基于神经网络方法的应力腐蚀裂纹定量重构
Quantitative Reconstruction of Stress Corrosion Crack by Using Neural Network
摘 要
应力腐蚀裂纹（SCC）主要沿着晶界进展，具有类似于树枝分叉的复杂微观结构，其无损定量检测难度较大。基于应力腐蚀裂纹的简化模型和神经网络，提出了一种SCC定量重构方案。主要思路包括将SCC等效为导电率不为零的半椭圆裂纹，采用涡流饼式探头检测信号作为重构源信号，利用FEM-BEM混合法程序计算教师信号，针对所选神经网络提出相应的裂纹参数化方法。最后利用提出的重构方法对模拟SCC进行了定量重构试验。结果表明，所提出的基于主成分分析和神经网络的方法可用于应力腐蚀裂纹的定量重构。
神经网络
建模
重构
Stress corrosion crack
Neural networks
Modeling
Reconstruction
Abstract
As stress corrosion crack(SCC) mainly propagates along grain boundary, it has a very complicated microstructure similar to the branches of a tree, which makes its nondestructive quantitative evaluation more difficult. A method for modeling SCC and a sizing scheme based on neural networks were introduced and evaluated. Impedance signals from a pancake probe scanned just over the crack were taken as the source signal for crack reconstruction. A lot of sample datasets were calculated by using a finite element method and boundary element method(FEM-BEM) hybrid code for network training. A parameterization method of crack for the output of neural network was introduced. The numerical results demonstrated that the neural networks approach is a suitable way for reconstruction of SCC.
中图分类号 TG115.28
所属栏目 2008远东无损检测新技术论坛优秀论文选登
基金项目
收稿日期 2008/6/25
修改稿日期
网络出版日期
作者单位点击查看
备注耿强(1983-)，男，硕士研究生，主要从事无损检测和信号处理。
引用该论文: GENG Qiang,WANG Li,CHEN Zhen-Mao. Quantitative Reconstruction of Stress Corrosion Crack by Using Neural Network[J]. Nondestructive Testing, 2008, 30(8): 543～546
耿强,王丽,陈振茂. 基于神经网络方法的应力腐蚀裂纹定量重构[J]. 无损检测, 2008, 30(8): 543～546
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】乔利杰,王燕斌,褚武扬.应力腐蚀裂纹机理.北京：科学出版社,1993.
【2】Zhenmao Chen, Kenzo Miya, Masaaki Kurokawa. Rapid prediction of eddy current testing signals using A-phi method and database. NDT&E International,1999,32(1):29-36(8).
【3】Radu C. Popa, Kenzo Miya. Approximate Inverse Mapping in ECT, Based on Aperture Shifting and Neural Network Regression. Journal of Nondestructive Evaluation,1998,17(4):209-221.
【4】盛剑霓.工程电磁声数值分析\[M\].西安：西安交通大学出版社,1999.
【5】Zhenmao Chen and Kenzo Miya, A New Approach for Optimal Design of Eddy Current Testing Probes. Journal of Nondestructive Evaluation,1998,17(3):105-116.
【6】李家伟,陈积懋.无损检测手册\[M\].北京：机械工业出版社,2002.
【7】Chen C L P. A Rapid Supervised Learning Neural Network for Function Interpolation and Approximation. IEEE Trans Neural Networks,1996,7:1220-1230.
【2】Zhenmao Chen, Kenzo Miya, Masaaki Kurokawa. Rapid prediction of eddy current testing signals using A-phi method and database. NDT&E International,1999,32(1):29-36(8).
【3】Radu C. Popa, Kenzo Miya. Approximate Inverse Mapping in ECT, Based on Aperture Shifting and Neural Network Regression. Journal of Nondestructive Evaluation,1998,17(4):209-221.
【4】盛剑霓.工程电磁声数值分析\[M\].西安：西安交通大学出版社,1999.
【5】Zhenmao Chen and Kenzo Miya, A New Approach for Optimal Design of Eddy Current Testing Probes. Journal of Nondestructive Evaluation,1998,17(3):105-116.
【6】李家伟,陈积懋.无损检测手册\[M\].北京：机械工业出版社,2002.
【7】Chen C L P. A Rapid Supervised Learning Neural Network for Function Interpolation and Approximation. IEEE Trans Neural Networks,1996,7:1220-1230.
相关信息
