基于生成式对抗网络的龙门式焊接机器人双目视觉方法  

Binocular Vision Method for Gantry Welding Robot Based on Generative Adversarial Networks

作　　者：龚文华 刘钊[2] 王兴东[3] GONG Wenhua;LIU Zhao;WANG Xindong(School of Automotive Engineering,Xiangyang Polytechnic,Xiangyang 441050,China;School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;School of Mechanical Automation,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]襄阳职业技术学院汽车工程学院,湖北襄阳441050 [2]武汉科技大学计算机科学与技术学院,湖北武汉430065 [3]武汉科技大学机械自动化学院,湖北武汉430081

出　　处：《信息与控制》2024年第6期783-792,共10页Information and Control

基　　金：国家自然科学基金项目(52375117)

摘　　要：为了克服电弧焊中焊接件热膨胀变形、烟雾干扰视觉导致难以获取准确的焊缝信息的问题,实现对于非标大型工件的自动焊接功能,本文设计了双目视觉焊缝空间位置信息采集系统,配置了红色线型结构激光、窄带红色滤镜和双目视觉相机,与焊枪一起固定在机器人的执行末端,在焊接过程中对于焊缝进行实时图像采集和位置感知。本文设计了生成式对抗网络(GAN)架构的深度学习神经网络,并采用了迁移学习进行跨域训练。实验表明,所设计的双目视觉系统能有效利用双目图像数据,实时输出在焊接区域里焊缝的位置和深度,在无专门图像校正的条件下,焊接过程中焊缝横向位置和焊缝高度二者的识别精度均可达1.0 mm。本文设计的焊接机器人双目视觉方法简明可行且成本低廉。To overcome issues such as thermal deformation of welded components and interference from smoke that make it difficult to obtain accurate weld seam information,this study designs binocular vision system based weld seam spatial position information acqusition for automatic welding of non⁃standard large workpieces.The system includes a red⁃line structured laser,narrow⁃band red filter,and binocular vision cameras fixed together with the welding gun at the robot′s effector.During welding,real⁃time image capture and position sensing of the seam are performed.A deep learning neural network based on the generative adversarial network(GAN)architecture is designed,and transfer learning is employed for cross⁃domain training.Experimental results demonstrate that the designed binocular vision system can effectively process binocular data,providing real⁃time seam position and depth.Without specialized image calibration,the recognition accuracy of the lateral position and height of the weld seam during the welding process can reach 1.0 mm.The proposed binocular vision method for welding robots is concise,feasible,and cost⁃effective.

关 键 词：焊缝跟踪 双目视觉 深度学习 焊接机器人 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP242[自动化与计算机技术—计算机科学与技术] TG409[金属学及工艺—焊接]