parameters (slope, surface roughness) at high-resolution layers, while enforcing physical consistency between precipitation intensity, radar reflectivity, and ground observations via the Z-R relationship. Based on hourly data from 2252 meteorological stations in Jiangxi Province (2021–2022), coupled with topographic factors (DEM, slope, aspect) and Normalized Difference Vegetation Index (NDVI), a technical framework of “data fusion–feature synergy–machine learning–spatial reconstruction” was established. Results demonstrate that the MSSSIM-PCE-RF model achieves a validation R² of 0.9465 and RMSE of 0.1865 mm, significantly outperforming the conventional RF model (R² = 0.9272). Notably, errors in high-altitude, steep-slope, and high-vegetation areas are reduced by 45.3%, 42.0%, and 43.1%, respectively, with peak precipitation period errors decreasing by 37.2%. Multi-scale topographic analysis reveals significant orographic lifting effects at 250–1000 m elevations, peak precipitation at 12–15° slopes, and abundant precipitation on south/southeast aspects. By explicitly embedding topographic modulation and physical consistency constraints, the model effectively alleviates systematic underestimation of extreme precipitation in complex terrain, providing high-resolution data support for transmission line disaster prevention and micro-meteorological risk assessment. Full article

To address the limited detection accuracy of casting defects—including pores, inclusions, and looseness—in digital radiography (DR) images, which stems from their small scale, high morphological variability, and interference from complex background textures, we propose MTS-YOLOv11: an edge–discrepancy collaborative defect detection framework tailored for casting DR imagery. Built upon YOLOv11, MTS-YOLOv11 incorporates three key innovations: (1) a Multi-Scale Edge Information Enhancement System (MSEES), integrated into the C3K2 module of the backbone network, to strengthen discriminative feature extraction for minute defects; (2) a TripletAttention mechanism embedded in high-level backbone stages to jointly calibrate channel–spatial dependencies and suppress texture-induced spurious responses under complex backgrounds; (3) a Scale-Discrepancy-Aware Gated Fusion (SDAGFusion) module positioned immediately before the detection head, enabling scale-discrepancy-aware gated fusion of multi-scale features, emphasizing defect regions while suppressing background interference. Experimental results show that on the casting DR dataset, MTS-YOLOv11 achieves mAP@0.5 = 96.5% and mAP@0.5:0.95 = 68.5%—improvements of 1.3 and 1.2 percentage points over the baseline YOLOv11—across all three defect categories. Moreover, on the same platform, MTS-YOLOv11 achieves an inference speed of 359.07 FPS, compared with 346.86 FPS for the baseline. Meanwhile, the model has 2.72M parameters and 7.8G FLOPs. These results indicate a consistent improvement in detection accuracy while maintaining a practical balance between precision and computational efficiency. Moreover, cross-dataset generalization tests on newly acquired industrial DR data show that MTS-YOLOv11 consistently outperforms the baseline across evaluation metrics, suggesting improved robustness to unseen imaging conditions and supporting its potential for real-world foundry inspection. Full article

Accurate plant recognition in desert grasslands is essential for ecological monitoring, yet existing models face critical limitations: poor generalization in complex natural environments and excessive computational demands for mobile deployment. This study proposes YOLOv11-PKD, a lightweight model integrating structured pruning and knowledge distillation for efficient desert grassland plant identification. First, we develop YOLOv11-STC, a high-capacity teacher model incorporating the SPPCSPC module for multi-scale feature extraction, Triplet Attention for spatial refinement, and a GSConv-based Slim Neck for optimized feature fusion. This architecture achieves 88.3% mAP50 on the DGPlant48 dataset, outperforming the baseline YOLOv11n by 6.8%. To enable edge deployment, we apply channel pruning guided by BatchNorm scaling factors, compressing the model by 19.75% in PParameters and 20% in GFLOPS (YOLOv11-Pruned: 79.5% mAP50, 4.7 MB). Subsequently, L2-based knowledge distillation recovers performance, yielding YOLOv11-PKD with 87.9% mAP50—approaching teacher-level accuracy—while maintaining 5.0 MB size, 2.150 M parameters, and 5.5 GFLOPS. The model is successfully deployed via a mobile application, achieving ~1 s response times for field-based plant identification. This work demonstrates a practical balance between accuracy and efficiency for resource-constrained ecological monitoring. Full article

