摘要
为解决移动式X射线管道检测系统中管道中心偏移引起的壁厚测量偏差问题,提出了一种管道壁厚测量方法。首先,在移动式X射线检测系统中获取投影图像;然后,使用U-Net神经网络处理投影图像以抑制噪声和伪影引起的干扰,从而准确提取管道内外径边缘等关键点的位置信息;最后,根据提出的基于偏心校正的管道壁厚计算方法得到管壁厚度。仿真和实验结果表明,该管道壁厚测量方法得到的壁厚相对误差小于5%,可以实现准确的管道壁厚检测。
In order to solve the wall thickness measurement deviation caused by the center deviation of pipe in mobile X-Ray detection system,a wall thickness measurement method of pipe was proposed.First,the projection image was obtained in the mo⁃bile X-Ray detection system.Then,the U-Net neural network was used to suppress the interference caused by noise or artifacts on the projected image,so as to realize the accurate extraction of the position information of the key points such as the inner and outer diameter edge of the pipe.Finally,according to the proposed calculation method of pipe wall thickness based on eccentricity correction,the pipe wall thickness was obtained.The simulation and experimental results show that the relative error of the pipe wall thickness calculation method proposed in this paper is less than 5%,which can realize the accurate wall thickness measure⁃ment of the pipe.
作者
汤雅惠
夏小琴
赵金涛
韩振烨
邹晶
TANG Ya-hui;XIA Xiao-qin;ZHAO Jin-tao;HAN Zhen-ye;ZOU Jing(School of Precision Instrument and Opto-Electronics Engineering,Tianjin University,Tianjin 300072,China)
出处
《管道技术与设备》
CAS
2022年第2期35-41,共7页
Pipeline Technique and Equipment
基金
国家自然科学基金资助项目(61771328)
国家重点研发计划资助项目(2017YFB1103900)。
关键词
移动式管道检测
壁厚测量
位姿偏移
边缘提取
偏心校正
壁厚计算
mobile pipeline detection
wall thickness measurement
pose offset
edge extraction
eccentricity correction