基于机器视觉的钢管壁厚在线检测方法研究

doi:10.3778/j.issn.1002-8331.2101-0127

摘要/Abstract

摘要： 在钢管生产过程中，需要对钢管的壁厚进行实时测量，以检验所生产的钢管是否符合规格。针对人工测量钢管壁厚中所出现的测量效率低、易产生疲劳且无法实时测量等问题，基于机器视觉测量技术，提出一种钢管壁厚在线检测方法。该方法首先采集钢管断面图像，然后对采集到的钢管图像进行预处理，使用Canny边缘检测算子检测钢管断面内外圈边缘特征，最后使用改进后的随机霍夫圆检测算法检测断面轮廓，根据设计的钢管壁厚测量方案计算得到各处钢管壁厚。改进的随机霍夫圆检测由于采用分区采样以及筛选出与边缘轮廓契合度最高的候选圆的方式，提高了原检测算法的检测精度与效率。经过实验验证，该方法测量精度高，效率高，能够满足对钢管壁厚在线检测的要求。

关键词: 机器视觉, 图像预处理, 改进随机霍夫变换, 圆检测算法, 钢管壁厚测量

Abstract: In the process of steel pipe production, the wall thickness of steel pipe needs to be measured in real time to check whether the produced steel pipe meets the steel pipe specifications. Aiming at the problems of low measurement efficiency, easy to fatigue and inability to achieve real-time measurement in manual measurement of wall thickness of steel pipe. Based on machine vision measurement technology, an online detection method of wall thickness of steel pipe is proposed. Firstly, collect the image of steel pipe section, then performs pretreatment operations on the collected steel pipe image. The Canny edge detection is used to detect the edge features of the inner and outer circle of the steel pipe. Finally, the improved random Hough transform circle detection algorithm is used to detect the profile of the section. According to the designed measurement scheme of wall thickness of steel pipe, the wall thickness of steel pipe is got everywhere. The improved random Hough circle detection improves the detection accuracy and efficiency of the original detection algorithm, due to the use of partition sampling and screening of candidate circles with the highest degree of conformity with the edge contour. Experiments show that this method has high measurement accuracy and high efficiency, and can meet the requirements for online detection of wall thickness of steel pipe.

Key words: machine vision, image pretreatment, improved random Hough transform, circle detection algorithm, measurement on wall thickness of steel pipe

涂德浴, 刘坤, 朱庆, 刘庆运. 基于机器视觉的钢管壁厚在线检测方法研究[J]. 计算机工程与应用, 2022, 58(16): 249-256.

TU Deyu, LIU Kun, ZHU Qing, LIU Qingyun. Research on Online Detection for Wall Thickness of Steel Pipe Based on Machine Vision[J]. Computer Engineering and Applications, 2022, 58(16): 249-256.

