Harvesting timing can directly determine the flavor quality of the fruit in large-scale intelligent cultivation. However, the uneven spatial distribution of factors, such as light and nutrients, can lead to variations in the fruit maturity among different trees, even among various parts of the same tree. Conventional detection can rely primarily on manual experience for sampling and discrimination. It is often required to accurately assess the overall maturity of the peach orchard in the sustainable industry. Furthermore, the differing ripening times of fruits in natural environments can combine with the complex interferences, such as foliage occlusion and fruit overlap. It is further difficult to accurately identify the peach maturity in orchards. According to the maturity requirements for harvested peaches in the national standard (NY/T 586-2002), and the technical code for peach storage (GB/T 26904-2020), previous study has conducted to classify the peach fruit maturity into three categories using color: 1) Unripe peach (up): The fruit surface is entirely green with no sign of color change; 2) Half-ripe peach (hp): The fruit surface can share a mix of red and green, where the color-changed area is less than 50%; 3) Ripe peach (rp): the color-changed area on the fruit surface can exceed 50%. In this study, an improved YOLOv8n model was proposed to identify the peach maturity in orchards. 1) The original Conv module was replaced with the PMSEConv (Peach Multi-Scale Efficient Convolution) module to capture multi-scale contextual features with fewer missed and false detections. 2) Peach Occlusion Attention mechanism (POAttention) was introduced into the Neck section to improve the detection accuracy for peach maturity in high-density and occluded environments. Finally, the EIoU loss function was adopted to optimize the bounding box regression, thereby enhancing the adaptability and practicality in complex orchard environments. Ablation experiment indicated that the improved YOLOv8n model shared better performance than before. Compared with the baseline YOLOv8n, the precision and recall rates increased by 5.2 and 2.8 percentage points, respectively, and the mean average precision (mAP@0.5) was improved by 5.9 percentage points. Simultaneously, the model complexity was effectively controlled, where the FLOPs and parameters were reduced by 0.5 G and 0.29 M, respectively, with a dual optimization of accuracy and computational efficiency. Compared with current mainstream object detection models, including RT-DETR, YOLOv3-tiny, YOLOv5, YOLOv6, YOLOv9, YOLOv10, YOLOv11, and YOLOv12, the improved YOLOv8n model was achieved in the optimal key metrics, with the precision of 84.5%, recall of 76.0%, and mAP@0.5 of 83.8%. Excellent performance was obtained in identifying the fruit maturity in complex orchard environments. The lightweight and efficient model can provide strong technical support for peach-picking robots in an intelligent orchard, thereby facilitating precise and efficient operations.

Manual sowing is often used in the early stage of seed breeding. However, the seed quality cannot fully meet the large-scale production in recent years. When sowing in the experimental field, 2-3 seeds are sown in each hole, where the small ones are removed and then the large ones after emergence. The seeds only require simple threshing and packaging. There is no need to clean and grade the seeds. Since 2015, most maize seeds have gradually replaced manual sowing with plot seeders. Small-scale experimental planting can be conducted through single-seed sowing. Therefore, the planting quality can be greatly improved during the experimental stage. The germination rate of seeds can increase for better consistency between seedling emergence and plant growth. It is necessary to grade the seeds, in order to better meet the requirements of single seed precision sowing in the seeder. The graded seeds have similar sizes and shapes, which is beneficial to the sowing qualification rate of the seeder. Maize seed grading before sowing has been one of the most important parts of seed breeding. There is a large demand for seed breeding machinery because seed breeding test has a heavy task, with many kinds and various modes. Therefore, it is necessary to develop the seed grading equipment for the different varieties of seed breeding tests. Efficient screening can be used to maintain an effective screening area, appropriate thickness of material layer, and effective movement. Numerous studies have focused mainly on the screen structure, vibration mode, screen hole shape, parameter optimization, and screening mechanism, in order to improve the screening performance of vibrating screens. However, it is still lacking in the existing grading equipment for seed breeding. The performance of seed breeding needs to be modified for better technical requirements. In this study, the variable-amplitude vibrating screen technology was proposed to improve the efficiency of seed grading and self-purification quality before sowing in seed breeding. A vibrating screen device was also designed for seed grading. Jingke 968 maize seed was taken as the test