Rice leaf diseases critically threaten global rice production by reducing crop yield and quality. Efficient disease detection in complex field environments remains a persistent challenge for sustainable agriculture. Existing deep learning-based methods for rice leaf disease detection struggle with inadequate sensitivity to subtle disease features, high computational complexity, and degraded accuracy under complex field conditions, such as background interference and fine-grained disease variations. To address these limitations, this research aims to develop a lightweight yet high-accuracy detection model tailored for complex field environments that balances computational efficiency with robust performance. We propose RDRM-YOLO, an enhanced YOLOv5-based network, integrating four key improvements: (i) a cross-stage partial network fusion module (Hor-BNFA) is integrated within the backbone network’s feature extraction stage to enhance the model’s ability to capture disease-specific features; (ii) a spatial depth conversion convolution (SPDConv) is introduced to expand the receptive field, enhancing the extraction of fine-grained features, particularly from small disease spots; (iii) SPDConv is also integrated into the neck network, where the standard convolution is replaced with a lightweight GsConv to increase the accuracy of disease localization, category prediction, and inference speed; and (iv) the WIoU Loss function is adopted in place of CIoU Loss to accelerate convergence and enhance detection accuracy. The model is trained and evaluated utilizing a comprehensive dataset of 5930 field-collected and augmented sample images comprising four prevalent rice leaf diseases: bacterial blight, leaf blast, brown spot, and tungro. Experimental results demonstrate that our proposed RDRM-YOLO model achieves state-of-the-art performance with a detection accuracy of 94.3%, and a recall of 89.6%. Furthermore, it achieves a mean Average Precision (mAP) of 93.5%, while maintaining a compact model size of merely 7.9 MB. Compared to Faster R-CNN, YOLOv6, YOLOv7, and YOLOv8 models, the RDRM-YOLO model demonstrates faster convergence and achieves the optimal result values in Precision, Recall, mAP, model size, and inference speed. This work provides a practical solution for real-time rice disease monitoring in agricultural fields, offering a very effective balance between model simplicity and detection performance. The proposed enhancements are readily adaptable to other crop disease detection tasks, thereby contributing to the advancement of precision agriculture technologies.

Wind turbine blade damage detection is crucial for advancing wind energy as a sustainable alternative to fossil fuels. Existing methods based on image processing technologies face challenges such as limited adaptability to complex environments, trade-offs between model accuracy and computational efficiency, and inadequate real-time inference capabilities. In response to these limitations, we put forward MSWindD-YOLO, a lightweight real-time detection model for wind turbine blade damage. Building upon YOLOv5s, our work introduces three key improvements: (1) the replacement of the Focus module with the Stem module to enhance computational efficiency and multi-scale feature fusion, integrating EfficientNetV2 structures for improved feature extraction and lightweight design, while retaining the SPPF module for multi-scale context awareness; (2) the substitution of the C3 module with the GBC3-FEA module to reduce computational redundancy, coupled with the incorporation of the CBAM attention mechanism at the neck network’s terminus to amplify critical features; and (3) the adoption of Shape-IoU loss function instead of CIoU loss function to facilitate faster model convergence and enhance localization accuracy. Evaluated on the Wind Turbine Blade Damage Visual Analysis Dataset (WTBDVA), MSWindD-YOLO achieves a precision of 95.9%, a recall of 96.3%, an mAP@0.5 of 93.7%, and an mAP@0.5:0.95 of 87.5%. With a compact size of 3.12 MB and 22.4 GFLOPs inference cost, it maintains high efficiency. After TensorRT acceleration on Jetson Orin NX, the model attains 43 FPS under FP16 quantization for real-time damage detection. Consequently, the proposed MSWindD-YOLO model not only elevates detection accuracy and inference efficiency but also achieves significant model compression. Its deployment-compatible performance in edge environments fulfills stringent industrial demands, ultimately advancing sustainable wind energy operations through lightweight lifecycle maintenance solutions for wind farms.

