Browse > Article
http://dx.doi.org/10.5207/JIEIE.2012.26.9.073

Improvement of Neural Network Performance for Estimating Defect Size of Steam Generator Tube using Multifold Cross-Validation  

Kim, Nam-Jin (Soongsil University, Dept. Electrical Engineering)
Jee, Su-Jung (Soongsil University, Dept. Electrical Engineering)
Jo, Nam-Hoon (Soongsil University, Dept. Electrical Engineering)
Publication Information
Journal of the Korean Institute of Illuminating and Electrical Installation Engineers / v.26, no.9, 2012 , pp. 73-79 More about this Journal
Abstract
In this paper, we study on how to determine the number of hidden layer neurons in neural network for predicting defect size of steam generator tube. It was reported in the literature that the number of hidden layer neurons can be efficiently determined with the help of cross-validation. Although the cross-validation provides decent estimation performance in most cases, the performance depends on the selection of validation set and rather poor performance may be led to in some cases. In order to avoid such a problem, we propose to use multifold cross-validation. Through the simulation study, it is shown that the estimation performance of defect width (defect depth, respectively) attains 94% (99.4%, respectively) of the best performance achievable among the considered neuron numbers.
Keywords
Steam Generator Tube; Eddy Current Testing; Neural Network; Multifold Cross-Validation;
Citations & Related Records
Times Cited By KSCI : 2  (Citation Analysis)
연도 인용수 순위
1 G. Chen, A. Yamaguchi, K. Miya, "A novel signal processing technique for eddy-current testing of steam generator tubes," IEEE Trans. Magnetics, Vol. 34, pp. 642-648, 1998.   DOI   ScienceOn
2 P. Xiang, S. Ramakrishnan, X. Cai, P. Ramuhalli, R. Polikar, S.S. Udpa, L. Udpa, "Automated analysis of rotating probe multi-frequency eddy current data from steam generator tubes," International Journal of Applied Electromagnetics and Mechanics, Vol. 12, pp. 151-164, 2000.
3 M. Das, H. Shekhar, X. Liu, R. Polikar, P. Ramuhalli, L. Udpa, S. Udpa, "A generalized likelihood ratio technique for automated analysis of bobbin coil eddy current data," NDT & E International, Vol. 35, pp. 329-336, 2002.   DOI
4 H. Haoyu, T. Takagi, "Inverse analyses for natural and multicracks using signals from a differential transmit-receive ECT probe," IEEE Trans. Magnetics, Vol. 38, pp. 1009-1012, 2002.   DOI   ScienceOn
5 S.J. Song and Y.K. Shin, "Eddy current Flaw characterization in tubes by neural networks and finite element modeling," NDT & E International, Vol. 33, pp. 233-243, 2000.   DOI   ScienceOn
6 Nam H. Jo, and Hyang-Beom Lee, "A Novel Feature Extraction for Eddy Current Testing of Steam Generator Tubes", NDT & E International, Vol. 42, pp. 658-663, Oct., 2009.   DOI   ScienceOn
7 이준표, 조남훈, "Bagging 방법을 이용한 원전SG 세관 결함패턴 분류성능 향상기법," 전기학회 논문지, Vol. 58, pp. 2532-2537, Dec., 2009.   과학기술학회마을
8 조남훈, "원전SG 세관 결함크기 예측을 위한 신경회로망 구조에 관한 연구," 조명전기설비학회논문지, Vol. 24, pp. 63-70, Jan., 2010.   과학기술학회마을   DOI
9 S. Haykin, Neural Networks, New Jersey: Prentice -Hall, 1999.