Rotary tillage blades, as critical components of soil tillage machinery, encounter significant challenges in mountainous agricultural operations, where excessive wear and high energy consumption are persistent issues. To address these problems, this study proposes an integrated strategy combining structural optimization with surface reinforcement. A blade–soil interaction model based on Smoothed Particle Hydrodynamics (SPH) was developed to optimize blade geometry, reducing power consumption to 0.106 kW with a simulation error of only 2.83%. In parallel, Fe60–WC composite coatings containing 30%, 35%, and 40% WC were fabricated on 65Mn substrates using laser cladding. Microstructural analysis revealed significant grain refinement with increasing WC content, while tribological tests showed that the 35% WC coating blades exhibited superior wear resistance, with a mass loss of 1.9 mg, and a relatively low friction coefficient of 0.362. Field trials further confirmed that the blades resulted in a 45.75% reduction in average wear, after structural enhancement and the application of the optimized coating, with a measured loss of 2.259 g compared to the uncoated blades. These findings demonstrate the synergistic benefits of structural optimization and advanced surface engineering, providing an effective pathway to improve the durability and efficiency of rotary tillage blades in demanding field conditions.

Efficient detection and localization of maize seedlings in complex field environments is essential for accurate plant segmentation and subsequent three-dimensional morphological reconstruction. To overcome the limited accuracy and high computational cost of existing models, we propose an enhanced architecture named MaizeStar-YOLO. The redesigned backbone integrates a novel C2F_StarsBlock to improve multi-scale feature fusion, while a PKIStage module is introduced to enhance feature representation under challenging field conditions. Evaluations on a diverse dataset of maize seedlings show that our model achieves a mean average precision (mAP) of 92.8%, surpassing the YOLOv8 baseline by 3.6 percentage points, while reducing computational complexity to 3.0 GFLOPs, representing a 63% decrease. This efficient and high-performing framework enables precise plant–background segmentation and robust three-dimensional feature extraction for morphological analysis. Additionally, it supports downstream applications such as pest and disease diagnosis and targeted agricultural interventions.

This study proposes a grading algorithm for Orah sorting lines based on machine vision and deep learning. The original ShuffleNet V2 network was modified by replacing the ReLU activation function with the Mish activation function to alleviate the neuron death problem. The ECA attention module was incorporated to enhance the extraction of Orah appearance features, and transfer learning was applied to improve model performance. As a result, the ShuffleNet_wogan model was developed. Based on the operational principles of the sorting line, a time-sequential grading algorithm was designed to improve grading accuracy, along with a multi-sampling diameter algorithm for simultaneous Orah diameter measurement. Experimental results show that the ShuffleNet_wogan model achieved an accuracy of 91.12%, a 3.92% improvement compared to the original ShuffleNet V2 network. The average prediction time for processing 10 input images was 51.44 ms. The sorting line achieved a grading speed of 10 Orahs per second, with an appearance grading accuracy of 92.5% and a diameter measurement compliance rate of 98.3%. The proposed algorithm is characterized by high speed and accuracy, enabling efficient Orah sorting.

The significant differences in insects trapped by pest detection lamps lead to low classification accuracy of existing models for rice pests. To address this issue, this paper proposes a small pest target detection and classification model (ViT-YOLOv5p) by integrating the YOLO backbone and Transformer module. First, the number of training samples is expanded through data augmentation during model training. Furthermore, appropriate noise data are introduced to enhance the robustness and generalization ability of the model. Before detection and classification, image cutting and stitching strategies are adopted to improve the detection accuracy of small objects. The bounding box of the pest is determined by the YOLO backbone, and the corresponding region is fed into the Transformer model to obtain the classification result. Finally, YOLOv5, Faster R-CNN, YOLOv4, and the proposed ViT-YOLOv5p are trained on the same dataset, with average detection time (ADT) and classification accuracy employed as evaluative metrics. The results show that ViT-YOLOv5p achieves the highest classification accuracy of 91.89% with an ADT of 50.41 ms. Compared with the commonly used Faster R-CNN, YOLOv5, and YOLOv4 models, the accuracy is improved by 1.50%, 8.71%, and 9.74%, respectively. This study provides a reference for agricultural pest detection, automatic insect classification systems, and deep learning-based detection of small agricultural targets.

Accurate in-season yield prediction is critical for guiding nitrogen management in rice production, particularly under the increasingly variable weather conditions in cold regions. However, the prediction accuracy of conventional crop models is often limited by uncertainties in model inputs and the inability to capture real-time crop status. This study proposed a yield prediction framework by coupling the CERES-Rice model with re-mote sensing observations and machine learning techniques. Field experiments were conducted in Northeast China from 2014 to 2018. Spectral data collected by the Rap-idSCAN active canopy sensor were used to retrieve key agronomic parameters, including aboveground biomass (AGB), leaf area index (LAI), plant nitrogen concentration (PNC) and plant nitrogen uptake (PNU), using a Random Forest algorithm. These variables were then assimilated into the CERES-Rice model to calibrate its sensitive parameters and im-prove yield predictions. The analysis showed that updating agronomic variables using remote sensing resulted in acceptable modeling accuracy (R² > 0.7). Using PNU and AGB outperformed LAI in enhancing model performance, while using PNC was unreliable. Without assimilation, CERES-Rice gave moderate performance (R² = 0.58, RMSE = 1.3 t ha⁻¹), while coupling with PNU improved prediction accuracy(R² = 0.67, RMSE = 0.79 t ha⁻¹). This study highlights the potential of integrating active canopy sensing and ma-chine learning with crop models for dynamic yield forecasting and provides a valuable reference for optimizing nitrogen management in rice systems.

The study of cotton stalk extraction resistance provides important parameters for the design of cotton stalk harvesting machinery. To investigate the effects of soil moisture content, cotton stalk diameter, and extraction angle on the extraction force of densely planted cotton stalks, this paper designs a real-time measurement system based on virtual instrument technology and conducts field tests. The tests were carried out in cotton fields at the First Farm in Aral City, Xinjiang, using the cotton variety “Xiulu Zhong 70”. Single-factor experiments were conducted with extraction angle and stalk diameter as influencing factors. A combined three-factor experiment was performed under the following conditions: soil moisture contents of 21.87% and 26.32%; extraction angles of 25°, 30°, and 35°; and cotton stalk diameters of 8.50–9.00 mm, 10.00–10.50 mm, and 11.50–12.00 mm. The results show that the minimum extraction force is required when the extraction angle is 30°. Soil moisture content significantly affects the extraction force, which increases with stalk diameter. The combined test results indicate that the order of significance of the three factors is as follows: cotton stalk diameter (A), extraction angle (B), and soil moisture content (C). The optimal combination is A₁B₁C₂, corresponding to a diameter of 8.50–9.00 mm, an extraction angle of 35°, and a soil moisture content of 26.32%. Based on comprehensive analysis, the recommended extraction angle range is 30–35°. The proposed system can efficiently complete cotton stalk extraction force tests, and the collected data provide valuable references for the design of cotton stalk harvesting machinery. By appropriately selecting the extraction angle and conducting harvesting under suitable soil moisture conditions, it is possible to reduce power consumption and improve production efficiency.