Grape berries are highly susceptible to diseases during growth and harvest, which severely impacts yield and postharvest quality. While rapid and accurate disease detection is essential for real-time control and optimized management, it remains challenging due to complex symptom patterns, occlusions in dense clusters, and orchard environmental interference. Although deep learning presents a viable solution, robust methods specifically for detecting grape berry diseases under dense clustering conditions are still lacking. To bridge this gap, we propose GBDR-Net—a high-accuracy, lightweight, and deployable model based on YOLOv10. It incorporates four key enhancements: (1) an SDF-Fusion module replaces the original C2f module in deeper backbone layers to improve global context and subtle lesion feature extraction; (2) an additional Detect-XSmall head is integrated at the neck, with cross-concatenated outputs from SPPF and PSA modules, to enhance sensitivity to small disease spots; (3) the nearest-neighbor upsampling is substituted with a lightweight content-aware feature reassembly operator (LCFR-Op) for efficient and semantically aligned multi-scale feature enhancement; and (4) the conventional bounding box loss function is replaced with Inner-SIoU loss to accelerate convergence and improve localization accuracy. Evaluated on the Grape Berry Disease Visual Analysis (GBDVA) dataset, GBDR-Net achieves a precision of 93.4%, recall of 89.6%, mAP@0.5 of 90.2%, and mAP@0.5:0.95 of 86.4%, with a model size of only 4.83 MB, computational cost of 20.5 GFLOPs, and a real-time inference speed of 98.2 FPS. It outperforms models such as Faster R-CNN, SSD, YOLOv6s, and YOLOv8s across key metrics, effectively balancing detection accuracy with computational efficiency. This work provides a reliable technical solution for the intelligent monitoring of grape berry diseases in horticultural production. The proposed lightweight architecture and its design focus on dense, small-target detection offer a valuable framework that could inform the development of similar systems for other cluster-growing fruits and vegetables.

The hot compression behavior of Mg‐9Gd‐3Y (GW93) alloy was investigated by carrying out isothermal compression tests at the deformation temperature range of 300–450°C and strain rate range of 0.001–1s⁻¹. Considering the influence of the strain on the formability of the GW93 alloy, three‐dimensional (3D) processing maps were established based on the dynamic material model. The 3D processing maps indicate that the formability of the material improved with the decrease of the strain rate and the increase of the heating temperature, and the material at lower heating temperature mostly underwent flow instability. The formable processing region of the hot deformation of the GW93 alloy was concentrated within the temperature range of 380–450°C and the strain rate range of 0.001–0.01 s⁻¹. Subsequently, the 3D processing maps were embedded into the finite element (FE) software DEFORM‐3D by means of user subroutines, and the formability of GW93 alloy during the isothermal plane strain forging process was predicted. The FE simulation results revealed that the formability of the material at low strain rate improved compared with that at high strain rate under the same temperature. Finally, an isothermal plane strain forging technological experiment was carried out, and the microstructure of the formed sample was analyzed. The experimental result is in good agreement with that of the numerical simulation. Combined with microstructural observation, the accuracy of the simulation results and the 3D processing maps of the GW93 alloy was verified.

A novel composite mechanical bulging process suitable for the manufacture of medium-duty commercial vehicle drive axle housings is proposed. The analytical expression for the limit bulging forming coefficient of tube blanks under conditions below the metal recrystallization temperature is derived, and the influence of the matching of various force parameters on the limit bulging forming coefficient is analyzed. The appropriate range for the axial auxiliary load during radial bulging is also presented. Based on the derived theory, a 5-ton commercial vehicle drive axle housing is selected as the research object. The key processes in the forming process are numerically simulated to obtain the metal flow state, stress-strain distribution, and wall thickness variation. The types and locations of defects that may occur during the bulging process are also predicted. To address the phenomenon of local wall thinning in the composite mechanical bulging process of the drive axle housing, a set of orthogonal simulation experiments is designed, focusing on the wall thickness thinning rate in the bridge arch bulging area and the crack-prone region, with respect to the process parameters. Based on the numerical simulation results, response surface equations are established for the expansion core's movement speed and axial auxiliary thrust in relation to the wall thickness thinning rate. Through parameter estimation of the response surface equation and regression analysis of significant influencing factors, the effects of process parameters on wall thickness thinning are obtained: the thinning rate in the bridge arch bulging area decreases with increasing expansion core movement speed and axial auxiliary thrust, while the thinning rate in the crack-prone region increases. The optimization of the response surface model and the determination of the optimal process parameter combination, based on field production conditions, show that the numerical simulation results and the wall thickness measurements from process experiments are in close agreement. No cracks occur in the axle housing, and the thinning is effectively alleviated. In contrast, mechanical bulging without axial auxiliary thrust leads to cracks, thus validating the feasibility of the proposed process scheme and the effectiveness of the parameter optimization. This research provides valuable technical reference for upgrading the manufacturing technology of large-span axle-tube products.