Page 108 - 无损检测2024年第十期
P. 108

试验研究
              试验研究

              DOI:10.11973/wsjc240082


                基于 Canny 算子边缘分割的海洋平台焊接构件


                                                 焊缝检测方法




                                                           顾天宝
                                          (海洋石油工程股份有限公司,天津 300452)

                       摘  要:当前海洋平台焊接构件焊缝的检测过程中,依托于Sobel(索贝尔)算子完成图像边缘
                   分割,对噪声信息比较敏感,使得检测结果ACC值(准确率)较低。因此,提出基于Canny算子边
                   缘分割的海洋平台焊接构件焊缝检测方法。运用数学形态学中的膨胀和腐蚀思想,对海洋平台焊
                   接构件焊缝图像进行滤波处理。首先将预处理后的图像输入视觉注意模型,提取图像包含的综合
                   显著性特征,从而标注出图像视觉显著区域;然后基于Canny算子边缘分割算法,检测出图像中的
                   全部边缘像素,并通过膨胀和细化操作实现边缘连接,从图像中分割出整个目标区域;最后选定一
                   个种子区域,按照生长判定准则获取区域生长结果,从而得出焊缝检测结果。试验结果表明,新设
                   计方法的焊缝检测结果ACC值稳定在0. 95以上,能够满足海洋平台焊接构件的安全检测要求。
                       关键词:Canny算子;边缘分割;图像处理;海洋平台;区域生长;焊缝检测
                       中图分类号:TP21;TG115.28      文献标志码:A    文章编号:1000-6656(2024)10-0070-06

                     Welding seam detection method for ocean platform welding components based on
                                             Canny operator edge segmentation


                                                          GU Tianbao
                                      (Offshore Oil Engineering Co.,Ltd., Tianjin 300452, China)

                      Abstract: In the current welding seam detection process of offshore platforms, image edge segmentation is achieved
                   by relying on the Sobel operator, which is sensitive to noise information, resulting in lower ACC values (accuracy) of the
                   welding seam detection results. Therefore, a welding seam detection method for offshore platform welded components
                   based on Canny operator edge segmentation was proposed. Using the concepts of expansion and corrosion in mathematical
                   morphology, the welding seam images of offshore platform welding components were filtered. The preprocessed images
                   were input into the visual attention model, the comprehensive saliency features contained in the image were extracted,
                   and the visual salient regions of the image were annotated. Based on the Canny operator edge segmentation algorithm, all
                   edge pixels in the image were detected, and edge connections were achieved through dilation and refinement operations
                   to segment the entire target area from the image. A seed region was selected and the region growth results were obtained
                   according to the growth judgment criteria, in order to obtain the weld seam detection results. The experimental results
                   showed that the ACC value of the new design method for weld seam detection was set above 0.95, which well met the
                   safety inspection requirements of welded components on offshore platforms.
                      Key words: Canny operator; edge segmentation; image processing; ocean platform; regional growth; weld inspection

                                                                     海洋平台是海上油气资源开发的重要设施,需
                                                                要在恶劣的环境中长时间运行 。在海洋工程领域,
                                                                                            [1]
                 收稿日期:2024-03-01
                                                                平台焊接构件的质量对于整个海洋平台的稳定性,
                 作者简介:顾天宝(1983—),男,本科,工程师,主要研究方向为
                                                                                           [2]
              海洋平台陆地建造,海底管线结构和海底管道工艺技术与工程项目管理                   安全性和使用寿命至关重要 。同时,由于海洋平
                 通信作者:顾天宝,ajmbwvu@163.com                       台建设过程中的焊接工作量较大,故对海洋平台焊
                70
                     2024 年 第 46 卷 第 10 期
                     无损检测
   103   104   105   106   107   108   109   110   111   112   113