With the improvement of our national living standard, consumers have higher requirements for the quality of eggs. The detection of cracked eggs is an important step before packing eggs. In order to solve the problems of high labor intensity and heavy workload in manual sorting of cracked eggs, a cracked egg sorting robot based on machine vision and YOLO v5 was designed. Firstly, the rotation Angle of each steering gear of the manipulator was obtained by inverse kinematics and converted into PWM duty cycle to realize the control of the three-axis series manipulator. Secondly, a high-definition 120°wide-angle camera was used as the image acquisition core to quickly acquire the image information of egg surface and label the 1 000 images collected. YOLO v5 models with different gradient descent batch sizes were then trained respectively, among which the model with gradient descent batch size of 8 had the highest mAP with a value of 98.92%. Finally, the model was called on the main board of the upper computer of the mechanical arm, and after the recognition and judgment of normal eggs and cracked eggs, the sorting stroke of the mechanical arm was started. In addition, the end pickup mechanism of the egg sorting robot was a pneumatic suction cup, which was mounted on the mechanical arm to achieve non-destructive absorption of eggs. The test results showed that the robot can identify the two kinds of eggs with the accuracy of 93.33% and 99.17%respectively, the average success rate of sorting is 94.34%, and the average sorting rate was 7.55 s/egg, which basically met the requirements. The research results can provide technical support for the screening of cracked eggs, and provide solutions for crack detection and sorting of eggs, which has high practical significance.

Biochar is a multifunctional material efficiently developed from biomass. It is combined with fertilizers to prepare biochar-based fertilizers, which has excellent slow-release performance and minimal soil burden. The carbonization temperature, carbonization time, and heating rate during biomass carbonization process affect the physical and chemical properties of biochar. The biochar under different carbonization temperatures, carbonization times and heating rates have a significant impact on the slow-release performance of biochar-based fertilizers. In this study, BP neural network coupled with genetic algorithm was used to predict and optimize key process parameters during the carbonization process of coffee shell biochar in order to improve the slow-release performance of biochar-based fertilizers. Results had shown that based on BP neural network-genetic algorithm, rapid prediction and optimization of the slow-release performance of coffee shell biochar-based fertilizer had been achieved through experiments. The optimal process parameters were: carbonization time of 2.8 h, carbonization temperature of 780.7 ℃, and the heating rate of 15.1 ℃/min. The seven-day cumulative nutrient release rate of the biochar-based fertilizer prepared under this process parameter was 45.9%, and the slow-release performance was improved. The study proposed a new method for optimizing the parameters of biochar carbonization process, which provided new ideas for the development of high-performance biochar preparation processes and had certain reference significance for improving the performance of biochar-based fertilizers.

During the operation of the rice combine harvester, the fuselage tilts due to the tilt and unevenness of the ground affect its maneuverability and operational reliability. Aiming at the problem of leveling due to the tilt of the field surface, this research developed an innovative dual-parallelogram chassis lifting mechanism for rice harvesters designed a hydraulic system to adjust the chassis height by extending the cylinder. Using Adams simulation software, a detailed model of the lifting chassis was constructed to analyze its performance, revealing a direct correlation between the hydraulic cylinder extension and chassis elevation. Notably, the mechanism could achieve leveling on slopes with inclination angles of up to 7.5°. Comprehensive evaluations of the liftable chassis system were conducted under both static and dynamic conditions. In the static tests, the system exhibited the capacity for comprehensive or unilateral auto-leveling contingent upon the tilt, with leveling times and angular variations confined to 3.6 s and ±0.4°, respectively. In dynamic tests conducted on sloped fields and paddy soils, the system reduced post-leveling mean tilt angles and standard deviations remained below 1.2° and 0.6°, respectively. These results demonstrated a substantial improvement in the stability and reliability of the chassis during operations. This research provides valuable insights into the design and optimization of automatic leveling mechanisms and structural innovations for harvester chassis.

There are common problems in Chinese grain combine harvester, such as difficulty in balancing operational performance and efficiency, high failure rate, and low automation level. Feed quantity is one of the important parameters of grain combine harvester, which directly affects the machine's operational performance, overall reliability, and economic benefits. Only when the feeding quantity stabilizes within the rated range can the harvester achieve optimal efficiency. Starting from the fact that feeding amount has a vital impact on machine performance, this paper focuses on the detection function of feeding amount by domestic and foreign combine harvesters with the help of sensing technology. The feeding quantity is mainly reflected by measuring the torque or power of the transmission shaft of key working components through torque sensors and detecting the extrusion force of materials on the mechanical structure shell through pressure sensors. Secondly, machine vision and laser radar technology are used to identify crop density and the bending force of crop stems is measured by force sensor to indirectly represent the feeding quantity. In addition, the reasons that affect the signal processing of feed quantity detection and the key technologies and applications of automatic control of feed quantity in combine harvesters were analyzed and sorted out. Finally, this study proposes the problems existing in the feeding rate detection technology of existing grain combine harvesters, as well as future research priorities and development trends. Although there are many methods for detecting the feeding quantity of domestic combine harvester, they all have low detection accuracy, poor system stability, and are only suitable for a single crop, making it difficult to promote and apply on a large scale. Therefore, there is still great room for improvement in Chinese technology for detecting the feeding quantity of combine harvester. We should increase our research and development efforts on high-precision agricultural sensors and controllers to improve the overall stability of the detection system; The future combine harvester will move towards large-scale, intelligent, and integrated directions.

