首页|基于三维检测的钢管外表面缺陷检测与识别方法

基于三维检测的钢管外表面缺陷检测与识别方法

扫码查看
无缝钢管表面介质的干扰以及人工检查漏检率高,造成钢管表面缺陷检测准确率不能满足在线检测的要求.二维相机检测的成像景深不够、成像灰度不均导致缺陷识别率低、缺陷误检、漏检等问题.因此提出3D点云的钢管外表面检测系统,解决成像景深小、缺陷识别率低和钢管表面存在干扰缺陷的问题.将深度学习算法和3D尺寸测量技术应用到无缝钢管的缺陷检测上,使用该套缺陷检测系统实现对缺陷尺寸的量化,更准确地检测出缺陷.本系统现场缺陷识别率可达90%以上,且检测速度快.此外,本系统具备周期缺陷报警、钢管表面缺陷统计报表打印、缺陷分级等多种功能,使表面缺陷检测系统多功能化及智能化,对减少人工劳动强度及提高无缝钢管质量具有积极意义.
Detecting and identifying method for defects on outer surface of steel pipes based on 3D detection
The interference of the surface medium of seamless steel pipes and the high leakage rate of manual inspection result in the accuracy of surface defect detection of steel pipes not meeting the re-quirements of online detection.The insufficient depth of field and uneven grayscale of imaging detec-ted by two-dimensional cameras result in low defect recognition rate,false detection of defects,and missed detection.Therefore,a 3D point cloud based steel pipe outer surface detection system was pro-posed to solve the problems of small imaging depth,low defect recognition rate,and interference de-fects on the steel pipe surface.Deep learning algorithms and 3D size measurement technology are ap-plied to defect detection of seamless steel pipes.This defect detection system is used to quantify the size of defects and detect them more accurately.The on-site defect recognition rate of this system can reach over 90%,and the detection speed is fast.In addition,this system has multiple functions such as periodic defect alarm,steel pipe surface defect statistical report printing,defect grading,etc.,mak-ing the surface defect detection system multifunctional and intelligent,which has positive significance in reducing manual labor intensity and improving the quality of seamless steel pipes.

seamless steel pipeouter surface defect detection3D defect size detectioncontour de-tectiondeep learning

刘国栋、苏成、王晓晨、吴昆鹏、王少聪、周锦波

展开 >

承德建龙特殊钢有限公司,河北承德 067201

北京科技大学设计研究院有限公司,北京 100083

北京科技大学高效轧制与智能制造国家工程研究中心,北京 100083

北京科技大学国家板带生产先进装备工程技术研究中心,北京 100083

展开 >

无缝钢管 外表面缺陷检测 3D缺陷尺寸检测 轮廓检测 深度学习

国家自然科学基金面上项目

51975043

2024

冶金自动化
冶金自动化研究设计院

冶金自动化

影响因子:0.685
ISSN:1000-7059
年,卷(期):2024.48(1)
  • 15