object. With the qualified rate of grading, operation time, and the number of plugging seeds as the test index, the response surface mathematical model was established by four-factor (feed port height, amplitude, vibration frequency, and screen inclination angle) three-level Box-Behnken test. The verification tests were carried out to optimize the parameters. There were highly significant effects of vibration frequency and screen inclination angle on the qualified rate of grading and operation time. The number of plugging seeds regression model was highly significant, but it was lacking in fitting, indicating the lower fitted regression model. There was no analysis of variance in the number of plugging seeds regression model. The greatest influence of vibration frequency was found on the qualified rate of grading, followed by the screen inclination angle, amplitude, and feed port height. There was the greatest influence of vibration frequency on the operation time, followed by the amplitude, screen inclination angle, and feed port height. The number of plugging seeds on the screen holes increased sharply at the low amplitude and vibration frequency. The very low self-purification was caused by the greater randomness in the number of plugging seeds. The optimal combination of parameters was obtained at the opening height of 19 mm, amplitude of 5 mm, vibration frequency of 8.25 Hz, and screen surface inclination angle of 7°. The validation test under the optimal conditions was 89.55% of the qualified rate of grading and 39 s of the operation time, which was basically consistent with the predicted after optimization. The better self-purification was achieved, where the number of plugging seeds was 8. The grading efficiency of the device was about 0.33 t/h. All the indicators can fully meet the design requirements. The operational performance was better than that of the uniform amplitude vibration grading device. The finding can provide a strong reference to design the seed grading equipment for seed breeding.

Sowing depth and simple blockage can limit the traditional planters in the wheat wheat-wide seedling belt during rotary tillage. In this study, the combination design was adopted with the fertilizer pipe and slide knife-type ditching. The slide knife-type ditching and fertilizer pipe were situated at the front-mounted of the working range gap of the wide seedling belt rotary tillage knife group. The coupling operation was realized for the slide knife-type ditching fertilizer pipe and rotary tillage knife group. Among them, the slide knife-type ditching and fertilizer pipe, rotary tillage knife group, seed distributor, and compaction wheel of the same seedling belt were collinear to create a wide seedling belt fertilization and sowing mode. The fundamental parameters were calculated for the blade line of the slide knife-type ditching fertilizer pipe and the arrangement of the rotary tillage knife group. An exponential function curve was fitted for the blade line, with a working depth of 100 mm. The rotary tillage knife group was featured by a symmetrical spiral arrangement with three rotary blades (L = 3) within the same soil soil-cutting area. In addition, the theoretical analysis was also carried out on the principle of cooperation between the slide knife-type ditching fertilizer pipe and the rotary tillage knife group. The discrete element simulation model was constructed to explore the traction force resistance of different slide knife-type ditching fertilizer pipes in the seedbed over time. A systematic investigation was made to clarify the influence of the relative position of the slide knife-type ditching fertilizer pipe and the rotary tillage knife group on the indexes, such as seedbed and sowing depth. The simulation results showed that there was the smallest resistance of 40° slide knife-type ditching fertilizer pipe. The front-mounted fertilizer pipe and rotary tillage knife group were combined to effectively avoid the influence of the fertilizer ditch on the consistency of sowing depth in the wide seedling belt. The field experiment was carried out with reference to the performance experiment standard of sowing operation. The experiment demonstrated that the new planter was better performed to realize the wide seedling belt sowing, when the forward speed of the machine was 1.11 m/s. The bBetter performance was achieved in the uniform sowing and a highly qualified rate of sowing depth, compared with the traditional planter. The qualified rate of sowing depth was 94.36%, while the coefficient of variation was 3.79%, indicating the excellent sowing. The front-mounted fertilizer pipe and the rotary tillage knife group were combined to form an 'inverted triangle' spatial pattern of three-dimensional distribution in the seed bed. This was also beneficial to the early nutrient absorption of the crop. The blockage was further avoided to cause by the small spacing between the fertilizer pipe and the seed distributor. The high passing was fully met the requirements for the wide seedling belt wheat planting. The findings can provide the support to optimize the wheat sowing device in the wide seedling belt.