The detection of underwater organisms represents a particularly challenging frontier within the field of computer vision. This paper proposes an underwater organism detection algorithm named the Enhanced Feature Extraction-based Underwater Organism Detection Network (EFE_UODNet). Firstly, this paper designs an Enhanced Global Context Guided Feature (EGCGF) module to extract organism feature information in a serial interaction manner, thereby enhancing the feature extraction capability for blurred organisms in low-quality underwater images. Secondly, this paper proposes an Advanced Multi-Scale Fusion Pyramid Network (AM-FPN) to achieve multi-level feature fusion. EFE_UODNet uses high-level features as weights and combines channel attention with spatial attention to fuse low-level information with high-level features. Finally, the Dynamic Head (DyHead) is introduced to better utilize the features output by AM-FPN, thereby improving detection performance in underwater scenes involving dense and highly similar targets. Experimental results on the DUO dataset demonstrate that the proposed EFE_UODNet model, using YOLOv8m as the baseline, achieves significant improvements across multiple metrics. These improvements include a 2.3% increase in Precision, 3.5% in Recall, 2.1% in F1-score, 3.5% in mAP[50–95], and 1.3% in mAP50. These accuracy gains are achieved while ensuring that inference time and parameter count still meet the real-time and resource requirements of this work. Additionally, its generalization ability is validated on the URPC2019 dataset. Compared to other underwater organism detection algorithms, the proposed model delivers outstanding overall performance on this task. Full article

Astronomical spectra, which encode rich astrophysical and chemical information, are fundamental to understanding celestial objects and universal laws. The advent of large-scale spectroscopic surveys, generating tens of millions of spectra, presents significant challenges for efficient data processing and analysis. To address these challenges, we develop an AI-powered platform (named “SpecZoo”) for spectral visualization and analysis. This platform integrates modern information technology and machine learning to lower the barrier to spectral data utilization and enhance research efficiency. Its core functionalities include interactive visualization, automated spectral classification, physical parameter measurement, spectral annotation, and multi-band/multi-modal data fusion, all supported by flexible user and data management systems. It has become an essential tool for the National Astronomical Data Center, directly supporting spectral data processing and research for major projects including LAMOST, SDSS, DESI, and so on. Furthermore, the platform demonstrates strong potential for science-education integration, providing a novel resource for cultivating talent in astronomy and data science. Full article

In high-speed parachuting, complex turbulent phenomena (i.e., deadly vortices) may cause problems such as parachute inflation delay or even deployment failure. To address these issues, this study develops a high-precision numerical simulation dummy model in which adaptive mesh generation techniques, combined with Euler–Lagrange bidirectional coupling based on a large eddy simulation, are employed to model the multiphase flow field during parachute descent. The key parameters are adjusted, and the numerical model is refined based on wind tunnel experiments and User-Defined Functions. The bidirectional validation of the experimental and simulated data reveals the mechanism of turbulent flow formation and its evolutionary patterns around the parachutist–parachute system for different lateral and descent velocities during the high-speed descent phase. A prediction model based on a multi-information fusion neural network algorithm is further established to address the challenge in special parachuting scenarios whereby vortices in the flow field around the parachutist prevent the parachute from opening. The model integrates the Haar wavelet to extract global low-frequency features that characterize the overall structure and trends, an energy valley optimization algorithm, a convolutional neural network, a bidirectional long short-term memory network, and a self-attention mechanism to achieve one-second-ahead turbulence prediction. With nine physical quantities as inputs and descent velocity as the output indicator, the model has a Root Mean Square Error of 0.085, a Mean Absolute Error of 0.051, and a Mean Absolute Percentage Error of 0.0021. Full article

To advance automatic tomato leaf disease detection in precision agriculture, this study addresses critical challenges in complex field environments, such as variable lesion scales, background interference, and deployment constraints. We propose MSP-Net, a task-driven detection framework with targeted architectural refinements integrating three specific optimizations. First, a Multi-Scale Perception Convolution Module (MSPCM) is introduced to capture diverse disease features across early-to-late infection stages. Second, SimAM-enhanced C3k2 layers are utilized to suppress background noise and focus on fine-grained lesion cues. Third, a Multi-Scale Feature Enhancement Module (MSFEM) bridges the semantic gap between shallow and deep features to improve fusion efficacy. Furthermore, we construct a lightweight variant, L-MSP-Net, using architectural migration and structured pruning for edge efficiency. Experimental results on the real-world Tomato-Village dataset show that MSP-Net achieves 92.0% mAP@0.5, outperforming the YOLOv11s baseline by 2.0%. L-MSP-Net attains 86.1% mAP@0.5, improving by 3.6% over the lightweight YOLOv11n baseline while reducing parameters by 10.5%, and is successfully deployed on the RK3588 edge platform. Additional cross-dataset experiments on PASCAL VOC and MS COCO evaluate the transferability of the proposed architectural refinements to generic object detection tasks. Full article

