交变/旋转磁场下焊接缺陷磁光成像检测与分类

李彦峰; 高向东; 季玉坤; 王春草

doi:10.3788/OPE.20202805.1046

您当前的位置：

首页 >

文章列表页 >

交变/旋转磁场下焊接缺陷磁光成像检测与分类

现代应用光学 | 更新时间：2020-07-09

- 交变/旋转磁场下焊接缺陷磁光成像检测与分类
- Detection and classification of welding defects by magneto-optical imaging under alternating/rotating magnetic field
- 光学精密工程 2020年28卷第5期页码：1046-1054
- 作者机构：
  
  广东工业大学广东省焊接工程技术研究中心，广东广州 510006
- 作者简介：
  
  [ "李彦峰 (1987－)，男，河南孟州人，博士研究生，2010年于安阳工学院获得学士学位，2013年于新疆大学获得硕士学位，主要从事焊接缺陷无损探伤的研究. E-mail：18820958550@163.com" ]
  高向东 (1963－)，男，河南郑州人，教授，博士生导师，1998年于华南理工大学获得博士学位，主要从事焊接自动控制的研究。E-mail：gaoxd@gdut.edu.cnGAO Xiang-dong, E-mail:gaoxd@gdut.edu.cn
- 基金信息：
  
  国家自然科学基金资助项目(51675104);广东省教育厅创新团队项目(2017KCXTD010);广州市科技创新发展专项资金项目(202002020430100004)
- DOI：10.3788/OPE.20202805.1046
  中图分类号： TG115.28
- 收稿日期：2019-07-29，
  
  修回日期：2019-09-20，
  
  录用日期：2019-9-20，
  
  纸质出版日期：2020-05-15
- 稿件说明：
移动端阅览
李彦峰, 高向东, 季玉坤, 等. 交变/旋转磁场下焊接缺陷磁光成像检测与分类[J]. 光学精密工程, 2020,28(5):1046-1054.

Yan-feng LI, Xiang-dong GAO, Yu-kun JI, et al. Detection and classification of welding defects by magneto-optical imaging under alternating/rotating magnetic field[J]. Optics and precision engineering, 2020, 28(5): 1046-1054.
李彦峰, 高向东, 季玉坤, 等. 交变/旋转磁场下焊接缺陷磁光成像检测与分类[J]. 光学精密工程, 2020,28(5):1046-1054. DOI： 10.3788/OPE.20202805.1046.

Yan-feng LI, Xiang-dong GAO, Yu-kun JI, et al. Detection and classification of welding defects by magneto-optical imaging under alternating/rotating magnetic field[J]. Optics and precision engineering, 2020, 28(5): 1046-1054. DOI： 10.3788/OPE.20202805.1046.

摘要

针对任意角度焊接缺陷难以检测的问题，研究在不同磁场激励下焊接缺陷磁光成像无损检测系统。重点介绍了由U形磁轭产生的交变磁场和平面交叉磁轭产生的旋转磁场激励焊件的机理，比较了交变/旋转磁场激励下不同焊接缺陷的磁光成像效果。基于法拉第旋转效应分析磁光成像特性与磁场强度之间的关系，磁光图像的灰度值可以匹配相应的漏磁场强度。采用主成分分析法提取融合图像列像素灰度特征和通过灰度共生矩阵提取磁光图像纹理特征，建立BP神经网络模型和支持向量机模型识别这些缺陷特征。试验结果表明，在旋转磁场激励下，BP神经网络模型和支持向量机模型的分类精度分别为94.1%和98.6%，相比交变磁场，分类精度分别提高了10.7%和8.5%。旋转磁场激励下的磁光成像克服了定向检测的局限性，能够实现对任意角度焊接缺陷的检测及分类。

Abstract

Aiming at the difficult to detect arbitrary-angle weld defects

a Magneto-Optical (MO) imaging Non-Destructive Testing (NDT) system for weld defects excited by different magnetic fields was studied. The mechanism of the alternating magnetic field generated by the U-shaped yoke and the rotating magnetic field produced by the plane cross yoke was introduced. The MO imaging effects of different weld defects excited by alternating/rotating magnetic field were compared. The relationship between imaging characteristics of MO images and magnetic field strength was analyzed based on the Faraday rotation effect. The gray value of MO image can match the corresponding leakage magnetic field strength. The principal component analysis method was used to extract the grayscale features of the fused image column pixels and the texture features of the MO image were extracted by the gray-level co-occurrence matrix. A BP neural network model and a support vector machine model were established to identify these defect features. Experimental results show that the classification accuracy of the BP neural network model and the support vector machine model can reach 94.1% and 98.6% respectively under the excitation of rotating magnetic field. Compared with the alternating magnetic field

the classification accuracy is improved by 10.7% and 8.5%

respectively. MO imaging under rotating magnetic field excitation overcomes the limitation of directional detection of MO imaging under traditional magnetic field excitation

and realizes the detection and classification of arbitrary-angle weld defects.