In view of the problem of relative displacement caused by wheel slippage during the operation of autonomous wheeled clam harvesting equipment on intertidal mudflats, which affects the path tracking accuracy of the autonomous driving system, a slip prediction method based on vehicle kinematics and dynamics models was proposed. The vehicle's motion trajectory was derived according to the four-wheel chassis kinematic model, and the walking dynamics model was established by incorporating tire lateral and longitudinal force characteristics. The calculation methods for longitudinal slip and lateral slip were clarified. An autonomous driving test platform was designed, consisting of perception, planning, and control layers. The platform collected position, steering angle, and wheel speed data using an RTK-GNSS system and relevant sensors. Longitudinal and lateral slip experiments were conducted to investigate the slip characteristics of the harvesting equipment in the intertidal environment. The longitudinal slip experiment analyzed the effects of motor PWM (pulse width modulation) and load on slip ratio, and a longitudinal slip model was established through data fitting. The lateral slip experiment explored the slip characteristics under different steering angles, leading to the fitting of a lateral slip model. To simplify calculations, the slip coefficient function was expressed in the form of a Taylor polynomial. The model's accuracy was validated through experiments, with the error between the actual and predicted trajectories being less than 16%, significantly reducing slip-related interference errors in autonomous driving on mudflats. Through experimental analysis and model optimization, this study improves the accuracy of slip prediction and provides a reference for achieving high-precision navigation for clam harvesting equipment in soft ground environments. Future research could focus on real-time parameter estimation of the slip model and the dynamics modeling of ground-contact components to enhance the equipment.

The intelligent advancement of agricultural machinery is a key focus in current agricultural engineering research. While machine vision technology has made preliminary progress in applications such as harvesting, breeding, and other crop-related fields, its use in defect detection for agricultural machinery remains limited. This study focused the airtightness defect detection of the agricultural machine pump, and presented a novel approach for automated detection based on machine vision. A deep learning algorithm based on MobileNetV3 convolutional neural network (CNN) was employed for the bubble recognition. In the airtightness detection experiment, the original bubble images were first processed by a bubble region extraction algorithm to reduce the image resolution. The post-processed images were then used for deep learning by MobileNetV3 CNN. The trained neural network model could recognize the bubble and its location in the airtightness detection. For performance evaluation, the recognition results could be compared with manually marked results to calculate the missing bubble recognition rate of the algorithm. The experiment results indicated that the missing recognition rate of the bubble algorithm is closely related with average diameter of the bubbles. The smaller of the average bubble diameter, the higher of the missing recognition rate, and the average bubble diameter was proportional to the leakage hole size on the pump. When the average bubble diameter was larger than 0.2 mm, the missing bubble recognition rate was below 2%, and when the average bubble diameter was smaller than 0.2 mm, the missing bubble recognition rate fluctuated between 5% and 10%. In this paper, the proposed bubble recognition algorithm effectively identifies and marks bubbles in images, enabling the detection of airtightness in agricultural pumps. However, further optimization is required to improve the algorithm's ability to recognize smaller bubbles and enhance its sensitivity to minute features in future work.

To address global climate change, reduce greenhouse gas (GHG) emissions, and support China's “carbon peaking and carbon neutrality” goals, this study reviews the current state of farmland carbon emissions in China and explores pathways for carbon sequestration and emission reduction from an agricultural perspective. A comprehensive analysis of carbon emissions across sectors, the composition of agricultural emission sources, and regional differences among provinces reveals that the evolution of China's GHG emissions can be divided into three phases: steady growth, rapid growth, and significant deceleration. The primary sources of greenhouse gas emissions in the agricultural sector include methane (CH₄) emissions from livestock enteric fermentation and rice production, as well as nitrous oxide (N₂O) emissions from microbial decomposition in agricultural soils. These sources exhibit significant regional and temporal variations, influenced by factors such as climate conditions, cropping patterns, and management practices. The study pointed out that changing current agricultural management practices is key to achieving emission reductions in agriculture. Optimizing management measures can not only mitigate agricultural carbon emissions but also enhance the carbon sequestration capacity of farmlands. Based on a cluster analysis of keywords and future research directions in the field of farmland carbon emissions in China, this study identifies current research hotspots and knowledge gaps. It emphasizes the importance of exploring regionally adaptive agronomic management practices to improve the effectiveness of carbon sequestration and emission reduction in different types of agricultural land, such as paddy fields and drylands. By analyzing the effects of high-frequency agronomic practices on increasing yields and reducing emissions, the study systematically elucidates the feasibility of measures such as optimizing water and fertilizer management, adjusting cropping structures, incorporating straw return and agricultural waste utilization, and adopting low-carbon agricultural equipment. This research provides systematic scientific evidence for theoretical studies and practical applications of farmland carbon sequestration and emission reduction in China. It also offers guidance for the promotion of relevant energy-saving and emission-reduction technologies. By focusing on the future pathways for green agricultural development, this study offers strategic insights for achieving the “dual-carbon” goals in China's agricultural sector.

