引用本文:
【打印本页】   【HTML】   【下载PDF全文】   查看/发表评论  【EndNote】   【RefMan】   【BibTex】
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 703次   下载 345 本文二维码信息
码上扫一扫!
分享到: 微信 更多
基于改进的边界追踪算法的管道法兰焊缝识别
钱晓明, 杨丽娟, 楼佩煌
南京航空航天大学 机电学院, 南京 210016
摘要:
针对目前管道法兰焊接中存在的缺点,文中对管道法兰焊缝进行先检测后识别,提出了一种基于改进的边界追踪算法的管道法兰焊缝识别方法.在焊缝检测阶段,利用曲率角估计的方法精确确定焊缝位置.在焊缝识别阶段,利用膨胀和掩码操作,根据检测到的焊缝位置,提出了一种在原图中设置不规则感兴趣区域的方法;细化边缘,并提出一种过滤伪边缘的算法.通过实际焊缝的试验验证,结果表明,基于改进的边界追踪算法的管道法兰焊缝识别方法能够准确的识别焊缝边缘,并且系统的识别稳定性好.
关键词:  焊缝识别  边界追踪  曲率角估计  不规则感兴趣区域  伪边缘过滤
DOI:
分类号:
基金项目:江苏省重点研发计划项目(BE2016004-3);江苏省精密与微细制造技术重点实验室开放基金项目;江苏省产学研合作前瞻性联合研究项目(BY2015003-11)
Recognition of weld seam for pipe flange based on improved boundary following algorithm
QIAN Xiaoming, YANG Lijuan, LOU Peihuang
College of Mechanical and Electrical Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Abstract:
For the disadvantages existing in the current pipe flange welding, a method was proposed to of recognize the weld seam for pipe flange based on improved boundary following algorithm, which is divided into two steps of detecting the position of weld seam and then recognizing the weld seam accurately. At first, a method of curvature estimation was applied to position the weld seam in the detecting process. Secondly, a method to set irregular region of interest through dilation and mask in the original image was proposed based on the position of weld seam. And then the edge was thinned, and an algorithm was proposed to filter the pseudo edge. Experiments results showed that the proposed method is reliable and can recognize the weld seam accurately.
Key words:  weld recognition  curvature estimation  boundary following  irregular ROI  pseudo edge filtering