Fully Automated Dispensing System Based on Machine Vision

Abstract

The manual dispensing and semi-automatic dispensing process in small and medium-sized electronic enterprises has the problems of low productivity and large dispensing positioning errors. This study takes RJDNEL-type PCB boards as the research object, proposes a fully automatic dispensing method based on machine vision, and plans the dispensing path. The method is based on vision imaging technology, and the optimized minimum outer rectangle algorithm is used to complete the extraction of dispensing positioning information; combined with the proposed path planning method based on a simulated annealing algorithm, the operational efficiency of the dispensing system is improved. The experimental results show that: the dispensing efficiency of the proposed path planning method is improved by 20%~30% compared with the traditional method; the positioning accuracy error of the system is less than 0.02mm; the matching accuracy is more than 99%, and the matching point positioning accuracy error is less than 0.02mm, which effectively improves the dispensing accuracy and dispensing efficiency while satisfying the dispensing quality