Crop protection machinery plays a crucial role in modern agricultural production. Advanced plant protection machinery is conducive to optimizing pesticide utilization, improving food quality, and supporting sustainable agricultural practices. Globally, pesticide application products from the United States, Western Europe, and Japan are at the leading level internationally. The relevant products have a high degree of automation and intelligence, and the operation efficiency and effect are generally better than the domestic level. They occupy the vast majority of the market share. By comparison, China demonstrates technical advantages primarily in crop protection drones. To accurately capture the current research status and future directions of crop protection machinery, this article reviews the development history of prominent crop protection equipment, including ground, aerial, and field management robots, both at home and abroad. According to the needs and characteristics of field and orchard pest control, plant protection machinery is subdivided into three technical branches: pesticide application, components, and intelligence. The application technology methods such as variable pesticide application, target pesticide application, electrostatic spray, and wind curtain air delivery are summarized, the technical principles of equipment such as chassis, spray boom balance, and robot drive are analyzed, and the application of intelligent technologies such as drone driving, line walking, and visual navigation are explained. From the perspective of remote management, it also explains the intelligent construction of operation planning, scheduling decision-making, operation evaluation, and digital platform. Comparison of domestic and international technology levels suggests that the future development of plant protection machinery should focus on low-volume, precise pesticide application methods, specialized equipment components, and autonomous, intelligent operation modes. As artificial intelligence continues to advance, plant protection equipment with capabilities for intelligent perception, analysis, decision-making, and automation is expected to dominate future development.

Appearance quality is an important indicator in assessing the quality of dried chrysanthemums. To achieve rapid and non-destructive detection of the appearance quality of chrysanthemums during drying, this study applied computer vision technology in the infrared-assisted hot air drying of chrysanthemums and developed a Python-based image processing algorithm to acquire information on the changes in the shrinkage and color of petals and stamens of chrysanthemums at different temperatures (35 ℃, 50 ℃, and 65 ℃). These parameters serve as evaluation indices for the appearance quality and facilitat precise control of the drying process. The kinetic analysis showed that the drying of chrysanthemums had a consistently decreasing drying rate. High drying temperatures significantly reduced drying time and increased drying rates (p<0.05). Evaluation of the fit of mathematical models for thin-layer drying, including the Henderson and Pabis model, the Page model, and the Lewis model, showed that these models were in better agreement with the experimental data and thus more accurately described the drying process of chrysanthemums. Furthermore, changes in shrinkage rate and lightness (L*), red/green (a*), and yellow/blue (b*) values during drying showed that the morphological and color of chrysanthemums depended on drying temperature and time. Lower temperatures and shorter drying times were favorable for maintaining the appearance quality of the chrysanthemums. Linear regression analysis using zero-order, first-order, and first-order fractional models showed that the first-order fractional model provided more accurate predictions of shrinkage and color changes during the drying process of chrysanthemums.

Propelled by the era of big data, intelligent question-answering systems have found widespread applications across various domains, offering users a means to swiftly and efficiently acquire answers. Compared to traditional methods of collecting textual knowledge and utilizing web search engines, these systems demonstrate distinct advantages. With the rapid evolution of knowledge graph technology, intelligent question-answering systems have entered a new stage of development. In response to the call for smart agriculture, this study has undertaken the construction of a knowledge-based question-answering system based on knowledge graphs, aiming to provide users with question-answering services related to crop diseases and pests. The primary tasks include: (1) Acquisition of crop disease and pest data: Employing a distributed web crawling framework to retrieve data from web pages related to crop diseases and pests and preprocessing operations involve data cleaning, analysis, and structuring. (2) Construction of knowledge graph: Following data analysis, defining entity and relationship categories for the knowledge ontology and completing the pattern layer construction of the knowledge graph. Utilizing rule-based triple templates for extracting entities from semi-structured text, building the data layer, and storing triples in the Neo4j graph database. (3) Design of question-answering algorithms: Employing the BERT-BiLSTM-CRF model for question entity recognition and the BERT-RNN model for question classification. Matching templates, executing queries through Cypher statements, and processing answers into natural language forms for return. (4) Implementation and visualization of the question-answering system: Integrating crop disease and pest knowledge graphs with question-answering algorithms, the Flask framework and various web technologies are used to implement functionalities such as user questioning, entity recognition, knowledge retrieval, and answer presentation. Experimental results indicate that the entity recognition and question classification models achieved Precision (P), Recall (R), and F1 scores of 93.22%, 92.69%, 92.21%, and 94.37%, 93.92%, 92.66%, respectively. Compared to other search methods, the question-answering system demonstrated higher accuracy and stability. This study provides an intelligent solution for agricultural informationization, offering a new pathway for users to acquire knowledge on crop diseases and pests.