In response to the challenges of detecting rice pests and diseases at different scales and the difficulties associated with deploying and running models on embedded devices with limited computational resources, this study proposes a multi-scale rice pest and disease recognition model (RGC-YOLO). Based on the YOLOv8n network, which includes an SPPF layer, the model introduces a structural reparameterization module (RepGhost) to achieve implicit feature reuse through reparameterization. GhostConv layers replace some standard convolutions, reducing the model’s computational cost and improving inference speed. A Hybrid Attention Module (CBAM) is incorporated into the backbone network to enhance the model’s ability to extract important features. The RGC-YOLO model is evaluated for accuracy and inference time on a multi-scale rice pest and disease dataset, including bacterial blight, rice blast, brown spot, and rice planthopper. Experimental results show that RGC-YOLO achieves a precision (P) of 86.2%, a recall (R) of 90.8%, and a mean average precision at Intersection over Union 0.5(mAP50) of 93.2%. In terms of model size, the parameters are reduced by 33.2%, and GFLOPs decrease by 29.27% compared to the base YOLOv8n model. Finally, the RGC-YOLO model is deployed on an embedded Jetson Nano device, where the inference time per image is reduced by 21.3% compared to the base YOLOv8n model, reaching 170 milliseconds. This study develops a multi-scale rice pest and disease recognition model, which is successfully deployed on embedded field devices, achieving high-accuracy real-time monitoring and providing valuable reference for intelligent equipment in unmanned farms.

Due to nutrient stress, which is an important constraint to the development of the global agricultural sector, it is now vital to timely evaluate plant health. Remote sensing technology, especially hyperspectral imaging technology, has evolved from spectral response modes to pattern recognition and vegetation monitoring. This study established a hyperspectral library of 14 NPK (nitrogen, phosphorus, potassium) nutrient stress conditions in rice. The terrestrial hyperspectral camera (SPECIM-IQ) collected 420 rice stress images and extracted as well as analyzed representative spectral reflectance curves under 14 stress modes. The canopy spectral profile characteristics, vegetation index, and principal component analysis demonstrated the differences in rice under different nutrient stresses. A transformer-based deep learning network SHCFTT (SuperPCA-HybridSN-CBAM-Feature tokenization transformer) was established for identifying nutrient stress patterns from hyperspectral images while being compared with classic support vector machines, 1D-CNN (1D-Convolutional Neural Network), and 3D-CNN. The total accuracy of the SHCFTT model under different modeling strategies and different years ranged from 93.92% to 100%, indicating the positive effect of the proposed method on improving the accuracy of identifying nutrient stress in rice.

In order to solve the problem of vigorous vibration of agricultural machinery frames, taking a vegetable precision seeder as an example, the concept of vibration reduction was proposed. The modal analysis of the frame was carried out, and the accuracy of the finite element model was verified by comparing the modal test of multipoint input and multipoint output (MIMO) and simulation results. Additionally, the main frequency of engine vibration was the main excitation source of frame resonance. According to the modal shapes, it was proposed to increase the fixed beam structure and to carry out simulation tests. The time-domain signal of the maximum deformation position in the first-order vibration mode was measured, and the vibration spectrum analysis maps before and after optimization were obtained by Fourier transform. A field experiment showed that the seeding quality of the whole machine was significantly improved after optimization. This study provides a reference for the analysis of vibration characteristics and the vibration reduction design of the agricultural machinery equipment.

It is difficult to determine the coefficient of restitution accurately due to the small size, light weight, and complex influencing factors of rice grain. In the study, the experimental principle of restitution coefficient was described by the impact method, and the restitution coefficients of four typical rice varieties in Northeast China were measured. According to the orthogonal experiment, the primary and secondary factors affecting the restitution coefficient of rice grain were collision material, spring compression (initial collision velocity), moisture content, and rice variety. A single factor test was carried out for the significant factors, and the results showed that: The restitution coefficient of rice grain to a Q235 steel plate, plexiglass plate, seed plate, and rubber plate decreased in turn, and the restitution coefficient gradually decreased with the increase of spring compression (initial collision velocity), and with the increase of water content. The restitution coefficient was obtained by a bench test and simulation test, and the results were 0.429 and 0.423, respectively. The reason for the error was discussed and analyzed, which effectively verified the validity of the measurement of the restitution coefficient of small grain size. This study provides a method for the determination of the restitution coefficient of small grain, and provides a reference for the optimization design of threshing and a cleaning device of the combine harvester and high-speed precision seeder.

Liquid fertilizer has many advantages, such as low production cost and little environmental pollution. Liquid fertilizer open furrow strip application method is widely used in fertilizer application operation. The widely used core-share furrow opener has a high operational resistance, disturbing the soil, hurting the crop roots, causing the liquid fertilizer to volatilize and deteriorating the fertilization effect. In this study, based on the streamline curve of the sturgeon body, we designed several bionic sturgeon liquid fertilizer deep application openers by combining bionics and analyzed the effects of several openers under different operating speeds on open furrow resistances and soil disturbance based on the discrete element method. The mechanism of open furrow resistances reduction and efficient soil backfill of the bionic structure were verified by indoor soil bin tests. The test results show that, compared with the core-share type furrow opener, both open furrow resistances and soil disturbance of the bionic sturgeon liquid fertilizer deep application opener are smaller. This study provides theoretical and practical references for the design of liquid fertilizer deep application openers.