现代制造工程 ›› 2024, Vol. 530 ›› Issue (11): 18-25.doi: 10.16731/j.cnki.1671-3133.2024.11.003

• 试验研究 • 上一篇    下一篇

基于改进U-Net算法的焊缝特征识别研究*

龚律凯1,2, 彭伊丽1,2, 陈绪兵1,2, 韩桂荣1,2,3, 李慧怡4   

  1. 1 武汉工程大学机电工程学院,武汉 430205;
    2 武汉工程大学智能焊接装备与软件工程技术湖北省研究中心,武汉 430205;
    3 湖北美术学院工业设计学院,武汉 430205;
    4 湖北工业大学计算机学院,武汉 430068
  • 收稿日期:2024-01-25 出版日期:2024-11-18 发布日期:2024-11-29
  • 通讯作者: 陈绪兵,博士,教授,研究方向为智能制造,物联网相关领域。E-mail:bluegif@gmail.com
  • 作者简介:龚律凯,硕士研究生,研究方向为智能制造与机器视觉。E-mail:312361430@qq.com
  • 基金资助:
    *国家自然科学基金项目(52205536);湖北省技术创新重点研发计划项目(2023BAB071)

Research on weld feature recognition based on improved U-Net algorithm

GONG Lükai1,2, PENG Yili1,2, CHEN Xubing1,2, HAN Guirong1,2,3, LI Huiyi4   

  1. 1 School of Mechanical and Electrical Engineering,Wuhan Institute of Technology,Wuhan 430205,China;
    2 Hubei Research Center of Intelligent Welding Equipment and Software Engineering Technology, Wuhan Institute of Technology,Wuhan 430205,China;
    3 School of Industrial Design,Hubei Institute of Fine Arts,Wuhan 430205,China;
    4 School of Computer Science,Hubei University of Technology,Wuhan 430068,China
  • Received:2024-01-25 Online:2024-11-18 Published:2024-11-29

摘要: 针对基于激光视觉机器人焊接过程中,由于噪声干扰导致焊缝激光条纹分割精度降低,不能精确焊接的问题,提出了一种改进U-Net算法的焊缝特征识别方法。改进型U-Net算法使用Mobile-Net作为主干网络,加强了网络的特征识别能力,并减少了模型的参数量。在编码与解码之间加入超强通道注意力机制,实现了特征的加权融合。模型采用混合损失函数,平衡了激光条纹在图像中的占比。在焊接机器人焊缝跟踪实验平台部署网络模型,实验结果表明,改进的U-Net算法平均交并比(Mean Intersection over Union,MIoU)为89.83 %,像素准确率(Pixel Accuracy,PA)为99.54 %,平均像素准确率(Mean Pixel Accuracy,MPA)为97.28 %,处理图像的时间为0.209 s,相比其他算法,具备更优的分割精度和较快的处理速度,可以更好地应用于有干扰的机器人焊接场景中。

关键词: 图像分割, 机器人焊接, U-Net算法, ECA注意力机制, 焊缝特征识别

Abstract: Aiming at the problems of laser vision robots during the welding process,the laser stripe segmentation accuracy of the weld seam was reduced due to noise interference and the inaccurate welding,an improved U-Net weld seam feature recognition method was proposed. The improved U-Net algorithm incorporates Mobile-Net as the underlying network,thereby augmenting the network′s capability for feature recognition and reducing the number of model parameters. Efficient channel attention network was added between encoding and decoding to achieve weighted fusion of features.The model adopted a mixed loss function to balance the proportion of laser stripes in the image. The network model was implemented on the experimental platform for seam tracking in welding robots. Experimental results showed that the Mean Intersection over Union (MIoU) of the improved U-Net algorithm was 89.83 %,the Pixel Accuracy (PA) was 99.54 %,the Mean Pixel Accuracy (MPA) was 97.28 %,and the image processing time was 0.209 s.Compared with other algorithms,it has better segmentation accuracy and faster processing speed.It can be more effectively applied to robot welding scenarios with interference.

Key words: image segmentation, robot welding, U-Net algorithm, ECA attention mechanism, weld feature recognition

中图分类号: 

版权所有 © 《现代制造工程》编辑部 
地址:北京市东城区东四块玉南街28号 邮编:100061 电话:010-67126028 电子信箱:2645173083@qq.com
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn