基于机器视觉的液化气空罐工件搬运系统设计与研究  

Design and research of workpiece handling system forempty liquefied gas tank based on machine vision

作　　者：刘文婧[1] 张旭成 LIU Wenjing;ZHANG Xucheng(School of Mechanical Engineering,Inner Mongolia University of Science&Technology,Baotou 014010,China)

机构地区：[1]内蒙古科技大学机械工程学院,内蒙古包头014010

出　　处：《内蒙古科技大学学报》2024年第4期403-408,共6页Journal of Inner Mongolia University of Science and Technology

基　　金：国家自然科学基金(52075270);内蒙古自治区自然科学基金(2022MS05006)。

摘　　要：工业机器人以示教方式抓取搬运不同位姿的工件时无法精准定位,需复杂定位工装辅助定位。针对这一问题,提出一种基于机器视觉的液化气空罐工件搬运系统方案。基于Open-CV与pclpy视觉库编写视觉定位程序引导工业机器人实现液化气空罐工件的钩取搬运。经实验测试,提出的基于机器视觉的液化气空罐工件搬运系统方案可行,视觉定位程序的定位最大误差为0.63 mm。较以往的人工作业效率提升较大,具有实时定位工件、无需复杂定位工装的优势。Industrial robots face challenges in precisely locating,grasping,and transporting workpieces with various positions and postures using demonstration learning.Therefore,they typically require assistance from complex positioning tools.To address this,a new scheme had been proposed for handling empty liquefied gas tanks using machine vision.A visual positioning program had been developed to guide industrial robots to perform hooking and handling of liquefied gas empty tank workpieces based on the Open-CV and pclpy vision libraries.Experimental results demonstrate the feasibility of this new scheme,with a maximum error of 0.63 mm in the visual positioning program.In comparison to previous manual operations,the new program significantly improves the positioning efficiency.It offers the advantage of real-time positioning of workpieces without relying on complex positioning tools.

关 键 词：机器视觉 视觉点云 图像处理 工业机器人 视觉定位 

分 类 号：TP241.2[自动化与计算机技术—检测技术与自动化装置]