无坡口对接焊缝特征角点检测方法

  • 王文超 ,
  • 高向东 ,
  • 丁晓东 ,
  • 张南峰
展开
  • 广东工业大学 广东省焊接工程技术研究中心, 广州 510006
王文超,男,1989年出生,硕士研究生.研究方向为焊接自动化.Email:wwc8882@163.com

收稿日期: 2017-03-03

  网络出版日期: 2019-07-16

基金资助

国家自然科学基金资助项目(51675104);广东省科技发展专项资金资助项目(2016A010102015);广东省教育厅创新团队项目(2017KCXTD010)

Detection of non-groove butt joint feature based on corner principle

  • WANG Wenchao ,
  • GAO Xiangdong ,
  • DING Xiaodong ,
  • ZHANG Nanfeng
Expand
  • Guangdong Provincial Welding Engineering Technology Research Center, Guangdong University of Technology, Guangzhou 510006, China

Received date: 2017-03-03

  Online published: 2019-07-16

摘要

针对无坡口平板对接焊缝,研究一种应用线结构光传感的角点检测原理实现焊缝特征检测与跟踪的方法.与基于线结构光形变特征检测焊缝位置的传统方法不同,根据激光条纹在焊缝处的灰度变化,运用图像形态学处理方法,提取焊缝中心特征.计算图像每列邻域内灰度值和,运用中心差分方法,提取焊缝图像感兴趣区域.再依据角点检测原理,确定焊缝中心亚像素级坐标位置,通过简单快速的系统标定,得到焊缝实际位置偏差.结果表明,对焊缝间隙为0.2 mm左右的对接焊缝进行跟踪试验,平均误差均保持在0.1 mm以内,满足焊缝跟踪精度要求.

本文引用格式

王文超 , 高向东 , 丁晓东 , 张南峰 . 无坡口对接焊缝特征角点检测方法[J]. 焊接学报, 2018 , 39(9) : 61 -64 . DOI: 10.12073/j.hjxb.2018390225

Abstract

A method for detecting and tracking the non-groove butt joint by using the principle of corner detection based on line structured light vision sensing is studied. It is different from the traditional line structured light sensing method to detect the weld position according to the deformation feature. The proposed method applies for the fact that the laser stripe has obvious gray gradient variation in the weld. The morphological image processing method is adopted to extract the feature of weld center. The gray value of each column in the image is calculated, and the region of interest is extracted by the central difference method. According to the principle of the corner detection method, the sub-pixel coordinates of the weld center can be determined accurately. The actual position deviation of the weld is obtained by using a simple and fast system calibration. Experimental results show that the average error can be kept within 0.1 mm by tracking a butt joint whose width is about 0.2 mm, which can meet the requirement of seam tracking precision.

参考文献

[1] He Y, Xu Y, Chen Y, et al. Weld seam profile detection and feature point extraction for multi-pass route planning based on visual attention model[J]. Robotics & Computer-Integrated Manufacturing, 2015, 37:251-261.
[2] 陈海永, 孙鹤旭, 徐德. 一类窄焊缝的结构光图像特征提取方法[J]. 焊接学报, 2012, 33(1):61-64 Chen Haiyong, Sun Hexu, Xu De. An image feature extraction method for a certain kind of narrow gap weld seam[J]. Transactions of the China Welding Institution, 2012, 33(1):61-64
[3] 邹勇, 李运华, 蒋力培, 等. 基于熔池图像尖端特征规律的焊接偏差测定方法[J]. 焊接学报, 2015, 36(8):18-22 Zou Yong, Li Yunhua, Jiang Lipei, et al. Method of detecting weld deviation based on the image feature of molten pool's edge[J]. Transactions of the China Welding Institution, 2015, 36(8):18-22
[4] Gao X, Mo L, Xiao Z, et al. Seam tracking based on Kalman filtering of micro-gap weld using magneto-optical image[J]. The International Journal of Advanced Manufacturing Technology, 2016, 83(1-4):21-32. doi:10.1007/s00170-015-7560-x
[5] 章为川, 孔祥楠, 宋文. 图像的角点检测研究综述[J]. 电子学报, 2015, 43(11):2315-2321 Zhang Weichuan, Kong Xiangnan, Song Wen. Review of image corner detection algorithms[J]. Chinese Journal of Electronics, 2015, 43(11):2315-2321, doi:10.3969/j.issn.0372-2112.2015.11.026
文章导航

/