Search Results (673)

To address the issue of agricultural robot loss of control caused by GNSS signal degradation or loss in complex agricultural environments such as farmland and orchards, this study proposes a neural network-based SLAM/GNSS fusion localization algorithm aiming to enhance the robot’s localization accuracy and stability in weak or GNSS-denied environments. It achieves multi-sensor observed pose coordinate system unification through coordinate system alignment preprocessing, optimizes SLAM poses via outlier filtering and drift correction, and dynamically adjusts the weights of poses from distinct coordinate systems via a neural network according to the GDOP. Experimental results on the robotic platform demonstrate that, compared to the SLAM algorithm without pose optimization, the proposed SLAM/GNSS fusion localization algorithm reduced the whole process average position deviation by 37%. Compared to the fixed-weight fusion localization algorithm, the proposed SLAM/GNSS fusion localization algorithm achieved a 74% reduction in average position deviation during transitional segments with GNSS signal degradation or recovery. These results validate the superior positioning accuracy and stability of the proposed SLAM/GNSS fusion localization algorithm in weak or GNSS-denied environments. Orchard experimental results demonstrate that, at an average speed of 0.55 m/s, the proposed SLAM/GNSS fusion localization algorithm achieves an overall average position deviation of 0.12 m, with average position deviation of 0.06 m in high GNSS signal quality zones, 0.11 m in transitional sections under signal degradation or recovery, and 0.14 m in fully GNSS-denied environments. These results validate that the proposed SLAM/GNSS fusion localization algorithm maintains high localization accuracy and stability even under conditions of low and highly fluctuating GNSS signal quality, meeting the operational requirements of most agricultural robots. Full article

This study evaluated the effect of various adhesive systems, particularly silane application, on the repair bond strength of a nanofill resin composite and associated stress distribution using finite element analysis (FEA). A total of 105 composite specimens (4 × 6 mm) were aged by thermal cycling (10,000 cycles), roughened, etched with phosphoric acid, and assigned to seven groups (n = 15): G1. control—no adhesive; G2. Single Bond Universal Adhesive; G3. composite primer; G4. PQ1; G5. Silane + PQ1; G6. Clearfil Universal Bond; G7. All-Bond Universal. Shear bond strength was measured using a universal testing machine (1 mm/min), and failure modes were microscopically classified. FEA was conducted under static and fatigue conditions using 3D models built in Fusion-360. Mechanical properties were obtained from technical data and the literature. A 300 N load was applied and contact detection (0.05 mm) and constraint zones were defined. Statistical analysis was performed using one-way ANOVA and Tukey’s HSD (p = 0.05). Pearson’s correlation was used to assess the relationship between bond strength and von Mises stress. The highest bond strength was found in G2 (21.54 MPa) while G1 showed the lowest (8.86 MPa). Silane-treated groups exhibited favorable stress distribution and a strong correlation between experimental and simulated outcomes. Silane applications significantly enhance composite repair performance. Full article

Traditional collision risk warning methods primarily focus on vehicle-to-vehicle collisions, neglecting conflicts between vehicles and vulnerable road users (VRUs) such as pedestrians, while the difficulty in predicting pedestrian trajectories further limits the accuracy of collision warnings. To address this problem, this study proposes a vehicle-to-everything-based (V2X) multi-fusion vehicle–pedestrian collision warning method, aiming to enhance the traffic safety protection for VRUs. First, Unmanned Aerial Vehicle aerial imagery combined with the YOLOv7 and DeepSort algorithms is utilized to achieve target detection and tracking at unsignalized intersections, thereby constructing a vehicle–pedestrian interaction trajectory dataset. Subsequently, key foundational modules for collision warning are developed, including the vehicle trajectory module, the pedestrian trajectory module, and the risk detection module. The vehicle trajectory module is based on a kinematic model, while the pedestrian trajectory module adopts an Attention-based Social GAN (AS-GAN) model that integrates a generative adversarial network with a soft attention mechanism, enhancing prediction accuracy through a dual-discriminator strategy involving adversarial loss and displacement loss. The risk detection module applies an elliptical buffer zone algorithm to perform dynamic spatial collision determination. Finally, a collision warning framework based on the Monte Carlo (MC) method is developed. Multiple sampled pedestrian trajectories are generated by applying Gaussian perturbations to the predicted mean trajectory and combined with vehicle trajectories and collision determination results to identify potential collision targets. Furthermore, the driver perception–braking time (TTM) is incorporated to estimate the joint collision probability and assist in warning decision-making. Simulation results show that the proposed warning method achieves an accuracy of 94.5% at unsignalized intersections, outperforming traditional Time-to-Collision (TTC) and braking distance models, and effectively reducing missed and false warnings, thereby improving pedestrian traffic safety at unsignalized intersections. Full article

