焊接缺陷的磁光成像小波多尺度识别及分类

高向东; 李国华; 萧振林; 陈晓辉

doi:10.3788/OPE.20162404.0930

您当前的位置：

首页 >

文章列表页 >

焊接缺陷的磁光成像小波多尺度识别及分类

信息科学 | 更新时间：2020-08-13

- 焊接缺陷的磁光成像小波多尺度识别及分类
- Detection and classification of welded defects by magneto-optical imaging based on multi-scale wavelet
- 光学精密工程 2016年24卷第4期页码：930-936
- 作者机构：
  
  1. 广东工业大学机电工程学院广东省计算机集成制造重点实验室,广东广州,510006
  2. 广州番禺高勋染整设备制造有限公司,广东广州,511400
- 作者简介：
- 基金信息：
  
  国家自然科学基金资助项目(No.51175095)();广东省协同创新与平台环境建设专项基金资助项目(No.2015B090901013)();广东省重大科技专项资助项
- DOI：10.3788/OPE.20162404.0930
  中图分类号： TP391.4;TG115.28
- 收稿日期：2016-01-16，
  
  修回日期：2016-03-03，
  
  纸质出版日期：2016-04-25
- 稿件说明：
移动端阅览
高向东, 李国华, 萧振林等. 焊接缺陷的磁光成像小波多尺度识别及分类[J]. 光学精密工程, 2016,24(4): 930-936

GAO Xiang-dong, LI Guo-hua, XIAO Zhen-lin etc. Detection and classification of welded defects by magneto-optical imaging based on multi-scale wavelet[J]. Editorial Office of Optics and Precision Engineering, 2016,24(4): 930-936
高向东, 李国华, 萧振林等. 焊接缺陷的磁光成像小波多尺度识别及分类[J]. 光学精密工程, 2016,24(4): 930-936 DOI： 10.3788/OPE.20162404.0930.

GAO Xiang-dong, LI Guo-hua, XIAO Zhen-lin etc. Detection and classification of welded defects by magneto-optical imaging based on multi-scale wavelet[J]. Editorial Office of Optics and Precision Engineering, 2016,24(4): 930-936 DOI： 10.3788/OPE.20162404.0930.

摘要

针对焊缝微小凹陷、未熔合和焊偏等焊接缺陷

提出了基于磁光成像无损探伤的小波多尺度边缘提取算法及主成分分析-误差反向传播神经网络(PCA-BP)缺陷分类模型;研究了焊件表面及近表面缺陷的可视化无损检测及分类方法。首先

通过对焊件施加感应磁场

利用法拉第磁致旋光原理构成磁光传感器

获取焊接缺陷磁光图像。然后

针对焊接缺陷磁光图像存在噪声干扰、对比度低且成像背景复杂等特征

基于小波模极大值的多尺度边缘信息融合方法

设计了具有高抗噪性的缺陷边缘检测算法。最后

通过PCA法对磁光图像列方向灰度变量进行预处理

得到能表征95%磁光图像列方向灰度变量信息的256个特征点作为输入特征量

构建了三层BP神经网络模型

对焊接缺陷样本进行分类。试验结果表明

所提方法能准确识别微小凹陷、未熔合和焊偏等焊接缺陷

模型分类准确率可达90.80%。

Abstract

A multi-scale wavelet edge extraction algorithm and Principal Component Analysis-Back Propagation(PCA-BP) neural network classification model were proposed based on magneto-optical imaging to detect the welded defects such as sags

insufficient fusion on subsurface and welding misalignment. The visualization of detection and the classification of welded defects on the surface and subsurface of weldments were explored. Firstly

the weldments were magnetized by using an excitation magnetic field. Meanwhile

a magneto optical (MO) sensor based on the principle of Faraday magneto effect was used to acquire the MO images of weldments with welded defects. Then

a defect edge extraction algorithm with a better anti-noise property was investigated based on wavelet modulus maxima multi-scale information fusion theory to process MO images suffered from serious noises

low contrast and complex background. Finally

the PCA was taken to preprocess the column grey variables of MO images and 256 feature points of column variable of MO images which could characterize grey variable by 95% were obtained. Furthermore

these feature points were regarded as inputs of a three-layer BP neural network model to classify the welded defects. Experiment results show that the proposed method can be applied to detection of welded defects as mentioned above

and the accuracy of PCA-BP classification model has reached to 90.80%.

关键词

Keywords

references

PRAVEEN A, VIJAYAREKHA K, ABRAHAM S T, et al.. Signal quality enhancement using higher order wavelets for ultrasonic TOFD signals from austenitic stainless steel welds[J]. Ultrasonics, 2013, 53(7):1288-1292.

周贤, 刘义伦. 炭素制品缺陷的X射线自动检测技术研究[J]. 光学精密工程, 2006, 14(3):503-508. ZHOU X, LIU Y L. X-ray automatic inspection techniques for carbon product defects[J]. Opt. Precision Eng., 2006, 14(3):503-508. (in Chinese)

HELIFA B, OULHADJ A, BENBELGHIT A, et al.. Detection and measurement of surface crack in ferromagnetic materials using eddy current testing[J]. NDT &E Int, 2006, 39:384-390.

LE M, LEE J, SHOJI T. A simulation of magneto-optical eddy current imaging[J]. NDT&E International, 2011, 44(8):783-788.

DENG Y M, LIU X, UDPA L. Magneto-optic imaging for aircraft skins inspection:A probability of detection study of simulated and experimental image data[J]. IEEE Transactions on Reliability, 2012, 61(4):901-908.

GAO X D, LIU Y H, YOU D Y. Detection of micro-weld joint by magneto-optical imaging[J]. Opt Laser Technol, 2014, 62:141-151.

高向东, 吴嘉杰. 微间隙焊缝磁光成像检测及跟踪方法[J]. 机械工程学报, 2015, 51(4):71-77. GAO X D, WU J J. Approach of detecting and tracking micro weld joint based on magneto optical imaging[J]. Chin J Mech Eng-En, 2015, 51(4):71-77. (in Chinese)

林丽君, 殷鹰, 何明格, 等. 基于小波模极大值的磁瓦裂纹缺陷边缘检测算法[J]. 电子科技大学学报, 2015, 44(2):283-288. LIN L J, YIN Y, HE M G, et al.. Edge detection algorithm of magnetic tile crack based on wavelet modulus maxima[J]. Journal of University of Electronic Science and Technology of China, 2015, 44(2):283-288. (in Chinese)

李红. 数值分析[M]. 武汉:华中科技大学出版社, 2003. LI H. Numerical Anylysis[M]. Wuhan:Huazhong University of Science and Technology Press, 2003. (in Chinese)

李海森, 张艳宁, 姚睿, 等. 基于主成分分析的直线运动模糊参数估计[J]. 光电精密工程, 2013, 21(10):2656-2663. LI H S, ZHANG Y N, YAO R, et al.. Parameter estimation of linear motion blur based on principal component analysis[J]. Opt. Precision Eng., 2013, 21(10):2656-2663. (in Chinese)

王灿进, 孙涛, 石宁宁, 等. 基于双隐含层BP算法的激光主动成像识别系统[J]. 光学精密工程, 2014, 22(6):1639-1647. WANG C J, SUN T, SHI N N, et al.. Laser active imaging and recognition system based on double hidden layer BP algorithm[J]. Opt. Precision Eng., 2014, 22(6):1639-1647. (in Chinese)

浏览量

326

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

似然关系模型在航天软件缺陷预测中的应用