To correct the working state of a throwing component and achieve an ideal narrow, far, and uniform material projectile flow for a side-throwing device for organic fertilizer with inclined opposing discs, a systematic optimization of the auxiliary mechanisms (baffle, upper deflector, and side deflector) was performed. Starting from a basic analysis of the working principles of each side-throwing device component, theoretical modeling and MATLAB numerical calculations were used to determine the departure angle providing the farthest fertilizer distance, as well as the maximum and minimum throwing angles required to achieve a target distance of 10 m. These calculations informed the optimization and configuration of the basic structures of each auxiliary mechanism component. The impact of the baffle on fertilizer movement was analyzed, leading to an optimization of the baffle’s height and its horizontal position in relation to the main throwing disc, guiding the design of the discharge port structure. Combining the theoretical analysis results, the surface of the upper deflector was fitted, and a side deflector was added to assist in limiting the scattering angle of the projectile flow. An EDEM simulation showed that the optimized auxiliary mechanisms worked well together, resulting in a narrower discharge width, a more concentrated projectile flow, and improved uniformity in spreading. Prototype testing confirmed that from the side projection angle between the spreading direction and vertically upward, the projectile flow angle domain was adjusted from 18°-45° to 23°-32°. With the optimization of other auxiliary mechanisms, the coefficient of variation in spreading uniformity decreased from 25.95% to 19.21%, the effective throwing distance increased from 10.1 to 11.2 m, and the scattering angle decreased from 12° to 4°, effectively enhancing the performance of the side-throwing device.

Currently, knowledge-based systems are generally updated manually, resulting in long cycles, low efficiency, and difficulty in ensuring comprehensive and systematic supplementary content. To address this issue, a knowledge-based system automatic updating method based on webpage information and user files is proposed for combine harvesters. The knowledge storage structure in an electronic warehouse is analyzed, and knowledge and data types are determined. A crawler designed to locate the combine harvester-related information in the target webpage realizes the acquisition and sorting of webpage knowledge and data. The type of file uploaded by the user is set based on the knowledge base and data type; the content of the user file is extracted and filtered, and the knowledge and data of the knowledge-based system are user-defined. The organized knowledge and data are stored or updated in the knowledge base to achieve automatic updating of the knowledge-based system based on webpage information and user files. The test results show that based on user file updates, the knowledge and data of the knowledge-based system can be customized according to user needs. This meets user requirements and allows for effective automatic updates based on webpages after automatic updating of the knowledge base based on webpages. After the automatic updating of the knowledge base based on webpage information is triggered, the knowledge and data from the three webpages that were initially crawled and read are automatically updated to the knowledge base in 5.265 s. Realizing the automatic updating of knowledge and data can shorten the updating period, maintain the effectiveness and practicability of the knowledge-based system, ensure the scientific and advanced nature of the intelligent design process, and provide technical models and methods for the knowledge collection of similar knowledge-based systems.

Rice is one of the most important staple crops in China, with an annual planting area of approximately 30 million hectares. However, the rice diseases have significantly impacted agricultural production, particularly in the regions with highly intensive farming and a high cropping index. The increasing prevalence of rice diseases has threatened the yield and food security. Early and accurate detection of rice diseases is often required for the effective control of rice diseases. However, several challenges still remain in the existing detection of embedded edge devices, such as the high computational demands of deep learning. This study aims to detect rice diseases using improved lightweight YOLOv8. Spot features of disease were extracted to enhance the detection accuracy in complex field environments. A diverse dataset of rice disease images was systematically collected from real-world fields. The image dataset also included the three major rice diseases: Rice Blast, Bacterial Blight, and Brown Spot. A strong foundation was provided to train and evaluate the deep learning models. In order to improve detection accuracy and computational efficiency, the lightweight model (YOLOv8-DiDL) was proposed to identify the rice disease using YOLOv8n. The key modifications were introduced to enhance the performance of the improved model. Firstly, an Inverted Residual Mobile Block (iRBM) was integrated into the backbone of convolutional modules. The micro disease features were then captured to promote the precision of detection on the small lesions. Secondly, a Deformable Convolutional Network (DCNv2) was incorporated to optimize the geometric size of disease symptoms. Stable performance of detection was achieved in complex and dynamic environments. Thirdly, a Dynamic Sample (DySample) operator was applied to reduce the computational complexity in real-world conditions. The model parameters were minimized for the computational overhead. The improved model was more efficient for the deployment of the resource-limited edge devices. Lastly, the standard Spatial Pyramid Pooling Fast (SPPF) module was replaced with a Large Separable Kernel Attention (LSKA) module. Multiple scale feature was fused in the pooling layer to recognize the diseases over the different scales and lighting conditions. A series of experiments were performed on the standardized platform. The results demonstrate that the improved YOLOv8-DiDL model was achieved with an accuracy of 91.4%, a recall of 83.5%, a mean average precision (mAP) of 90.8%, a parameter count of 2 270 553, and a model weight of only 7.5 MB. Compared with the baseline YOLOv8n network, the improvements were 7.0% in accuracy, 0.5% in recall, and 2.5% in mAP, while simultaneously the model weights were reduced by 9.7% and floating-point operations per second by 7.4%. A comparison was also made on the backbone network, heatmaps, and full-process feature maps. The high effectiveness was found after modifications. Each enhancement positively contributed to both detection accuracy and computational efficiency, thus enhancing the real-time detection of small disease spots. The improved model was achieved with high accuracy and lower computational costs, thus making it feasible for real-world agricultural applications. The reliability of the improved model was validated to detect the rice diseases. An advanced approach was then provided for the precision management in rice fields. Both detection accuracy and deployment efficiency were improved for real-time disease monitoring in intelligent agriculture. The finding can also be further extended into the detection of crop diseases in smart and sustainable agriculture.