The laser heterogeneous lap welding of nickel-plated steel and Cu sheets has been investigated in this study. The YAG (Yttrium-Aluminum-Garnet) laser beam only penetrates the upper Ni-plated steel sheet and cannot weld the bottom Cu sheet due to the low absorption coefficient of the YAG laser beam. Incorporating a blue-light and fiber laser into the coaxial laser beam significantly improves the quality of the weld fusion zone. The fiber laser beam can penetrate the upper nickel-plated steel sheet, and the blue-light laser beam can melt the bottom copper sheet. Introducing the blue-light laser to the coaxial laser beams overcomes the low reflectivity of the bottom copper sheet. The fiber/blue-light coaxial laser continuous welding can achieve the best integrity and defect-free welding. It shows potential in the mass production of the next generation of lithium batteries. Full article

Timely and accurate identification of plant diseases is critical to mitigating crop losses and enhancing yield in precision agriculture. This paper proposes AgriFusionNet, a lightweight and efficient deep learning model designed to diagnose plant diseases using multimodal data sources. The framework integrates RGB and multispectral drone imagery with IoT-based environmental sensor data (e.g., temperature, humidity, soil moisture), recorded over six months across multiple agricultural zones. Built on the EfficientNetV2-B4 backbone, AgriFusionNet incorporates Fused-MBConv blocks and Swish activation to improve gradient flow, capture fine-grained disease patterns, and reduce inference latency. The model was evaluated using a comprehensive dataset composed of real-world and benchmarked samples, showing superior performance with 94.3% classification accuracy, 28.5 ms inference time, and a 30% reduction in model parameters compared to state-of-the-art models such as Vision Transformers and InceptionV4. Extensive comparisons with both traditional machine learning and advanced deep learning methods underscore its robustness, generalization, and suitability for deployment on edge devices. Ablation studies and confusion matrix analyses further confirm its diagnostic precision, even in visually ambiguous cases. The proposed framework offers a scalable, practical solution for real-time crop health monitoring, contributing toward smart and sustainable agricultural ecosystems. Full article

Currently, the determination of the molten zone thickness in HDPE pipes during butt fusion welding primarily depends on experimental and numerical methods, leading to high costs and reduced efficiency. In this study, a mathematical (MM) model based on Neumann’s solution for the melting of a semi-infinite region was developed to efficiently predict the average molten zone (AMZ) thickness of HDPE pipes under varying heating temperatures and heating times while incorporating the effects of heat convection. Additionally, a two-dimensional CFD model was constructed using finite element analysis (FEA) to validate the MM model. Welding pressure was not considered in this study. The effects of heating temperature, heating time, and heat convection on the AMZ thickness in HDPE pipes were systematically analyzed. The heating temperature at the heated end of HDPE ranged from 190 °C to 350 °C in 20 °C increments, with a temperature of 28 °C as the ambient and initial setting, and the heating time was set to 180 s for both the MM and CFD models. The results demonstrate a strong correlation between the AMZ thickness predictions from the MM and CFD models. The relative error between the MM and CFD models ranges from 0.280% to 10,830% with heat convection and from −2.398% to 8.992% without heat convection. Additionally, for the MM model, the relative error between cases with and without heat convection ranges from 0.243% to 0.433%, whereas for the CFD model, it varies between 1.751% and 3.189%. These findings confirm the reliability of the MM model developed in this study and indicate that thermal convection has a minimal impact on AMZ thickness prediction for large-diameter, thick-walled HDPE pipes. Full article

An ultra-high-strength press-hardening steel (PHS) and a high-strength dual-phase steel (DP) were butt-joined by the gas metal arc welding (GMAW) process, aiming to assess the effects of a high heat input welding process on the structure-property relationship and residual stress. The post-weld microstructure, the microhardness profile, the tensile behavior, and the experimentally obtained residual stresses (by x-ray diffraction) of the steels in dissimilar (PHS-DP) and similar (PHS-PHS, DP-DP) pair combinations have been analyzed. Results indicated that the ultimate tensile strength (UTS) of the dissimilar pair PHS-DP achieves a similar strength to the DP-DP joint, whereas the elongation was similar to that of the PHS-PHS weldment. The failure location of the tensile specimens was expected and systematically observed at the tempered and softer sub-critical heat-affected zone (SC-HAZ) in all welded conditions. Compressive residual stresses were consistently observed along the weldments in all specimens; the more accentuated negative RS were measured in the PHS joint attributed to the higher volume fraction of martensite; furthermore, the negative RS measured in the fusion zone (FZ) could be well correlated to weld restraint due to the sheet anchoring during the welding procedure, despite the presence of predominant ferrite and pearlite microstructures. Full article

