Design of Conveying Control System for Sugarcane Harvester Based on Machine Vision

The mismatch between the conveying capacity of sugarcane harvesters and the feeding amount is the main cause of blockages in the conveying system. To address this issue, this paper proposes a control system that integrates machine vision technology with a programmable logic controller (PLC). First, the YOLOv8n segmentation algorithm is combined with depth data to detect the cane intake amount. Then, through interactive experiments, the relationship between roller speeds and feeding amount is explored, and PLC control rules are established. The experimental results show that the system has an average detection error of 5.69%, an overall response time of 2 s, and the blockage rate at the maximum feeding amount is reduced from 17.76% (without control) to 4.32% (with control).