Seed clearing is a critical stage during precision seed metering process to ensure high seed singulation. However, there is a lack of understanding of the dynamics in the seed clearing process. In this study, a model was developed to predict initial seed clearing angle, in the seed clearing process using vector fields. The model was applied to an existing high-speed metering device and soybean seeds, and the model was evaluated with bench testing results. Results showed that dynamic changes in forces and constraints of seeds during the seed clearing process could be abstracted as vectors, and the changes of vector directions could be described by their phase angles. The phase angles were functions of the rotational angle of the seed meter. The phase angle of the constraint boundary linearly increases with the increase of the rotational angle. The phase angle of the force fluctuates, as the rotational angle changes. Initial seed clearing angle obtained from the phase angles varies from 8° to 59°, depending on the seeder travel speed. When comparing the values of the initial seed clearing angles predicted by the model with those from the bench tests, the root mean square error (RMSE) were from 2.73 to 3.14, and the correlation (r) between predict and observer were all higher than 0.98, indicating that the model had reasonably good accuracy.

Thousands of plots can be required to sow in the breeding fields. The seeds cannot be mixed among plots, due to different varieties need to be sown in each plot. A plot seeder can be used to fully meet the requirements, such as continuous and interval sowing. Therefore, the seeder needs to be frequently cleaned and replace seeds, which is different from the field seeder. Fortunately, neatly arranged aisles can be expected to strengthen the isolation between varieties and mutual influence. At the same time, it is convenient to walk in the aisle between plots, in order to conduct the field surveys during harvesting. However, the seeds can be inevitably sown on the aisle between plots, particularly in the existing maize plot planters. Two reasons can be attributed to the excessive seeding in the seed metering device. One, the seeds in the seed filling cavity cannot be cleaned in time, resulting in the seed plate absorbing the excess seeds. Another, the seed plate is filled with the seeds too early at the moment when the seeds of the next plot enter the seed-filling cavity. Furthermore, air-suction seed metering devices have been widely used in most plot precision seeders, due to their better seeding performance. In this study, a blocking-type air-suction seed metering device was designed to improve the consistency of aisle width between maize plots. The technical idea was extended to accurately block the excess seeds that were adsorbed by the seed plate into the seed-throwing area. A blocking function was added to the traditional plot seed metering device. The filling-cleaning-changing functions were shifted to the continuous filling-blocking-cleaning-changing operations of the plot seed metering device. The movement trajectory of the blocked seeds was reasonably planned. Mechanical and kinematic analyses were conducted on the maize seeds in the seed-blocking stage. The key parameters of the blocking mechanism were determined, according to the brachistochrone curve. The brachistochrone curved surface was used to simulate the contact surface between the blocking plate and the blocked seed. The main parameters of the rotating circle corresponding to the brachistochrone curved surface were determined as a radius of 53.70 mm and a rotation angle of 0.482π. The linkage plate in the blocking mechanism was used to prevent the seed cleaning airflow from sucking away the seeds to be sown on the seed plate during seed cleaning, thus causing missed sowing. The key parameters of the blocking mechanism were determined after optimization. A two-factor six-level full factorial bench test was carried out to take the test factors as the reaction distance of the blocking plate triggering the closing action and the closing state duration distance. The results showed that the probability of adsorbing one more seed at the end of the previous plot was 33.33%, and the probability of adsorbing one more seed in advance of the next plot was 10.00%. The blocking effect was dominated by the reaction distance after the blocking plate triggered the closing action and the closing state duration distance. When the reaction and duration distance were 1.2 and 0.8 m, respectively, the device was used to successfully block 4 suction holes between the neighboring plots of the seed discharging plate. The optimal combination of operation parameters was verified by the field tests, indicating the normal seeds to be sown. The blocking success rate of the blocking-type air-suction seed metering device was 100%, and the coefficient of variation of aisle width between plots was 4.19%. The coefficient of variation was reduced by 9.47 percentage points, compared with the traditional device. There was a better alignment of the aisle between plots in the maize plot after the operation using the blocking-type air-suction seed metering device. The blocking mechanism fully met the actual operational requirements. The finding can also provide the technical reference to promote the maize plot seeder.