To address the challenges of missed and false detections in citrus fruit detection caused by environmental factors such as leaf occlusion, fruit overlap, and variations in natural light in hilly and mountainous orchards, this paper proposes a citrus detection model based on an improved YOLOv5 algorithm. By introducing receptive field convolutions with full 3D weights (RFCF), the model overcomes the issue of parameter sharing in convolution operations, enhancing detection accuracy. A focused linear attention (FLA) module is incorporated to improve the expressive power of the self-attention mechanism while maintaining computational efficiency. Additionally, anchor boxes were re-clustered based on the shape characteristics of target objects, and the boundary box loss function was improved to Foal-EIoU, boosting the model’s localization ability. Experiments conducted on a citrus fruit dataset labeled using LabelImg, collected from hilly and mountainous areas, showed a detection precision of 95.83% and a mean average precision (mAP) of 79.68%. This research not only significantly improves detection performance in complex environments but also provides crucial data support for precision tasks such as orchard localization and intelligent picking, demonstrating strong potential for practical applications in smart agriculture.

The bruising of fruits occurs at various stages, including picking, transportation, and sale. For fruits with large kernels that occupy a significant portion of their overall volume, considering the impact of the kernel is crucial in elucidating the mechanisms of bruising and controlling bruise formation. This study employs reverse engineering to develop a composite finite element model of loquat peel, flesh, and kernels. Bruise formation during collisions is analyzed from the perspectives of contact force, equivalent stress, energy, bruise volume, and bruise susceptibility, aiming to reveal the significant role of the fruit core in the bruise formation process. In this paper, we propose the use of 3D printing technology to accurately quantify bruise measurement for fruits with large kernels. The results showed that the maximum contact force, equivalent stress, and internal energy between loquat and steel/wood were essentially consistent, but all exceeded those observed when using rubber. Due to the blocking of stress transmission by the kernel, the susceptibility of loquats to bruising increases with height before decreasing. This study elucidates the mechanism of bruise formation in fruits with large kernels and provides methods and ideas for the research and precise measurement of complex fruit bruising characteristics.

Selecting an appropriate disc coulter is crucial for reducing the power consumption of no-till seeders, preventing straw from being pressed into seed furrows, improving the soil penetration performance of the disc coulter, and thus minimizing the weight of no-till seeders. This study utilized the quadratic regression orthogonal rotation central composite approach. With the application of EDEM and RecurDyn software, a virtual simulation model of the interaction between a toothed disc coulter and soil was developed. The angle of front serration δ, the angle of rear serration θ, and the number of serrations n were taken as experimental factors. The draft F_v and penetration resistance F_N were selected as performance evaluation indicators for parameter combination optimization simulation tests. The results indicated that δ, θ, and n have significant influences on F_v and F_N (p < 0.05). When the optimized parameter combinations δ, θ, and n were respectively determined as 16°, 39.1°, and 13, both F_v and F_N reached their minimum values. A comparative experimental study was conducted with the optimized toothed disc coulter and six existing disc coulters; under the working conditions of 14.4 km·h⁻¹, both the draft and penetration resistance of the toothed disc coulter are minimized. The draft was 227.5 ± 8.9 N and the penetration resistance was 415.9 ± 5.3 N. Meanwhile, the toothed disc coulter had the highest ratio of soil disturbance area to draft, indicating better soil loosening effects.

This study focuses on enhancing the comprehensive utilisation of rice straw by proposing a vibration-assisted compression technology, with the aim of resolving inherent issues in traditional baling, such as uneven compression and low density. This study designed a multi-point vibration-assisted compression test rig and established a vibration-enhanced compression mechanical model based on the physical properties of rice straw. By integrating discrete element method (DEM) simulations with bench testing, the optimal length-to-width ratio of 1:1 was identified for achieving superior compaction quality. A systematic analysis was conducted to evaluate the effects of vibration point configuration, frequency, and amplitude control on straw bale integrity. The results of the DEM simulations demonstrated that vibration-assisted compression significantly enhanced the compaction uniformity and stability of rice straw. The dimensional stability coefficient and pressure transmission rates of the straw bales reached 88.25% and 58.04%, respectively, validating the efficacy of the vibration-assisted compression technique. This study provides innovative concepts and theoretical foundations for optimising the design of straw baling and in-field collection equipment. It holds critical significance for advancing the resource-efficient utilisation of agricultural residues and promoting sustainable agricultural practices.