The effects of the gas tungsten arc (GTA) welding process on the microstructure and microhardness of two Mg-5Al-3RE and Mg-5Al-5RE experimental alloys (RE—rare earth elements) are presented. Both alloys were gravity-cast in a steel mould and GTA-welded in the same conditions. Analyses of the alloys’ microstructure were carried out by scanning electron microscopy (SEM+EDX) as well as X-ray diffraction (XRD). In as-cast conditions; both alloys were mainly composed of α-Mg; Al₁₁RE₃; and Al₁₀RE₂Mn₇ intermetallic phases. Additionally; α+γ eutectic (where γ is Al₁₂Mg₁₇) in the Mg-5Al-3RE alloy and an Al₂RE phase in the Mg-5Al-5RE material were revealed. The same phase composition was revealed for both alloys after the GTA welding process. The results of the dendrite arm size (DAS) and Vickers microhardness measurements were also described. Both welded materials exhibited an intensive size reduction of the structural constituents after GTA welding. About 75% smaller values of the dendrite arm spacing were revealed in the fusion zones of the investigated materials than in the as-cast conditions. The GTA welding process also influenced the microhardness of the experimental alloys and increased them by about 21% compared to the base metal; which was the consequence of the refinement of the structural constituents. Full article

The southwestern mountainous region of China (SMRC), characterized by complex geological environments, experiences frequent landslide disasters that pose significant threats to local residents. This study focuses on the Qijiang District of Chongqing, where we conduct a systematic evaluation of wavelength and observation geometry effects on InSAR-based landslide monitoring. Utilizing multi-sensor SAR imagery (Sentinel-1 C-band, ALOS-2 L-band, and LUTAN-1 L-band) acquired between 2018 and 2025, we integrate time-series InSAR analysis with geological records, high-resolution topographic data, and field investigation findings to assess representative landslide-susceptible zones in the Qijiang District. The results indicate the following: (1) L-band SAR data demonstrates superior monitoring precision compared to C-band SAR data in the SMRC; (2) the combined use of LUTAN-1 ascending/descending orbits significantly improved spatial accuracy and detection completeness in complex landscapes; (3) multi-source data fusion effectively mitigated limitations of single SAR systems, enhancing identification of small- to medium-scale landslides. This study provides critical technical support for multi-source landslide monitoring and early warning systems in Southwest China while demonstrating the applicability of China’s SAR satellites for geohazard applications. Full article

The unique vegetation in riparian zones is fundamental for various ecological and socio-economic functions in these transitional areas. Sustainable management requires detailed spatial information about the occurring flora. Here, we present a Deep Learning (DL)-based approach for processing multimodal high-resolution remote sensing data (aerial RGB and near-infrared (NIR) images and elevation maps) to generate a classification map of the tidal Elbe and a section of the Rhine River (Germany). The ground truth was based on existing mappings of vegetation and biotope types. The results showed that (I) despite a large class imbalance, for the tidal Elbe, a high mean Intersection over Union (IoU) of about 78% was reached. (II) At the Rhine River, a lower mean IoU was reached due to the limited amount of training data and labelling errors. Applying transfer learning methods and labelling error correction increased the mean IoU to about 60%. (III) Early fusion of the modalities was beneficial. (IV) The performance benefits from using elevation maps and the NIR channel in addition to RGB images. (V) Model uncertainty was successfully calibrated by using temperature scaling. The generalization ability of the trained model can be improved by adding more data from future aerial surveys. Full article

This study addresses the challenges of redundant crop identification features and low computational efficiency in complex agricultural environments, particularly in arid regions. Focusing on the Hexi region of Gansu Province, we utilized the Google Earth Engine (GEE) to integrate Sentinel-2 optical imagery (10 bands) and Sentinel-1 radar data (VV/VH polarization), constructing a 96-feature set that comprises spectral, vegetation index, red-edge, and texture variables. The recursive feature elimination random forest (RF-RFE) algorithm was employed for feature selection and model optimization. Key findings include: (1) Variables driven by spatiotemporal differentiation were effectively selected, with red-edge bands (B5–B7) during the grain-filling stage in August accounting for 56.7% of the top 30 features, which were closely correlated with canopy chlorophyll content (p < 0.01). (2) A breakthrough in lightweight modeling was achieved, reducing the number of features by 69%, enhancing computational efficiency by 62.5% (from 8 h to 3 h), and decreasing memory usage by 66.7% (from 12 GB to 4 GB), while maintaining classification accuracy (PA: 97.69%, UA: 97.20%, Kappa: 0.89). (3) Multi-source data fusion improved accuracy by 11.54% compared to optical-only schemes, demonstrating the compensatory role of radar in arid, cloudy regions. This study offers an interpretable and transferable lightweight framework for precision crop monitoring in arid zones. Full article

