DOI QR코드

DOI QR Code

Magnetic Flux Leakage (MFL) based Defect Characterization of Steam Generator Tubes using Artificial Neural Networks

  • Daniel, Jackson (National Engineering College, Department of Electronics and Instrumentation Engineering) ;
  • Abudhahir, A. (Vel Tech Multitech Dr. Rangarajan Dr. Sakunthala Engineering College, Department of Electrical and Electronics Engineering) ;
  • Paulin, J. Janet (National Engineering College, Department of Electronics and Instrumentation Engineering)
  • Received : 2016.08.18
  • Accepted : 2017.01.04
  • Published : 2017.03.31

Abstract

Material defects in the Steam Generator Tubes (SGT) of sodium cooled fast breeder reactor (PFBR) can lead to leakage of water into sodium. The water and sodium reaction will lead to major accidents. Therefore, the examination of steam generator tubes for the early detection of defects is an important requirement for safety and economic considerations. In this work, the Magnetic Flux Leakage (MFL) based Non Destructive Testing (NDT) technique is used to perform the defect detection process. The rectangular notch defects on the outer surface of steam generator tubes are modeled using COMSOL multiphysics 4.3a software. The obtained MFL images are de-noised to improve the integrity of flaw related information. Grey Level Co-occurrence Matrix (GLCM) features are extracted from MFL images and taken as input parameter to train the neural network. A comparative study on characterization have been carried out using feed-forward back propagation (FFBP) and cascade-forward back propagation (CFBP) algorithms. The results of both algorithms are evaluated with Mean Square Error (MSE) as a prediction performance measure. The average percentage error for length, depth and width are also computed. The result shows that the feed-forward back propagation network model performs better in characterizing the defects.

References

  1. Derac Son, Wonik Jung, Duck Gun Park, and Kwon Sang Ryu, IEEE Trans. Magn. 45, 2724 (2009). https://doi.org/10.1109/TMAG.2009.2020537
  2. P. Xiang, S. Ramakrishnan, X. Cali, P. Ramuhalli, R. Polikar, S. S. Udpa, and L. Udpa, Int. J. Appl. Electromagn. Mechan. 12, 151 (2000).
  3. Baofu Lu, Belle and R. Upadhyaya, IEEE Trans. Nuclear Science 52, 484 (2005). https://doi.org/10.1109/TNS.2004.843121
  4. Ameet Joshi, Lalita Udpa, Satish Udpa, and Antonello Tamburrino, IEEE Trans. Magn. 42, 3168 (2006). https://doi.org/10.1109/TMAG.2006.880091
  5. M. Li and D. A. Lowther, IEEE Trans. Magn. 46, 3221 (2010). https://doi.org/10.1109/TMAG.2010.2045744
  6. Maryam Ravan, Reza Khalaj Amineh, Slawomir Koziel, K. Natalia, Nikolova, and P. James, Reilly 46, 1024 (2010).
  7. Yuji Gotoh and Norio Takahashi, IEEE Trans. Magn. 38, 1209 (2002). https://doi.org/10.1109/20.996309
  8. Kenji Sakai, Koji Morita, YutaHaga, Toshihiko Kiwa, Katsumi Inoue, and Keiji T. Sukada, IEEE Trans. Magn. 51, 11 (2015).
  9. J.-H. Kim, M.-H. Kim, and D.-H. Choi, J. Magn. 18, 202 (2013). https://doi.org/10.4283/JMAG.2013.18.2.202
  10. S. J. Farley, J. F. Durodola, N. A. Fellows, and L. H. Hernandez-Gomez, NDT&E Int. 52, 69 (2012). https://doi.org/10.1016/j.ndteint.2012.08.011
  11. D.-G. Park, M. B. Kishore, J. Y. Kim, L. J. Jacobs, and D. H. Lee, J. Magn. 21, 57 (2016). https://doi.org/10.4283/JMAG.2016.21.1.057
  12. R. A. Chayjan, Australian J. Crop. Sci. 4, 180 (2010).
  13. H. Demuth, M. Beale, and M. Hagan, Neural Network Toolbox User's Guide. The Mathworks, Inc., Natrick, USA (2009).
  14. D. S. Badde, A. K. Gupta, and K. V. Patki, IOSR J. Mech. and Civil Eng., 01-06.
  15. Sumit Goyal and Gyandera Kumar Goyal, Canadian Journal on Artificial Intelligence, Machine Learning and Pattern Recognition, 2 (2011).
  16. Francesco Riganti Fulginei and Alessandro Salvini, IEEE Trans. Magn. 48 (2012).
  17. A. A. Carvalho, J. M. A. Rebello, L. V. S. Sagrilo, C. S Camerini, and I. V. J. Miranda, NDT&E Int. 39, 661 (2006). https://doi.org/10.1016/j.ndteint.2006.04.003
  18. Debmalya Mukherjee, S. Saha, and S. Mukhopadhyay, Inverse mapping of magnetic flux leakage signal for defect characterization, NDT&E Int. 54, 198 (2013). https://doi.org/10.1016/j.ndteint.2012.11.001
  19. Alaa Eleyan and Hasan Demirel. Co-occurrence matrix and its statistical features as a new approach for face recognition, Turk J. Elec. Eng. & Comp. Sci. 19, 97 (2011).
  20. P. Karuppasamy, P. A. Abudhahir, M. Prabhakaran, S. Thirunavukkarasu, B. P. C. Rao, and T. Jayakumar, J. Non-destructive Evaluation 35, 1 (2016).
  21. Yan Shi, Chao Zhang, Rui Li, Maolin Cai, and Guanwei Jia, Sensors 15, 31036 (2015). https://doi.org/10.3390/s151229845
  22. Jackson Daniel, R. Mohanagayathri, and A. Abudhahir, IEEE International Conference on Electronics and Communication Systems (2014).
  23. A. David and Clausi, J. Can, Remote Sensing 28, 45 (2002).
  24. Abdolvahab Ehsanirad and Y. H. Sharath Kumar, Oriental Journal of Computer Science & Technology 3, 31 (2010).
  25. Mohamed Layouni, Sofiene Tahar, and Mohamed Salah Hamdi, IEEE Symposium on computational Intelligence for Engineering Solutions 14855753, 95 (2014).

Cited by

  1. Simulation of Real Defect Geometry and Its Detection Using Passive Magnetic Inspection (PMI) Method vol.8, pp.7, 2018, https://doi.org/10.3390/app8071147