Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Classification of ultrasonic signals of thermally aged cast austenitic stainless steel (CASS) using machine learning (ML) models

  • Kim, Jin-Gyum (Korea Institute of Nuclear Safety) ;
  • Jang, Changheui (Department of Nuclear and Quantum Engineering, Korea Advanced Institute of Science and Technology) ;
  • Kang, Sung-Sik (Korea Institute of Nuclear Safety)
  • Received : 2021.07.08
  • Accepted : 2021.09.29
  • Published : 2022.04.25
Download PDF
⟨ Previous Next ⟩

Abstract

Cast austenitic stainless steels (CASSs) are widely used as structural materials in the nuclear industry. The main drawback of CASSs is the reduction in fracture toughness due to long-term exposure to operating environment. Even though ultrasonic non-destructive testing has been conducted in major nuclear components and pipes, the detection of cracks is difficult due to the scattering and attenuation of ultrasonic waves by the coarse grains and the inhomogeneity of CASS materials. In this study, the ultrasonic signals measured in thermally aged CASS were discriminated for the first time with the simple ultrasonic technique (UT) and machine learning (ML) models. Several different ML models, specifically the K-nearest neighbors (KNN), Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP) models, were used to classify the ultrasonic signals as thermal aging condition of CASS specimens. We identified that the ML models can predict the category of ultrasonic signals effectively according to the aging condition.

Keywords

Acknowledgement

This study was supported by the Korea Foundation of Nuclear Safety (KoFONS) using financial resources granted by the Nuclear Safety and Security Commission (NSSC) of the Republic of Korea. (No. 2106001). The thermally aged CASS specimens were provided by the PNNL as a part of an international collaborative R&D project of PIONIC. We wish to thank Dr. Jongbeom Kim, Dr. Kyung-Mo Kim (Korea Atomic Energy Research Institute, KR) who helped us in providing the ultrasonic equipment. Also, we would like to acknowledge Dr. Thak Sang Byun (Oak Ridge National Laboratory, US) who helped us in providing the information of specimens.