A new lift enhancement scheme is designed for the cruise flight process of a tail-sitter UAV (Unmanned Aerial Vehicle), proposing a fusion configuration with embedded grid channels on the duct wall. The low pressure zone at the lip of the duct is induced to expand through the grid channels, forming a significant force component difference with the non-grid side, thereby generating significant lift effects for the propeller of the ducted fan during level flight. Taking a ducted fan system as an example, a design method for embedding grids into the ducted wall is established. By using the sliding mesh technique to simulate propeller rotation, the effects of annular distribution angle, grid channel width, circumferential and flow direction grid quantity on its aerodynamic performance are evaluated. The results indicate that the ducted fan embedded in the grid can generate a lift about 22.16% of total thrust without significantly affecting thrust and power characteristics. The increase in circumferential distribution angle increases within a reasonable range and benefits the lift of the propeller. However, the larger the grid width, the more it affects the lip and tail of the duct. Ultimately, the overall effect actually deteriorates the performance. The number of circumferential grids has a relatively small impact. As the number of flow grids increases, the aerodynamic characteristics of the entire fusion configuration significantly improves, due to its favorable induction of airflow at the lip and tail of the duct, as well as blocking the dissipation of blade-tip vortices. Full article

Accurate multi-class semantic segmentation of disaster-affected areas is essential for rapid response and effective recovery planning. We present CSDNet, a context-aware segmentation model tailored to disaster scene scenarios, designed to improve segmentation of both large-scale disaster zones and small, underrepresented classes. The architecture combines a lightweight transformer module for global context modeling with depthwise separable convolutions (DWSCs) to enhance efficiency without compromising representational capacity. Additionally, we introduce a detection-guided feature fusion mechanism that integrates outputs from auxiliary detection tasks to mitigate class imbalance and improve discrimination of visually similar categories. Extensive experiments on several public datasets demonstrate that our model significantly improves segmentation of both man-made infrastructure and natural damage-related features, offering a robust and efficient solution for post-disaster analysis. Full article

Mineral prospectivity mapping (MPM) is a pivotal technique in geoscientific mineral resource exploration. To address three critical challenges in current deep convolutional neural network applications for geoscientific mineral resource prediction—(1) model bias induced by imbalanced distribution of ore deposit samples, (2) deficiency in global feature extraction due to excessive reliance on local spatial correlations, and (3) diminished discriminative capability caused by feature smoothing in deep networks—this study innovatively proposes a T-GCN model integrating Transformer with graph convolutional neural networks (GCNs). The model achieves breakthrough performance through three key technological innovations: firstly, constructing a global perceptual field via Transformer’s self-attention mechanism to effectively capture long-range geological relationships; secondly, combining GCNs’ advantages in topological feature extraction to realize multi-scale feature fusion; and thirdly, designing a feature enhancement module to mitigate deep network degradation. In practical application to the PangXD ore district, the T-GCN model achieved a prediction accuracy of 97.27%, representing a 3.76 percentage point improvement over the best comparative model, and successfully identified five prospective mineralization zones, demonstrating its superior performance and application value under complex geological conditions. Full article

Faults and fracture sets in carbonate reservoirs are key geological features that govern hydrocarbon migration, accumulation, and wellbore stability. Their accurate detection is essential for structural interpretation, reservoir modeling, and drilling risk assessment. In this study, we propose an Optimally Oriented Coherence Attribute (OOCA) method that integrates geological guidance with multi-frequency structural analysis to achieve enhanced sensitivity to faults and fractures across multiple scales. The method is guided by depositional and tectonic principles, constructing model traces along directions with maximal structural variation to amplify responses at geological boundaries. A distance-weighted computation and extended directional model trace strategy are adopted to further enhance the detection of fine-scale discontinuities, overcoming the limitations of traditional attributes in resolving subtle structural features. A Gabor-based multi-frequency fusion framework is employed to simultaneously preserve large-scale continuity and fine-scale detail. Validation using physical modeling and field seismic data confirms the method’s ability to enhance weak fault imaging. Compared to traditional attributes such as C3 coherence, curvature, and instantaneous phase, OOCA delivers significantly improved spatial resolution. In zones with documented lost circulation, the identified structural features align well with drilling observations, demonstrating strong geological adaptability and engineering relevance. Overall, the OOCA method offers a geologically consistent and computationally efficient solution for high-resolution fault interpretation and drilling risk prediction in structurally complex carbonate reservoirs. Full article