Design and Experiment of the Automatic Laying System for Rice Seedling Tray

Abstract

In the process of raising rice seedlings, it is necessary to manually place the seedling trays one by one in the seedling field, which is labor intensive and low in efficiency. In order to solve this problem, according to the actual conditions of the rice seedling field, this paper designs and develops an automatic rice tray laying system, which consists of a gantry truss moving unit, a tray laying trolley unit, a tray laying mechanism unit and a sensor control unit. Through the movement and timing coordination of the cams in the laying mechanism unit, four actions of holding, clamping, laying and restoring are designed to realize the orderly and automatic laying of the stacked seedling trays one by one. In order to meet the agronomic requirements of the horizontal and vertical spacing of seeding trays, especially the efficiency of rice tray laying, the control strategies of the key parts of the system were simulated, selected and optimized. For the longitudinal movement of the gantry truss, the cross-coupling control strategy is adopted to realize the detection and compensation correction of the synchronous position error of the two driving motors. As for the drive motor of the laying trolley and the laying mechanism, the optimized master-slave follow-up control method is adopted to improve the efficiency and accuracy. The results of simulation and field experiment show that when the tray trolley moves on the gantry truss at the speed of 7.5 cm/s, the gantry truss moves at the speed of 35 cm/s in the longitudinal direction, and when the height of the tray laying mechanism is 100 mm from the ground and the motor speed is 375 rpm, the horizontal spacing of the tray can be maintained at 25 ± 5 mm and the vertical spacing at 15 ± 5 mm. The efficiency of tray laying can be increased by 35.7%, up to 380 trays/h, meeting the technical requirements of mechanized field tray laying.

Evaluation Model of Rice Seedling Production Line Seeding Quality Based on Deep Learning

“…Contrastingly, most contemporary rice seeding trays do not conform to a grid pattern and present a more stochastic seed distribution, increasing the complexity of detection, with scant research addressing seeding quality detection for this tray type. Detecting unseeded areas in rice seeding trays can empower farmers and producers to monitor production, analyze pertinent data, and render decisive support for reseeding tasks [10]. Therefore, this research centers on the analysis of rice seedling tray images, employing deep learning as the foundational technology.…”