In the manufacturing of high-reliability components, sinusoidal wobble laser welding has gained preference due to its excellent performance. However, surface defect inspection for such welds is challenged by large variations in defect scales, the coexistence of multiple defects, and scarce samples, which collectively limit existing detection methods. To address these issues, this paper proposes a lightweight detection framework that integrates a generative adversarial network with an improved YOLO architecture. First, a frequency-domain-enhanced StyleGAN2-AFMS model is constructed to effectively augment high-quality defect samples. Second, a YOLO11n-WAFE detector is designed, which incorporates an ADownECA downsampling module to enhance the capability of capturing subtle defects and an Edge-Aware Semantic–Detail Fusion module to improve discriminative robustness under multi-defect conditions. To validate the approach, an industrial-level Sinusoidal Wobble Laser Weld Defect Dataset is built. Experiments reveal that the proposed framework boosts mAP@0.5 to 94.2% (an 8% improvement over the baseline) and mAP@0.5:0.95 to 77.4%, with an F1-score of 89.5%, while maintaining lightweight (2.15 M parameters) and fast (656 FPS) characteristics. This study provides a high-precision and efficient solution for few-shot industrial defect inspection. Full article

Powder-bed arc additive manufacturing (PBAAM) may reduce the cost of powder-bed metal additive manufacturing and enable thicker layers than laser powder bed fusion (LPBF), but melt-track stability limits are not well established. Here, 316L stainless steel powder (15–53 µm) was melted by a TIG-based arc in a custom powder-bed system while varying current, travel speed, layer thickness and hatch distance. Single tracks on an inclined bed (≈0–0.4 mm thickness) were used to identify continuity loss and melt-pool width, quantified from top-view images via width profiles, a gap-based continuity metric and the coefficient of variation. Parallel-track tests at 0.15, 0.20 and 0.25 mm layer thickness with hatch distances set to 25%, 50% and 75% of the measured melt-pool width assessed inter-track bonding and lack of fusion, and selected parameters were validated in five-layer builds. Higher current with low-to-moderate travel speeds produced wider, more stable melt pools on the inclined bed. Hatch ratios of 25–50% were the most effective for sustaining fusion in single layers and multi-layer builds, whereas 75% promoted unbonded regions and narrow-track morphologies. Overall, PBAAM can process substantially thicker layers with relatively simple equipment, but requires a narrow, carefully tuned window to balance continuity, fusion and heat accumulation. Full article

With the increasing adoption of intelligent inspection systems for substation equipment, massive amounts of data are being generated. To address the challenge of balancing detection accuracy and lightweight deployment in current object detection models, this paper proposes YOLOv10-SPD (Substation Power Defect), a high-precision yet lightweight improved model tailored for substation defect detection. Compared to existing methods, the proposed model introduces multiple innovations in structural design and module fusion. (1) A Feature Modulation Module is proposed to significantly enhance the model’s ability to perceive and model defect details. (2) A hybrid module integrating structural information and channel attention is designed to efficiently reconstruct and represent feature maps. (3) A Multi-Scale Context Modeling Module is developed, leveraging shared convolutional kernels to achieve compact expression of multi-scale semantic information. (4) An Efficient Detection Head adopts a hierarchical semantic fusion strategy, further improving recognition accuracy for small and multi-scale targets. (5) A Weight-Magnitude-Based Hierarchical Pruning Strategy is introduced to compress model size and boost inference efficiency while maintaining accuracy. Experiments on a public substation defect dataset demonstrate that the proposed method achieves 94.11% mAP@0.5, outperforming the baseline YOLOv10n by 5.14%, while reducing model parameters by 76.09% and computational costs by 38.82%. The model achieves higher detection accuracy with lower computational overhead, effectively meeting the requirements for efficient and accurate substation defect detection, demonstrating strong practical applicability. Full article

The main aim of this study was to evaluate the applicability of a low-cost, double-wall gas metal arc welding (GMAW)-based wire arc additive manufacturing (WAAM) process for aluminum alloy AlMg5, with an emphasis on microstructural heterogeneity, layer-dependent defect formation, and their implications for mechanical performance and geometric characteristics. A Taguchi L9 (3³) design of experiments was employed to investigate the influence of welding current (40–60 A), shielding gas flow (10–20 L/min), and arc correction (0–40%) on wall geometry, material utilization, and overall process quality through multi-response optimization. The optimal parameter set (60 A, 15 L/min, 0% arc correction) resulted in a 54.9% improvement in the Grey Relational Grade compared to the lowest-performing configuration. Metallographic analysis revealed heterogeneous grain evolution governed by the multilayer thermal history, with porosity levels ranging from 3.20% to 3.49% and lack-of-fusion defects preferentially concentrated in interlayer and mid-height regions. The fabricated high-wall structure exhibited hardness values between 72 and 85 HV and an average ultimate tensile strength of 175 MPa. The observed mechanical scatter was consistent with localized microstructural heterogeneity and spatial defect distribution. The results demonstrate that geometric evaluation alone is insufficient as a quality metric for WAAM components and must be complemented by metallographic integrity assessment. Overall, the study highlights the importance of direct parameter optimization in double-wall WAAM structures to mitigate defect formation and enhance mechanical reliability under industrially accessible deposition conditions. Full article