期刊
IEEE TRANSACTIONS ON MAGNETICS
卷 49, 期 5, 页码 1653-1656出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TMAG.2012.2236827
关键词
Hybrid inverse analysis; local wall thinning; pulsed eddy current testing; quantitative NDT
资金
- Grants-in-Aid for Scientific Research [23246038, 24860005] Funding Source: KAKEN
Quantitative non-destructive evaluation, especially sizing of piping wall thinning in nuclear power plants is still a difficult and urgent issue. In this paper, an inversion approach for PECT (pulsed eddy current testing) signals is developed based on ANN (artificial neural network) method at first for profile reconstruction of wall thinning, the sizing result of NN is then utilized as the initial value of the CG (conjugate gradient) inversion scheme to overcome the shortages of both the NN (accuracy problem) and CG (local minimum problem) methods. Several reconstruction examples using the proposed hybrid strategy indicate that the combination of NN and CG methods is rather effective for wall thinning reconstruction from PECT signals in view of both the robustness and sizing accuracy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据