基于神经网络和涡流检测的自然裂纹形状重构
Natural Crack Profile Reconstruction Using Eddy Current Technique and Neural Network
摘 要
基于涡流检测的裂纹形状重构在压力容器和热交换管道等关键设备结构的无损评价中越来越重要。从裂纹产生机理出发，对裂纹进行了分类并分析了自然裂纹与人工裂纹的区别。采用神经网络方法对自然裂纹形状进行了重构。重构结果表明该方法具有快速、精确的优点。同时讨论了该方法的不足并提出了解决思路。
涡流检测
自然裂纹
形状重构
Artificial neural network
Eddy current testing
Natural crack
Profile reconstruction
Abstract
The reconstruction of crack profiles is getting more and more important in the NDE of structures such as pressure vessel, tubes in heat exchanges. Based on the different generation mechanisms, the cracks were classified and the differences between artificial and natural cracks were analyzed. The crack profiles were reconstructed based on artificial neural network and the reconstructed results validated the method being having many advantages, such as high speed and precision. The drawback of this method was also discussed and the measures to overcome it were proposed.
中图分类号 TG115.28
所属栏目 科研成果与学术交流
基金项目 广东省重点攻关资助项目(2006B12401001)
收稿日期 2007/4/16
修改稿日期
网络出版日期
作者单位点击查看
备注张思全(1971-)，男，讲师，博士研究生，从事电磁无损检测技术研究工作。
引用该论文: ZHANG Si-Quan,CHEN Tie-Qun,LIU Gui-Xiong,YANG He-Fa. Natural Crack Profile Reconstruction Using Eddy Current Technique and Neural Network[J]. Nondestructive Testing, 2008, 30(5): 280～284
张思全,陈铁群,刘桂雄,杨何发. 基于神经网络和涡流检测的自然裂纹形状重构[J]. 无损检测, 2008, 30(5): 280～284
共有人对该论文发表了看法，其中：
人认为该论文很差
人认为该论文较差
人认为该论文一般
人认为该论文较好
人认为该论文很好
参考文献
【1】Auld B A, Moulder J C. Review of advances in quantitative eddy current nondestructive evaluation[J]. Journal of Nondestructive Evaluation,1999,18(1):3-36.
【2】Chen Z, Aoto K, Miya K. Reconstruction of cracks with physical closure from signals of eddy current testing[J]. IEEE Transactions on Magnetics,2000,36(4):1018-1022.
【3】黄卡玛，赵 翔.电磁场中的逆问题及应用[M].北京:科学出版社,2005.
【4】柯常波，陈铁群，张欣宇.基于BP神经网络的超声无损测定表面开口裂纹高度[J].兵器材料科学与工程,2007,30(1):17-21.
【5】肖春生，王树宗，朱华兵.基于人工神经网络的电涡流逆问题解[J].无损检测,2005,27(4):172-175.
【6】Tian G Y, Sophian A, Taylor D, et al. Wavelet-based PCA defect classification and quantification for pulsed eddy current NDT[J]. IEE Proc Sci Meas Technol,2005,152(4):141-148.
【7】Stephane Mallat. A Wavelet Tour of Signal Processing[M]. USA: Academic Press,1999.
【8】Noritaka Yusa, Weiying Cheng, Zhenmao Chen, et al. Generalized neural network approach to eddy current inversion for real cracks[J]. NDT&E International,2002,35(8):609-614.
【2】Chen Z, Aoto K, Miya K. Reconstruction of cracks with physical closure from signals of eddy current testing[J]. IEEE Transactions on Magnetics,2000,36(4):1018-1022.
【3】黄卡玛，赵 翔.电磁场中的逆问题及应用[M].北京:科学出版社,2005.
【4】柯常波，陈铁群，张欣宇.基于BP神经网络的超声无损测定表面开口裂纹高度[J].兵器材料科学与工程,2007,30(1):17-21.
【5】肖春生，王树宗，朱华兵.基于人工神经网络的电涡流逆问题解[J].无损检测,2005,27(4):172-175.
【6】Tian G Y, Sophian A, Taylor D, et al. Wavelet-based PCA defect classification and quantification for pulsed eddy current NDT[J]. IEE Proc Sci Meas Technol,2005,152(4):141-148.
【7】Stephane Mallat. A Wavelet Tour of Signal Processing[M]. USA: Academic Press,1999.
【8】Noritaka Yusa, Weiying Cheng, Zhenmao Chen, et al. Generalized neural network approach to eddy current inversion for real cracks[J]. NDT&E International,2002,35(8):609-614.
相关信息
