基于3D机器视觉的离心泵叶轮智能无序上料技术应用研究

Research on application of intelligent bin-picking technology of centrifugal pump impeller based on 3D machine vision

离心泵的生产目前仍以人工手动操作为主,为了提高离心泵生产的自动化程度,降低工人劳动强度,设计并搭建了基于3D机器视觉的离心泵叶轮智能无序上料系统。离心泵叶轮智能无序上料系统采用双目视觉结合结构光技术采集场景中的三维信息,重点研究了工程塑料、铝合金和不锈钢3种不同材料的叶轮在3D机器视觉下的成像表现,通过实验研究得出了光源设计的优化参数,实现了叶轮位姿的识别和抓取。此外,通过实验模拟了叶轮上料过程,在不同摆放条件下的抓取成功率均超过了90%,验证了离心泵叶轮智能无序上料系统的可行性,并分析了随机摆放条件下铝合金叶轮及不锈钢叶轮存在个别无法识别的原因。

At present, the production of centrifugal pump is still dominated by manual operation.In order to improve the automation of centrifugal pump production and reduce the labor intensity of workers, an intelligent bin-picking system of centrifugal pump impeller based on 3D machine vision was designed and built. The intelligent bin-picking technology of centrifugal pump impeller system uses binocular vision combined with structured light technology to collect three-dimensional information of the scene, and the imaging performance of impellers made of engineering plastics, aluminum alloy and stainless steel respectively under 3D machine vision was focused on. Through experimental research, the optimized parameters of light source design were given, and the position recognition and grasping of the impellers were realized.In addition, the feeding process of the impeller was simulated through experiments, and the success rate of grasping under different placement conditions is more than 90 %.The feasibility of the bin-picking system is verified, and the causes of individual unrecognition of the impellers made of aluminum alloy or stainless steel under random placement conditions were analyzed.