首页

首页 > 学术科研 > 正文

首页

学术科研
战略所人物
活动会议
合作交流
战略所动态
通知公告
视频

学术科研

WeldNet: An ultra fast measurement algorithm for precision laser stripe extraction in robotic welding

题目WeldNet: An ultra fast measurement algorithm for precision laser stripe extraction in robotic welding
作者Dai, Chuyi Wang, Congcong Zhou, Zhixuan Wang, Zhen Liu, Ding
作者单位Xidian Univ, Hangzhou Inst Technol, Hangzhou 311231, Peoples R China Univ Alberta, Fac Engn, Dept Elect & Comp Engn, Edmonton, AB T6G 1H9, Canada Tianjin Univ Technol, Sch Comp Sci & Engn, Minist Educ, Key Lab Comp Vis & Syst, Tianjin 300384, Peoples R China Minist Educ, Engn Res Ctr Learning Based Intelligent Syst, Tianjin 300384, Peoples R China Peking Univ, Guanghua Sch Management, Beijing 100871, Peoples R China
关键词：SEAM TRACKING SYSTEM
时间：2025年1月1日
出版者：MEASUREMENT
摘要The integration of laser vision sensors in robotic welding improves seam tracking accuracy, but welding noise poses significant challenges. Our research introduces WeldNet, enhances laser stripe extraction, significantly outperforming traditional and deep neural network (DNN) solutions inefficiency and measurement precision. WeldNet comprises lightweight modules for optimal feature extraction, including Multi-Part Channel Convolution (MPC) blocks, Parallel Shift Multilayer Perceptrons (PS-MLP), and Serial Shift MLP (SS-MLP). A specially designed data augmentation strategy is also integrated to address the complex noise encountered in robotic welding. Experimental results demonstrate WeldNet's effectiveness in reducing welding noise interference, achieving a real-time processing speed of 145 FPS on RTX 2080 Ti GPU, approximately 5x faster than existing state-of-the-art methods. With a Dice coefficient of 87.52% and an IoU value of 77.82%, WeldNet not only enhances operational efficiency but also markedly improves precision in industrial robotic welding.
URLhttp://hdl.handle.net/20.500.11897/729739
ISSN0263-2241
DOI10.1016/j.measurement.2024.116219
收录情况SCI€
作者单位 Xidian Univ, Hangzhou Inst Technol, Hangzhou 311231, Peoples R China Univ Alberta, Fac Engn, Dept Elect & Comp Engn, Edmonton, AB T6G 1H9, Canada Tianjin Univ Technol, Sch Comp Sci & Engn, Minist Educ, Key Lab Comp Vis & Syst, Tianjin 300384, Peoples R China Minist Educ, Engn Res Ctr Learning Based Intelligent Syst, Tianjin 300384, Peoples R China Peking Univ, Guanghua Sch Management, Beijing 100871, Peoples R China 时间 2025年1月1日
出版者 MEASUREMENT URL http://hdl.handle.net/20.500.11897/729739
ISSN 0263-2241 DOI 10.1016/j.measurement.2024.116219
收录情况 SCI€ 分类
TOP