窄搭接焊缝涡流信号的特征提取与缺陷识别
|
摘要
提出了一种有效识别窄搭接焊缝缺陷的涡流检测方法。首先用经验模态分解提取焊缝涡流信号的特征参数;然后基于主成分分析对特征参数进行降维,去掉其中的冗余信息,得到焊缝的主元特征;最后将主元特征作为支持向量机的输入构建多分类器,对窄搭接焊缝的涡流实测信号进行缺陷识别。结果表明该方法准确度高、复杂度低,能有效识别焊缝的不同缺陷,具有良好的工程应用价值。
An effective eddy current testing method was presented to identify the defects of narrow lap joints.Firstly,the characteristic parameters of eddy current signals were extracted by EMD.Then,based on PCA,the characteristic parameters were reduced,the redundant informations were removed,and the main element characteristics of the welds were obtained.In the end,the main element features were used as the inputs of SVM to construct the multi-classifier,and the eddy current measurement signals of the narrow lap were identified.The results show that this method has high accuracy and low complexity.It may effectively identify different defects of weld seams,and has good engineering application values.
An effective eddy current testing method was presented to identify the defects of narrow lap joints.Firstly,the characteristic parameters of eddy current signals were extracted by EMD.Then,based on PCA,the characteristic parameters were reduced,the redundant informations were removed,and the main element characteristics of the welds were obtained.In the end,the main element features were used as the inputs of SVM to construct the multi-classifier,and the eddy current measurement signals of the narrow lap were identified.The results show that this method has high accuracy and low complexity.It may effectively identify different defects of weld seams,and has good engineering application values.
引文
[1]张彩云.电阻焊接技术及其应用设备[J].电子工艺技术,2003,24(5):201-203.ZHANG Caiyun.Resistance Welding Technology and Application Equipment[J].Electronics Process Technology,2003,24(5):201-203.
[2]张会云,严仍春,楼敏珠.阻抗平面显示技术在涡流检测信号处理中的应用[J].无损检测,2003,25(1):44-47.ZHANG Huiyun,YAN Rengchun,LOU Minzhu.Application of Impedance Diagram Display Technology to Signal Processing in Eddy Current Testing[J].Nondestructive Testing,2003,25(1):44-47.
[3]刘兴乐,刘志平,黎玄,等.基于脉冲涡流热成像的金属结构焊缝表面裂纹识别方法[J].中国机械工程,2016,27(14):1925-1931.LIU Xingle,LIU Zhiping,LI Xuan,et al.Method for Surface Crack Detection of Welded Structure in Pulsed Eddy Current Thermography[J].China Mechanical Engineering,2016,27(14):1925-1931.
[4]HE Y Z,PAN M C,LUO F L,et a1.Pulsed Eddy Current Imaging and Frequency Spectrum Analysis for Hidden Defect Nondestructive Testing and Evaluation[J].NDT&E International,2011,44(4):344-352.
[5]周德强,田贵云,尤丽华,等.基于频谱分析的脉冲涡流缺陷检测研究[J].仪器仪表学报,2011,32(9):1948-1953.ZHOU Deqiang,TIAN Guiyun,YOU Lihua,et al.Study on Pulsed Eddy Current Defect Signal Detection Technology Based on Spectrum Analysis[J].Chinese Journal of Scientific Instrument,2011,32(9):1948-1953.
[6]GAO B,BAI L,WOO W L,et al.Automatic Defect Identification of Eddy Current Pulsed Thermography Using Single Channel Blind Source Separation[J].IEEE Transactions on Instrumentation&Measurement,2014,63(4):913-922.
[7]程力勇,米高阳,黎硕,等.基于主成分分析-支持向量机模型的激光钎焊接头质量诊断[J].中国激光,2017(3):76-83.CHENG Liyong,MI Gaoyang,LI Shuo,et al.Quality Diagnosis of Joints in Laser Brazing Based on Principle Component Analysis-support Vector Machine Model[J].Chinese Journal of Lasers,2017(3):76-83.
[8]HUANG N E,SHEN Z,LONG S R,et al.The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis[J].Proceedings of the Royal Society of London,Series A:Mathematical,Physical and Engineering Sciences,1998,454(1971):903-995.