References

  1. O.K. Chopra, A. Sather, Initial assessment of the mechanisms and significance of low-temperature embrittlement of cast stainless steels in LWR system. Nuclear Regulatory Commission, 1990. NUREG/CR-5385.
  2. H.M. Chung, Aging and life prediction of cast duplex stainless steel components, Int. J. Pres. Ves. Pip. 50 (1-3) (1992) 179-213. https://doi.org/10.1016/0308-0161(92)90037-G
  3. H. Jang, S. Hong, C. Jang, J.G. Lee, The effects of reversion heat treatment on the recovery of thermal aging embrittlement of CF8M cast stainless steels, Mater. Des. 56 (2014) 517-521. https://doi.org/10.1016/j.matdes.2013.12.010
  4. C. Jang, H. Jang, S. Hong, J.G. Lee, Evaluation of the recovery of thermal aging embrittlement of CF8M cast stainless steels after reversion heat treatments, Int. J. Pres. Ves. Pip. 131 (2015) 67-74. https://doi.org/10.1016/j.ijpvp.2015.04.011
  5. T.S. Byun, D.A. Collins, T.G. Lach, E.L. Carter, Degradation of impact toughness in cast stainless steels during long-term thermal aging, J. Nucl. Mater. 542 (2020) 152524. https://doi.org/10.1016/j.jnucmat.2020.152524
  6. B. S. Kong, C. Jang, S. Kang, T. S. Byun, Evaluation of thermal ageing of cast austenitic stainless steels - mechanical properties in micro- and macro-scale, in: Proceedings of the 13th International Symposium on the Integrity of Nuclear Components, Virtual Meeting, April 21-22, 2021.
  7. C. Wunderlich, C. Tschope, F. Duckhorn, Advanced methods in NDE using machine learning approaches, in: AIP Conference Proceedings, 1, 2018, 020022.
  8. J.B. Harley, D. Sparkman, Machine learning and NDE: past, present, and future, in: AIP Conference Proceedings, 2102, 2019, 090001.
  9. P. Gardner, R. Fuentes, N. Dervilis, C. Mineo, S.G. Pierce, E.J. Cross, K. Worden, Machine learning at the interface of structural health monitoring and nondestructive evaluation, Philosophical Transactions of the Royal Society A 378 (2182) (2020) 20190581.
  10. A.J. Fredo, R.S. Abilash, R. Femi, A. Mythili, C.S. Kumar, Classification of damages in composite images using Zernike moments and support vector machines, Compos. B Eng. 168 (2019) 77-86. https://doi.org/10.1016/j.compositesb.2018.12.064
  11. W. Choi, H. Huh, B.A. Tama, G. Park, S. Lee, A neural network model for material degradation detection and diagnosis using microscopic images, IEEE Access 7 (2019) 92151-92160. https://doi.org/10.1109/access.2019.2927162
  12. 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
  13. N. Munir, J. Park, H.J. Kim, S.J. Song, S.S. Kang, Performance enhancement of convolutional neural network for ultrasonic flaw classification by adopting autoencoder, NDT E Int. 111 (2020) 102218. https://doi.org/10.1016/j.ndteint.2020.102218
  14. P. Jeong, F. Ammirato, Ultrasonic examination of cast stainless steel component in nuclear power plant. Review of Progress in Quantitative Nondestructive Evaluation, 1989, pp. 2105-2112.
  15. P. Ramuhalli, et al., Ultrasonic Characterization of Cast Austenitic Stainless Steel Microstructure: Discrimination between Equiaxed-And Columnar-Grain Material-An Interim Study, Pacific Northwest National Lab.(PNNL), 2009. PNNL-18912.
  16. R.E. Jacob, et al., NDE Reliability Issues for the Examination of CASS Components, Pacific Northwest National Lab.(PNNL), 2019. PNNL-28840.
  17. P. Majumdar, S.B. Singh, M. Chakraboty, Elastic modulus of biomedical titanium alloys by nano-indentation and ultrasonic techniques - a comparative study, Mater. Sci. Eng. 489 (2008) 419-425. https://doi.org/10.1016/j.msea.2007.12.029
  18. J. Kim, J.G. Kim, B. Kong, K.M. Kim, C. Jang, S.S. Kang, K.Y. Jhang, Applicability of nonlinear ultrasonic technique to evaluation of thermally aged CF8M cast stainless steel, Nuclear Engineering and Technology 52 (3) (2020) 621-625. https://doi.org/10.1016/j.net.2019.09.004
  19. ASTM A351/A351M-00, Standard Specification for Castings, Austenitic, Austenitic-Ferritic (Duplex), for Pressure-Containing Parts, ASTM International, West Conshohocken, PA, USA, 2000.
  20. L. Buitinck et al., API Design for Machine Learning Software: Experiences from the Scikit-Learn Project. arXiv. 2015. https://arxiv.org/abs/1309.0238.
  21. L.E. Peterson, K-nearest neighbor, Scholarpedia 4 (2) (2009) 1883. https://doi.org/10.4249/scholarpedia.1883
  22. W.S. Noble, What is a support vector machine? Nat. Biotechnol. 24 (12) (2006) 1565-1567. https://doi.org/10.1038/nbt1206-1565
  23. Scikit-learn (support vector machine), Available online: https://scikit-learn.org/stable/modules/svm.html#svm-mathematical-formulation. (Accessed 7 July 2021).
  24. M.W. Gardner, S.R. Dorling, Artificial neural networks (the multilayer perceptron) - a review of applications in the atmospheric sciences, Atmospheric environment 32 (14-15) (1998) 2627-2636. https://doi.org/10.1016/S1352-2310(97)00447-0
  25. V. Nair, G.E. Hinton, Rectified linear units improve restricted Boltzmann machines, in: Haifa Icml (Ed.), Israel, 2010. June 21-24.
  26. D. P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization. arXiv. 2014. https://arxiv.org/abs/1412.6980.
  27. F. Pedregosa, et al., Scikit-learn: machine learning in Python, J. Mach. Learn. Res. 12 (2011) 2825-2830.
  28. DeepAi, Available online: https://deepai.org/machine-learning-glossary-and-terms/accuracy-error-rate. (Accessed 7 July 2021).
  29. G. Zhang, M.Y. Hu, B.E. Patuwo, D.C. Indro, Artificial neural networks in bankruptcy prediction: general framework and cross-validation analysis, Eur. J. Oper. Res. 116 (1) (1999) 16-32. https://doi.org/10.1016/S0377-2217(98)00051-4
  30. Scikit-learn (Confusion matrix). Available online: https://scikit-learn.org/0.18/auto_examples/model_selection/plot_confusion_matrix.html. (Accessed 7 July 2021).
  31. C. Goutte, E. Gaussier, A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. European Conference on Information Retrieval, 2005, pp. 345-359.