Journal of the Korean Society for Nondestructive Testing (비파괴검사학회지)

The Korean Society for Nondestructive Testing (한국비파괴검사학회)
권호 표지

A Study on Bagging Neural Network for Predicting Defect Size of Steam Generator Tube in Nuclear Power Plant

원전 증기발생기 세관 결함 크기 예측을 위한 Bagging 신경회로망에 관한 연구

  • Kim, Kyung-Jin (Department of Electrical Engineering, Soongsil University) ;
  • Jo, Nam-Hoon (Department of Electrical Engineering, Soongsil University)
  • 김경진 (숭실대학교 전기공학부) ;
  • 조남훈 (숭실대학교 전기공학부)
  • Received : 2010.05.12
  • Accepted : 2010.08.06
  • Published : 2010.08.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we studied Bagging neural network for predicting defect size of steam generator(SG) tube in nuclear power plant. Bagging is a method for creating an ensemble of estimator based on bootstrap sampling. For predicting defect size of SG tube, we first generated eddy current testing signals for 4 defect patterns of SG tube with various widths and depths. Then, we constructed single neural network(SNN) and Bagging neural network(BNN) to estimate width and depth of each defect. The estimation performance of SNN and BNN were measured by means of peak error. According to our experiment result, average peak error of SNN and BNN for estimating defect depth were 0.117 and 0.089mm, respectively. Also, in the case of estimating defect width, average peak error of SNN and BNN were 0.494 and 0.306mm, respectively. This shows that the estimation performance of BNN is superior to that of SNN.

본 논문에서는 원자력 발전소 증기발생기 세관에 발생할 수 있는 결함의 크기측정에 사용되는 Bagging 신경회로망에 대한 연구를 수행하였다. Bagging은 부트스트랩(bootstrap) 샘플링에 기반을 둔 추정기 앙상블을 생성하는 방법이다. 증기발생기 세관의 결함 크기측정을 위하여 다양한 폭과 깊이를 갖는 4가지 결함패턴의 eddy current testing 신호를 생성하였다. 그 다음, 단일 신경회로망(single neural network; SNN)과 Bagging 신경회로망(Bagging neural network; BNN)을 구성하여 각 결함의 폭과 깊이를 추정하였다. SNN과 BNN 추정성능은 최대오차를 이용해서 측정하였다. 실험결과, 결함 깊이 추정시의 SNN과 BNN 최대오차는 0.117mm와 0.089mm 이었다. 또한, 결함 폭 추정 시에는 SNN과 BNN 최대오차는 0.494mm와 0.306mm 이었다. 이러한 실험결과는 BNN 추정성능이 SNN 추정성능보다 우수하다는 것을 보여준다.

Keywords

Acknowledgement

Supported by : 한국연구재단

References

  1. E. E. Kriezis, T. D. Tsiboukis, S. M. Panas and J. A. Tegopoulos, "Eddy currents: 309 theory and applications," Proceedings of the IEEE, Vol. 80, No. 10, pp. 1559-1589 (1992) https://doi.org/10.1109/5.168666
  2. H. B. Lee and D. H. Kim, "Impedance calculation for a plate with crack in eddy current NDT using 3D indirect BIEM," IEEE Transactions on Magnetics, Vol. 36, No.5, pp. 3131-3133 (2000) https://doi.org/10.1109/20.908709
  3. K. Miya, "Recent advancement of electromagnetic nondestructive inspection technology in Japan," IEEE Transactions on Magnetics, Vol. 38, No.2, pp. 321-326 (2002) https://doi.org/10.1109/20.996088
  4. M. Rebican, Z. Chen, N. Yusa, L. Janousek and K. Miya, "Shape reconstruction of multiple cracks from ECT signals by means of a stochastic method," IEEE Transactions on Magnetics, Vol. 42, No.4, pp. 1079-1082 (2006)
  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) https://doi.org/10.1016/S0963-8695(99)00046-8
  6. H. Haoyu and T. Takagi, "Inverse analyses for natural and multicracks using signals from a differential transmit-receive ECT probe," IEEE Transactions on Magnetics, Vol. 38, No. 2, Part 1, pp. 1009-1012 (2002) https://doi.org/10.1109/20.996259
  7. 조남훈, 이향범, 한기원, 송성진, "신경회로망을 이용한 원전SG 세관 결함패턴 분류성능 향상기법", 전기학회논문지 Vol. 56, No. 7, pp. 1224-1230. (2007)
  8. 한기원, 조남훈, 이향범 "신경회로망을 이용한 원전SG 세관 결함크기 예측", 비파괴검사학회지 Vol. 27, No. 5, pp. 383-392. (2007)
  9. M. T. Hagan, H. B. Demuth and M. H. Beale, Neural Network Design, PWS Pub. Co (1995)
  10. L. Breiman, "Bagging predictors," Machine Learning, 24, pp. 123-140 (1996)
  11. D. Opitz and R. Maclin, "Popular ensemble methods: an empirical study," Journal of Artificial Intelligence Research, pp. 169-198, November (1999)
  12. L. I. Kuncheva, Combining Pattern Classifiers: Methods and Algorithms, John Wiley & Sons. Inc (2004)
  13. N. M. Wanas and M. S. Kamel, "Decision fusion in neural network ensembles," Proceedings of the International Joint Conference on Neural Network, Washington DC, Vol. 4, pp. 2952-2957 (2001)
  14. M. P. Perrone and L. N. Cooper, "When networks disagree: Ensemble methods for hybrid neural networks," Neural Networks for Speech and Image Processing by R. J. Marmmone, Ed., Chapman-Hall (1993)