[9]周德强,李勇,张秋菊,等.脉冲涡流金属厚度检测信号及其特征提取[J].中国机械工程,2012,23(15):11-13.ZHOU Deqiang,LI Yong,ZHANG Qiuju,et al.Feature Extraction of Pulsed Eddy Current Signals on Metal Thickness Measurement[J].China Mechanical Engineering,2012,23(15):11-13.
[10]何正嘉,陈进,王太勇,等.机械故障诊断理论及应用[M].北京:高等教育出版社,2010:31-67.HE Zhengjia,CHEN Jin,WANG Taiyong,et al.Theory and Application of Mechanical Fault Diagnosis[M].Beijing:Higher Education Press,2010:31-67.
[11]JOLLIFFE I T.Principal Component Analysis[M].New York:Springer,1986:29-59,363-365.
[2]张会云,严仍春,楼敏珠.阻抗平面显示技术在涡流检测信号处理中的应用[J].无损检测,2003,25(1):44-47.ZHANG Huiyun,YAN Rengchun,LOU Minzhu.Application of Impedance Diagram Display Technology to Signal Processing in Eddy Current Testing[J].Nondestructive Testing,2003,25(1):44-47.
[3]刘兴乐,刘志平,黎玄,等.基于脉冲涡流热成像的金属结构焊缝表面裂纹识别方法[J].中国机械工程,2016,27(14):1925-1931.LIU Xingle,LIU Zhiping,LI Xuan,et al.Method for Surface Crack Detection of Welded Structure in Pulsed Eddy Current Thermography[J].China Mechanical Engineering,2016,27(14):1925-1931.
[4]HE Y Z,PAN M C,LUO F L,et a1.Pulsed Eddy Current Imaging and Frequency Spectrum Analysis for Hidden Defect Nondestructive Testing and Evaluation[J].NDT&E International,2011,44(4):344-352.
[5]周德强,田贵云,尤丽华,等.基于频谱分析的脉冲涡流缺陷检测研究[J].仪器仪表学报,2011,32(9):1948-1953.ZHOU Deqiang,TIAN Guiyun,YOU Lihua,et al.Study on Pulsed Eddy Current Defect Signal Detection Technology Based on Spectrum Analysis[J].Chinese Journal of Scientific Instrument,2011,32(9):1948-1953.
[6]GAO B,BAI L,WOO W L,et al.Automatic Defect Identification of Eddy Current Pulsed Thermography Using Single Channel Blind Source Separation[J].IEEE Transactions on Instrumentation&Measurement,2014,63(4):913-922.
[7]程力勇,米高阳,黎硕,等.基于主成分分析-支持向量机模型的激光钎焊接头质量诊断[J].中国激光,2017(3):76-83.CHENG Liyong,MI Gaoyang,LI Shuo,et al.Quality Diagnosis of Joints in Laser Brazing Based on Principle Component Analysis-support Vector Machine Model[J].Chinese Journal of Lasers,2017(3):76-83.
[8]HUANG N E,SHEN Z,LONG S R,et al.The Empirical Mode Decomposition and the Hilbert Spectrum for Nonlinear and Non-stationary Time Series Analysis[J].Proceedings of the Royal Society of London,Series A:Mathematical,Physical and Engineering Sciences,1998,454(1971):903-995.
[9]周德强,李勇,张秋菊,等.脉冲涡流金属厚度检测信号及其特征提取[J].中国机械工程,2012,23(15):11-13.ZHOU Deqiang,LI Yong,ZHANG Qiuju,et al.Feature Extraction of Pulsed Eddy Current Signals on Metal Thickness Measurement[J].China Mechanical Engineering,2012,23(15):11-13.
[10]何正嘉,陈进,王太勇,等.机械故障诊断理论及应用[M].北京:高等教育出版社,2010:31-67.HE Zhengjia,CHEN Jin,WANG Taiyong,et al.Theory and Application of Mechanical Fault Diagnosis[M].Beijing:Higher Education Press,2010:31-67.
[11]JOLLIFFE I T.Principal Component Analysis[M].New York:Springer,1986:29-59,363-365.