DOI QR코드

DOI QR Code

MRPC eddy current flaw classification in tubes using deep neural networks

  • Park, Jinhyun (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Han, Seong-Jin (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Munir, Nauman (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Yeom, Yun-Taek (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Song, Sung-Jin (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Kim, Hak-Joon (Department of Mechanical Engineering, Sungkyunkwan University) ;
  • Kwon, Se-Gon (Korea Railroad Corp.)
  • Received : 2019.03.25
  • Accepted : 2019.05.13
  • Published : 2019.10.25

Abstract

Accurate and consistent characterization of defects in steam generator tubes (SGT) in nuclear power plants is one of the key issues in the field of nondestructive testing since the large number of signals to be analyzed in a time-limited in-service inspection causes a serious problem in practice. This paper presents an effective approach to this difficult task of automated classification of motorized rotating pancake coil (MRPC) eddy current flaw acquired from tube specimens with deliberated defects using deep neural networks (DNN). This approach consists of five steps, namely, the data acquisition using the MRPC probe in the tube, the signal preprocessing to make data more suitable for training DNN, the data augmentation for boosting a training performance, the training of DNN, and finally demonstration of the trained DNN for discriminating the axial and circumferential defects. The high performance obtained in this study shows that DNN is useful for classification of defects in tubes from the MRPC eddy current signals even though the number of signals is very large.

Acknowledgement

Supported by : Korea Agency for Infrastructure Technology Advancement (KAIA)

References

  1. J.Y. Yoo, Prediction and Evaluation of Eddy Current Testing Signals from Rotating Pancake Coil Probe in Steam Generator Tubes, Master Thesis, Sungkyunkwan University, 2005.
  2. Steam generator(nuclear power), wikipedia. https://en.wikipedia.org/wiki/Steam_generator_(nuclear_power. (Accessed 6 March 2019).
  3. D.R. Diercks, W.J. Shack, J. Muscara, Overview of steam generator tube degradation and integrity issues, Nucl. Eng. Des. 194 (1999) 19-30. https://doi.org/10.1016/S0029-5493(99)00167-3
  4. L. Obrutsky, J. Renaud, R. Lakhan, Overview of Steam Generator Tube-Inspection Technology, CINDE, 2009.
  5. Steam Generator Management Program, Automated Analysis of Rotating Probe Eddy Current Data, EPRI, Palo Alto, CA, 2009, p. 1018560.
  6. ReveospECT, Zetec. https://www.zetec.com/services/inspection-services/revospect-inspection-services/2224-2/. (Accessed 6 March 2019).
  7. AIDA, Orano. http://us.areva.com/home/liblocal/docs/News/2015/AREVA_MIRA_EPRI.pdf. (Accessed 6 March 2019).
  8. KHNP Central Research Institute, Performance evaluation of automatic evaluation program of steam generator NDT, electimes (2017) last modified Jul 11, http://www.electimes.com/article.php?aid=1499732564146246003. (Accessed 6 March 2019).
  9. N. Munir, H.J. Kim, S.J. Song, S.S. Kang, Investigation of deep neural network with drop out for ultrasonic flaw classification in weldments, J. Mech. Sci. Technol. 32 (7) (2018) 3073-3080. https://doi.org/10.1007/s12206-018-0610-1
  10. N. Munir, H.J. Kim, J. Park, S.J. Song, S.S. Kang, Convolutional neural network for ultrasonic weldment flaw classification in noisy conditions, Ultrasonics 94 (2019) 74-81. https://doi.org/10.1016/j.ultras.2018.12.001
  11. L. Udpa, P. Ramuhalli, J. Benson, S. Udpa, Automated analysis of eddy current signals in steam generator tube inspection, in: Proceedings of the 16th WCNDT, 2004.
  12. Steam Generator ECT Guidelines OPR-1000(I-600HTMA), Korea Hydro & Nuclear Power, 2015.
  13. 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, Int. J. Appl. Electromagn. Mech. 12 (2000) 151-164.
  14. A. Geron, Hands on Machine Learning with Scikit-Learn and Tensorflow, O'Reilly, Media, 2017.
  15. G.E. Hinton, N. Srivastava, A. Krizhevsky, I. Sutskever, R.R. Salakhutdinov, Improving Neural Networks by Preventing Co-adaptation of Feature Detectors, 2012 arXiv preprint, parXiv:1207.0580.
  16. N. Srivastava, G.E. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res. 15 (1) (2014) 1929-1958.