关键词

Keywords

references

高向东 , 蓝重洲 , 陈子琴 , 等 . 焊接缺陷磁光成像动态检测与识别 . 光学精密工程 , 2017 . 25 ( 5 ): 1135 - 1141 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201705003 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201705003 .

X D GAO , CH ZH LAN , Z Q CHEN , 等 . Dynamic detection and recognition of welded defects based on magneto-optical imaging . Opt. Precision Eng. , 2017 . 25 ( 5 ): 1135 - 1141 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201705003 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201705003 .

滕国阳 , 周晓军 , 杨辰龙 , 等 . 厚截面碳纤维复合材料远表面微缺陷超声检测 . 光学精密工程 , 2018 . 26 ( 12 ): 3108 - 3117 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201812028 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201812028 .

G Y TENG , X J ZHOU , CH L YANG , 等 . Ultrasonic detection method of micro defects in thick-section CFRP . Opt. Precision Eng. , 2018 . 26 ( 12 ): 3108 - 3117 . http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201812028 http://d.old.wanfangdata.com.cn/Periodical/gxjmgc201812028 .

A MAHMOUDI , F REGRAGUI . Synthetic minority oversampling and linear cross-validated support vector machine-based recursive feature elimination to classify weld flaws in radiographic images . Materials Evaluation , 2015 . 73 ( 2 ): 186 - 197 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=6e81c0abf9b5dc8988bdcdd37750192d http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=6e81c0abf9b5dc8988bdcdd37750192d .

R MOHAMMAD , R A MOHAMMAD , F HAMED . Heat residual stress measurement of welded areas in steel pipes via magnetic particle testing . Materials Evaluation , 2012 . 70 624 - 630 .

O MARESCHAL , C CORDIER , C DOLABDJIAN , 等 . Aluminum alloy sensitization evaluation by using eddy current techniques based on IGMR-magnetometer head . IEEE Transactions on Magnetics , 2019 . 55 ( 1 ): 1 - 4 .

程玉华 , 周肇飞 , 尹伯彪 . 磁光/涡流实时成像检测系统的研究 . 光学精密工程 , 2006 . 14 ( 5 ): 797 - 801 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc200605014 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc200605014 .

Y H CHENG , ZH F ZHOU , B B YIN . Study on magneto-optical/eddy current imaging system for real-time testing . Opt. Precision Eng. , 2006 . 14 ( 5 ): 797 - 801 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc200605014 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=gxjmgc200605014 .

X D GAO , G H LI , Z Q CHEN , 等 . Modeling for detecting weld defects based on magneto-optical imaging . Applied Optics , 2018 . 57 ( 21 ): 6110 - 6119 . DOI: 10.1364/AO.57.006110 http://doi.org/10.1364/AO.57.006110 .

Y H CHENG , Y M DENG , L B BAI , 等 . Enhanced laser-based magneto-optic imaging system for nondestructive evaluation applications . IEEE Transactions on Instrumentation and Measurement , 2013 . 62 ( 5 ): 1192 - 1198 . DOI: 10.1109/TIM.2012.2220039 http://doi.org/10.1109/TIM.2012.2220039 .

U RADTKE , R ZIELKE , H G RADEMACHER , 等 . Application of magneto-optical method for real-time visualization of eddy currents with high spatial resolution for nondestructive testing . Optics and Lasers in Engineering , 2001 . 36 ( 3 ): 251 - 268 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=1fee745ef8f5629be582f647ffe1f6a4 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=1fee745ef8f5629be582f647ffe1f6a4 .

W LI , X N YUAN , G M CHEN , 等 . High sensitivity rotating alternating current field measurement for arbitrary-angle underwater cracks . Ndt & E International , 2016 . 79 123 - 131 . http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=09de9d68a09c66b31ad2f5cf292ee220 http://www.wanfangdata.com.cn/details/detail.do?_type=perio&id=09de9d68a09c66b31ad2f5cf292ee220 .

W LI , YY CHEN , W B SUN , 等 . A gingivitis identification method based on contrast-limited adaptive histogram equalization, gray-level co-occurrence matrix, and extreme learning machine . International Journal of Imaging Systems and Technology , 2019 . 29 ( 1 ): 77 - 82 . https://onlinelibrary.wiley.com/doi/abs/10.1002/ima.22298 https://onlinelibrary.wiley.com/doi/abs/10.1002/ima.22298 .

G ZHENG , X F LI , L Z ZHOU , 等 . Development of a gray-level Co-occurrence matrix-based texture orientation estimation method and its application in sea surface wind direction retrieval from SAR imagery . IEEE Transactions on Geoscience and Remote Sensing , 2018 . 56 ( 9 ): 5244 - 5260 . DOI: 10.1109/TGRS.2018.2812778 http://doi.org/10.1109/TGRS.2018.2812778 .

浏览量

722

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

焊接缺陷磁光成像三维轮廓重构识别

损毁字符的磁光成像复原识别

磁光成像漏磁特征在焊接缺陷轮廓重构中的应用

面向高光谱影像分类的多特征流形鉴别嵌入

融合纹理特征与深度信息的足迹自动比对算法