基于机器视觉的金属工件智能分拣系统设计  

Design of Metal Workpiece Intelligent Sorting System Based on Machine Vision

作　　者：张炳星 高军伟 Zhang Bingxing;Gao Junwei(School of Automation,Qingdao University,Qingdao,Shandong 266071,China)

机构地区：[1]青岛大学自动化学院,山东省工业控制技术重点实验室,山东省青岛市266071

出　　处：《工具技术》2023年第3期140-144,共5页Tool Engineering

基　　金：山东省自然科学基金资助(ZR2019MF063)。

摘　　要：针对传统工业中人工分拣效率低和成本高等问题,设计了基于机器视觉的机械臂智能分拣系统。通过摄像头采集图像并对图像进行灰度滤波操作后,使用SOA-OTSU算法对图像进行阈值分割,对目标区域进行Blob连通域分析,实现对工件的识别与定位。运用标准D-H参数法建立三自由度机械臂模型,将工件位置坐标代入逆运动学方程,解得每个连杆的关节转角,将其转化为机械臂步进值,并通过串口通信方式发送给Arduino,由Arduino控制机械臂完成工件的抓取与放置。实验结果表明,该方法提高了分拣系统抓取的准确性。Aiming at the problem of low efficiency and high cost of manual sorting in traditional industry, an intelligent sorting system based on machine vision is designed.The image is collected by camera, and the gray filtering operation is performed on the image, SOA-OTSU algorithm is used to segment the threshold value of the image, and then Blob connected domain analysis is performed on the target area to realize the recognition and location of the workpiece.The standard D-H parameter method is used to establish a 3-DOF mechanical arm model, the position coordinates of the workpiece are put into the inverse kinematics equation, and the joint rotation angle of each connecting rod is solved, which is converted into the stepping value of the mechanical arm, and then sent to Arduino through serial communication.The Arduino controlls the mechanical arm to complete the grasp and placement of the workpiece.Experimental results show that this method can improve the accuracy of the sorting system.

关 键 词：机器视觉 SOA-OTSU Blob连通域 Arduino控制 

分 类 号：TG87[金属学及工艺—公差测量技术] TH122[机械工程—机械设计及理论] TP241[自动化与计算机技术—检测技术与自动化装置]