参考文献

[1] CHURSIN Y A，REDKO L A，FEDOROV E M，et al.Enlargement of measuring zone in laser gauges without sacrificing measurement accuracy[J].Measurement，2019，131：647-653.
[2] 伍晶晶，张士晶，陈华，等.基于CR技术的钢管壁厚测量工艺研究[J].失效分析与预防，2019，14（5）：300-306.
WU J J，ZHANG S J，CHEN H，et al.Measurement technology of steel pipe wall thickness based on computer radiograph[J].Failure Analysis and Prevention，2019，14（5）：300-306.
[3] 廉盟.大型薄壁件壁厚超声自动测量方法与关键技术[D].大连：大连理工大学，2019.
LIAN M.Methods and key technologies of automatic ultrasonic thickness measurement of large thin-wall parts[D].Dalian：Dalian University of Technology，2019.
[4] 杨文桥，郑力新.浅谈机器视觉[J].现代计算机，2020（30）：66-69.
YANG W Q，ZHENG L X.Talking about machine vision[J].Modern Computer，2020（30）：66-69.
[5] 陈英.机器视觉技术的发展现状与应用动态研究[J].无线互联科技，2018，15（19）：147-148.
CHEN Y.Study on development status and application trends of machine vision technology[J].Wireless Internet Technology，2018，15（19）：147-148.
[6] 高玮军，师阳，杨杰，等.一种改进的轻量人头检测方法[J].计算机工程与应用，2021，57（1）：207-212.
GAO W J，SHI Y，YANG J，et al.An improved lightweight head detection method[J].Computer Engineering and Applications，2021，57（1）：207-212.
[7] HUANG Z，FU H L，FAN X D，et al.Surface damage detection equipment for subway tunnels based on machine vision system[J].Journal of Infrastructure Systems，2020，27（1）：04020047.
[8] BATCHELOR B G.Automatic visual inspection in industry[J].Industrial Robot，1978，5（4）：174-176.
[9] 何文斌，魏爱云，明五一，等.基于机器视觉的水果品质检测综述[J].计算机工程与应用，2020，56（11）：10-16.
HE W B，WEI A Y，MING W Y，et al.Survey of fruit quality detection based on machine vision[J].Computer Engineering and Applications，2020，56（11）：10-16.
[10] 王艳.机器视觉测量技术研究与应用[D].武汉：华中师范大学，2018.
WANG Y.Research and application of machine vision measurement technology[D].Wuhan：Central China Normal University，2018.
[11] 宣德坤.基于机器视觉的轴承与同步带轮尺寸检测技术研究[D].郑州：河南工业大学，2020.
XUAN D K.Research on bearing and synchronous wheel dimension detection technology based on machine vision[D].Zhengzhou：Henan University of Technology，2020.
[12] 宋薇，陈兴，沈林勇.基于视觉的环形密封件在线检测[J].仪表技术与传感器，2020（5）：62-67.
SONG W，CHEN X，SHEN L Y.Vision-based ring seal online detection[J].Instrument Technique and Sensor，2020（5）：62-67.
[13] 张恒，何文雪.基于机器视觉的坚果尺寸检测系统设计[J].工业仪表与自动化装置，2020（6）：52-55.
ZHANG H，HE W X.Design of nut size detection system based on machine vision[J].Industrial Instrumentation and Automation，2020（6）：52-55.
[14] 郝孟娟，董桂西，高立鹏，等.铁塔构件制孔尺寸机器视觉在线检测系统的设计[J].组合机床与自动化加工技术，2020（2）：123-127.
HAO M J，DONG G X，GAO L P，et al.Design of machine vision online detection system for hole-making dimension of the steel tower components[J].Modular Machine Tool and Automatic Manufacturing Technique，2020（2）：123-127.
[15] 刘华超，张俊然，刘云飞.引入特征损失对CycleGAN的影响研究[J].计算机工程与应用，2020，56（22）：217-223.
LIU H C，ZHANG J R，LIU Y F.Influence of identity loss on CycleGAN[J].Computer Engineering and Applications，2020，56（22）：217-223.
[16] 赵博文，张力夫，潘在峰，等.基于OpenCV的图像滤波方法比较[J].信息与电脑（理论版），2020，32（15）：78-80.
ZHAO B W，ZHANG L F，PAN Z F，et al.Comparison of OpenCV-based image filtering methods[J].Information and Computer（Theoretical Edition），2020，32（15）：78-80.
[17] CHILLARóN M，VIDAL V，VERDú G.Evaluation of image filters for their integration with LSQR computerized tomography reconstruction method[J].PLoS One，2020，15（3）：e0229113.
[18] 张宸枫.基于小波自适应阈值结合双边滤波的图像降噪[D].哈尔滨：哈尔滨理工大学，2019.
ZHANG C F.Image noise reduction based on wavelet adaptive threshold combined with bilateral filtering[D].Harbin：Harbin University of Science and Technology，2019.
[19] 刘硕.阈值分割技术发展现状综述[J].科技创新与应用，2020（24）：129-130.
LIU S.Summarize the development of threshold segmentation technology[J].Technology Innovation and Application，2020（24）：129-130.
[20] OTSU N.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems，Man and Cybernetics，1978，9（1）：62-66.
[21] 张金波.灰度图像的边缘检测算法研究[D].南京：东南大学，2019.
ZHANG J B.Research on edge detection algorithm of gray image[D].Nanjing：Southeast University，2019.
[22] CANNY J.A computational approach to edge detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，1986，8（6）：679-698.
[23] FARIS A P，WAHIDIN W.Comparison between image processing methods for detecting object like circle[P].Digital Medicine and Image Processing，2018.
[24] 沈夏炯，段晓宇，原万里，等.基于连通区域标记算法的圆检测算法的研究[J].计算机工程与应用，2018，54（21）：95-98.
SHEN X J，DUAN X Y，YUAN W L，et al.Research on circle detection algorithm based on connected region labeling algorithm[J].Computer Engineering and Applications，2018，54（21）：95-98.
[25] XU L，OJA E.Randomized Hough transform（RHT）：basic mechanisms algorithms，and computational complexities[J].CVGIP：Image Understanding，1993，57（2）：131-154.