In this paper, a garlic combine harvester machine was designed and some influential parameters of the machine were optimized. The working parts of the machine mainly consisted of a reel, a reciprocating cutter, a seedling conveyor, a profiling depth-stop device, a digging shovel and a lifting chain. Each part had unique structural parameters and motion parameters, as different parameters would deeply affect the performance of the machine. A logistical regression algorithm was utilized to analyze the working speed of the reel, the digging depth of the reciprocating cutter and the lifting speed of the lifting chain. This paper also discussed the influence of these three functions on the damage rate based on the collected data when harvesting garlic. Specifically, each function was tested 60 times for collecting data. The experimental results showed that the order of influence of the three functions on the damage rate was the digging depth, working speed and lifting speed. Moreover, the lowest damage rate was 0.18% when the digging depth was 100 mm, the working speed was 1.05 km·h⁻¹ and the lifting speed was 0.69 m·s⁻¹. A validation test was taken out based on the three functions of the analysis results, and the damage rate was 0.83%, which was close to the analysis results, and proved that the analysis results were accurate and meaningful. The research results are beneficial to the development and application of the garlic combine harvester.

Prior to dispatch from manufacturing facilities, seeders require rigorous performance evaluations for their seeding capabilities. Conventional manual inspection methods are notably less efficient. This study introduces a wheat seeding detection approach anchored in an enhanced YOLOv5s image-processing technique. Building upon the YOLOv5s framework, we integrated four CBAM attention mechanism modules into its model. Furthermore, the traditional upsampling technique in the neck layer was superseded by the CARAFE upsampling method. The augmented model achieved an mAP of 97.14%, illustrating its ability to elevate both the recognition precision and processing speed for wheat seeds while ensuring that the model remains lightweight. Leveraging this advanced model, we can effectively count and locate seed images, enabling the precise calculation and assessment of sowing uniformity, accuracy, and dispersion. We established a sowing test bench and conducted experiments to validate our model. The results showed that after the model was improved, the average accuracy of wheat recognition was above 97.55% under different sowing rates and travel speeds. This indicates that this method has high precision for the total number of seed particles. The sowing rate and sowing travel speed were consistent with manual measurements and did not significantly affect uniformity, accuracy, or dispersion.

The technology of the divider and lifter mechanisms of a garlic harvester using the depth limit, straw divide, and straw lift modes was studied in Lanling County, Shandong Province, China, according to the characteristics of high hardness, good uprightness and narrow row spacing of garlic planting. A test prototype of the divider and lifter mechanisms of the garlic harvester was designed and manufactured. Single-factor experiments and orthogonal regression experiments were carried out using the experimental factors of working speed, the angle of the divider, the height of the tip of the divider’s tooth from the ground, the ratio of the lifter’s speed to working speed and the length of the lifter’s tooth. The index was the success rate of feed. The results showed that the working speed, the angle of the divider and the length of the lifter’s tooth had a significant influence on the success rate of feed (p < 0.05), but the experimental factors of the height of the tip of the divider’s tooth from the ground and the ratio of the lifter’s speed to working speed did not have a significant influence on the success rate of feed (p > 0.05). The effects of the angle of the divider, the working speed, and the length of the divider’s tooth on the success rate of feed decreased in significance. When the working speed was 0.72 km·h⁻¹, the length of the lifter’s tooth was 343.5 mm and the angle of the divider was 20°, the success rate of feed was the highest (98.18%). The research results are conducive to promoting high-quality and efficient combined harvesting of garlic in Lanling County, Shandong Province, China.

Given the problem that traditional garlic cultivation patterns in China have difficulty in achieving comprehensive mechanized production, an experimental investigation on mechanization-friendly cultivation agronomy was conducted. In this study, an orthogonal experimental method was used to conduct continuous tracking experiments for three years in three major garlic production regions of China. All the experiments were used to verify the impacts of sprout orientation, planting mode, planting density, and row spacing on garlic bulb yield per hectare. For every impact, nine experiments were processed. The results indicated the following: (1) planting density influenced the garlic bulb yield per hectare extremely significantly, followed by row spacing, planting pattern, and sprout orientation; (2) the combination of sprout orientation (1–45°), planting pattern (large ridge), a planting density (42.75)/10,000 plants per hectare, and row spacing (26 + 10) led to the largest garlic bulb yield per hectare, which means this combination was the best form of cultivation agronomy. This study will provide a valuable reference for China’s farmland suitability for agricultural machinery operation (FSAM) production program.

In this study, a leading–drawing–cutting–type profiled root–trimming device was designed to address the problems of high impurity and damage rates that occur with the operation of a pull–cut garlic harvester. The main components of the designed device include a pull–clamp mechanism, roll–pulling mechanism, root–trimming knife mechanism, lifter, gearbox, universal drive shaft, motor, and frame that, together, can complete the root–trimming operation for a pull–cut garlic harvester. An orthogonal regression test was carried out by taking the roller diameter, the roller inclination angle, the knife rotation speed, and the working speed as factors and by taking the impurity rate and the damage rate as indices. The results of the orthogonal regression test showed that the impurity rate was most strongly affected by the roller diameter, followed by the knife rotation speed, the working speed, and the roller inclination angle. Meanwhile, the damage rate was most strongly affected by the knife rotation speed, followed by the roller diameter, the working speed, and the roller inclination angle. The regression analysis showed that when the roller diameter was 100 mm, the roller inclination angle was 25°, the knife rotation speed was 200 r·min⁻¹, and the working speed was 1.22 km·h⁻¹, the comprehensive trimming quality reached its maximum value of 97.82%. The verification result of the parallel test gave a value of 97.52%, which was mainly affected by the irregular sizes of the bulbs, but it showed no significant difference from the regression analysis results. The tests verified that the profiled root–trimming device could be applied to develop the technology of garlic pull–cut harvesters.

After undergoing peeling-machine operations, skinned garlic cloves affect subsequent processing, and their manual removal is harmful to health. In this paper, an intelligent garlic-clove-removal test bench was designed, which mainly included a hopper, lifter, vibration conveyor, conveyor belt, visual system, removal robot, control cabinet, frame, etc. A technical method based on machine vision technology to distinguish whether or not garlic cloves had a skin was explored to ensure that the test bench could complete the recognition of the skinned garlic cloves, and to check that the test bench could also complete the removal of skinned garlic cloves. Tests were carried out to check the success rate of machine vision and the removal robot, and to optimize the parameters of the test bench. The results showed that the average success rate of machine vision was 99.15%, and the average success rate of the removal robot was 99.13%. The results also showed that the order of the three factors influence index was the conveying speed, the conveying volume, and the removal period. The regression analysis showed that when the conveying speed was 0.1 m·s⁻¹, the grasping period was 1.725 s, the conveying volume was 104.4 kg·h⁻¹, the qualified rate of the finished product was 97.15%, and the verification test result was 97.02%, which had no significant difference from the analysis result. The research results of this paper are conducive to the development of intelligent detection technology of garlic cloves, and to the development of garlic-planting technology and deep processing technology.