Corn harvester row alignment is a critical factor to improve harvesting quality and reduce cob drop loss. In this paper, a corn harvester automatic row alignment system is designed with a self-propelled corn combine harvester, incorporating a front-end touch row alignment mechanism of the cutting table and a harvester steering control system. Corn stalk lateral deviation from the reference row during harvesting is detected by a front-end touch-row alignment mechanism that serves as an input to the automatic alignment system. The harvester steering control system consists of Hirschmann PLC controller, electric steering wheel, steering wheel deflection angle detection device, display module and mode selection module, etc. The adaptive fuzzy PID control algorithm is used to determine the desired turning angle of the harvester steering wheel by combining with the harvester kinematic model, and the model is simulated and analyzed by Matlab/Simulink software. The automatic row alignment system was mounted on a 4LZ-8 self-propelled corn harvester for field tests, and the test results showed that the average percentage of deviation of corn stalks from the center of the row alignment cutting path within ±15 cm during the automatic row alignment process was 95.4% at harvester speeds ranging from 0 to 4.6 km/h, which could meet the requirements of the corn harvester for row alignment harvesting. The test results meet the requirements of the corn harvester for row alignment and serve as a benchmark for the research on automatic row alignment of corn harvesters.

Detection of maize leaf diseases using improved MobileNet V3-small

Garlic planting requires a single seed with a scaly bud upward and vertically. In this study, an automatic garlic seed directing device was designed for auxiliary garlic seeding by utilizing a seed placed funnel, a correcting mechanism, and an automatic control system. Three factors influenced device performance: characteristics of garlic seeds, limited notch diameter of the seed placed funnel, and funnel taper of the seed placed funnel. The most optimal structural parameters of the seed placed funnel were determined via theoretical analysis. The research samples of Lanling and Jinxiang garlic were divided into three groups according to their respective sizes. 3D design software (Solidworks) was used to simulate the above three factors and analyze their rules of action. The obtained simulation results demonstrated that the suitable range of funnel taper and limited notch diameter of seed placed funnel for the three groups of seed were from 40° to 60° and 6-8 mm, respectively. The bench test showed that when the funnel taper was 60° and the limited notch diameter was 10 mm, the success rates of the three groups’ seeds in terms of scaly bud directing were 89.8%, 91.6% and 96.6% respectively, which satisfied the agricultural requirements of garlic planting. Accordingly, the corresponding results may promote the study and improvement of garlic intelligent planting equipment. Keywords: garlic, garlic seed directing, simulation and analysis, automatic control DOI: 10.25165/j.ijabe.20201306.5142 Citation: Geng A J, Li X Y, Hou J L, Zhang J, Zhang Z L, Chong J. Design and experiment of automatic garlic seed directing device. Int J Agric & Biol Eng, 2020; 13(6): 85–93.

Traditional maize ear harvesters mainly rely on manual identification of fallen maize ears, which cannot realize real-time detection of ear falling. The improved You Only Look Once-V4 (YOLO-V4) algorithm was combined with the channel pruning algorithm to detect the dropped ears of maize harvesters. K-means clustering algorithm was used to obtain a prior box matching the size of the dropped ears, which improves the Intersection Over Union (IOU). Compare the effect of different activation functions on the accuracy of the YOLO-V4 model, and use the Mish activation function as the activation function of this model. Improve the calculation of the regression positioning loss function, and use the CEIOU loss function to balance the accuracy of each category. Use improved Adam optimization function and multi-stage learning optimization technology to improve the accuracy of the YOLO-V4 model. The channel pruning algorithm was used to compress the model and distillation technology was used in the fine-tuning of the model. The final model size was only 10.77% before compression, and the test set mean Average Precision (mAP) was 93.14%. The detection speed was 112 fps, which can meet the need for real-time detection of maize harvester ears in the field. This study can provide a technical reference for the detection of the ear loss rate of intelligent maize harvesters. Keywords: maize ear detection, YOLO-V4, channel pruning algorithm, real-time detection DOI: 10.25165/j.ijabe.20221503.6660 Citation: Gao A, Geng A J, Zhang Z L, Zhang J, Hu X L, Li K. Dynamic detection method for falling ears of maize harvester based on improved YOLO-V4. Int J Agric & Biol Eng, 2022; 15(3): 22–32.

Applying different types of fertilizers to different depths of soil according to demand is advantageous in that it can optimize the distribution of nutrients in arable soil, adjust the nutrient supply of each growth stage of wheat, and increase grain yield. In the study, a layered fertilization opener that could realize the layered fertilization was developed. The interaction model between the opener, fertilizer and soil was established using EDEM simulation software. A response surface analysis was used to determine the optimal parameters of the opener. Specifically, the horizontal distance between the fertilizer drop openings was 140 mm, the machine speed was 1.05 m/s, and the angle of the opener was 37 degrees. Furthermore, field experiments demonstrated that the average depth of upper layer was 8.39 cm, the average depth of middle layer was 16.465 cm, the average depth of lower layer was 24.025 cm, the average spacing of upper layer was 8.075 cm, and the average spacing of lower layer was 7.6 cm. The corresponding findings demonstrated that the layering effect of the opener met the requirements of the fertilization standard.

Reducing ear damage is the key to improving the quality of maize harvests. In order to reduce the impact and damage of the ear caused by the ear snapping mechanism, this paper proposes a method to convert ear deformation energy during collision into elastic potential energy in the ear snapping mechanism. According to the above method, a low-damage maize snapping mechanism was designed. In order to verify the feasibility of energy conversion in reducing damage, the dynamic model of the contact between the ear and the snapping plate was established, and a dynamic simulation analysis was carried out based on the finite element method (FEM). In order to obtain better parameters for the improved mechanism, a test rig was established, after which a performance test was carried out on the test rig. The results showed that the primary and secondary order that affected the ear damage rate was the rotational speed of the snapping roller, the spring stiffness and the forward speed. The data processing software Design Expert was used to optimize the parameters, it was concluded that when the rotational speed was 805 r·min⁻¹, the forward speed was 1.29 m·s⁻¹, the spring stiffness was 33.5 N·mm⁻¹, the model predicted that the ear damage rate was 0.023%. Therefore, this paper could provide further reference for research into maize low-damage ear snapping technology.