Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Impact parameter prediction of a simulated metallic loose part using convolutional neural network

  • Received : 2020.06.09
  • Accepted : 2020.10.14
  • Published : 2021.04.25
Download PDF
⟨ Previous Next ⟩

Abstract

The detection of unexpected loose parts in the primary coolant system in a nuclear power plant remains an extremely important issue. It is essential to develop a methodology for the localization and mass estimation of loose parts owing to the high prediction error of conventional methods. An effective approach is presented for the localization and mass estimation of a loose part using machine-learning and deep-learning algorithms. First, a methodology was developed to estimate both the impact location and the mass of a loose part at the same times in a real structure in which geometric changes exist. Second, an impact database was constructed through a series of impact finite-element analyses (FEAs). Then, impact parameter prediction modes were generated for localization and mass estimation of a simulated metallic loose part using machine-learning algorithms (artificial neural network, Gaussian process, and support vector machine) and a deep-learning algorithm (convolutional neural network). The usefulness of the methodology was validated through blind tests, and the noise effect of the training data was also investigated. The high performance obtained in this study shows that the proposed methodology using an FEA-based database and deep learning is useful for localization and mass estimation of loose parts on site.

Keywords

Acknowledgement

This work was supported by the Ministry of Science and ICT and the National Research Foundation of Korea (NRF) grant funded by the Korea government (2017M2A8A4015158).

References

  1. W.D. Rhodes, et al., Export Control Guide: Loose Parts Monitoring Systems for Nuclear Power Plants, Oak Ridge National Laboratory, 2012. ORNL/TM-2012/601.
  2. C.W. Mayo, et al., Loose-Parts Monitoring System Improvements, Electric Power Research Institute, 1988. EPRI NP-5743.
  3. J. Yang, et al., Detection method of loose parts in nuclear reactor based on eigenvector algorithm, Prog. Nucl. Energy 91 (2016) 250-255. https://doi.org/10.1016/j.pnucene.2016.03.020
  4. S.H. Shin, Mass estimation of impacting objects against a structure using an artificial neural network without consideration of background noise, Nuclear Engineering and Technology 43 (4) (2011) 343-354. https://doi.org/10.5516/NET.2011.43.4.343
  5. J.S. Kim, et al., Development of automatic algorithm for localizing loose parts with a steam generator, Nucl. Eng. Des. 219 (2002) 269-276. https://doi.org/10.1016/S0029-5493(02)00281-9
  6. B.J. Olma, Source location and mass estimation in loose parts monitoring of LWR's, Prog. Nucl. Energy 15 (1985) 583-594. https://doi.org/10.1016/0149-1970(85)90086-1
  7. S.M. Ziola, Source Location in Thin Plates Using Cross-Correlation, Progress in Nuclear Energy, Naval Postgraduate School, 1991. Ph.D. Thesis.
  8. T. Tsunoda, et al., Studies on the loose Part Evaluation technique, Prog. Nucl. Energy 15 (1985) 569-579. https://doi.org/10.1016/0149-1970(85)90084-8
  9. C.W. Mayo, Loose-Part Mass and energy estimation, Prog. Nucl. Energy 34 (3) (1999) 263-282. https://doi.org/10.1016/S0149-1970(98)00010-9
  10. S. Moon, et al., Model-based localization and mass-estimation methodology of metallic loose parts, Nuclear Engineering and Technology 52 (4) (2020) 846-855. https://doi.org/10.1016/j.net.2019.10.005
  11. S.H. Shin, et al., Markov chain-based mass estimation method for loose Part Monitoring system and its performance, Nuclear Engineering and Technology 49 (2017) 1555-1562. https://doi.org/10.1016/j.net.2017.05.005
  12. S. Moon, et al., FEA-based metal sphere map for mass estimation of simulated loose part in reactor coolant system, Prog. Nucl. Energy 106 (2018) 357-366. https://doi.org/10.1016/j.pnucene.2018.03.008
  13. S. Moon, et al., Plate bending wave propagation behavior under metal sphere impact loading, J. Mech. Sci. Technol. 32 (No. 3) (2018) 1117-1124. https://doi.org/10.1007/s12206-018-0214-9
  14. J. Liska, et al., Localization of loose Part Impacts on the general 3D surface of the nuclear power plant coolant circuit components, Prog. Nucl. Energy 99 (2017) 140-146. https://doi.org/10.1016/j.pnucene.2017.05.004
  15. Dassault, ABAQUS Version 6.14, User's Manual, Dassault Systems Simulia, 2018.
  16. H. Sun, et al., Simultaneous identification of structural parameters and dynamic input with incomplete output-only measurements, Struct. Contr. Health Monit. 21 (No. 6) (2014) 868-889. https://doi.org/10.1002/stc.1619
  17. H. Sun, et al., A sweeping window method for detection of flaws using an explicit dynamic XFEM and absorbing boundary layers, Int. J. Numer. Methods Eng. 105 (2016) 1014-1040. https://doi.org/10.1002/nme.5006
  18. C.E. Rasmussen, et al., Gaussian Processes for Machine Learning, The MIT Press, 2006.
  19. E. Papatheou, et al., Wind turbine structural health monitoring: a short investigation based on SCADA data, in: 7th European Workshop on Structural Health Monitoring, 2014, pp. 515-519.
  20. R. Fuentes, et al., Autoregressive Gaussian Process for Structural Damage Detection, ISMA 2014, 2014, pp. 469-484.
  21. L. Bornn, et al., Structural health monitoring with autoregressive support vector machines, J. Vib. Acoust. 131 (2009), 021004-1-021004-9. https://doi.org/10.1115/1.3025827
  22. Y. LeCun, et al., Deep Learning, Nature 521 (7553) (2015) 436-444. https://doi.org/10.1038/nature14539
  23. N. Munir, et al., 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
  24. B.G. Gallager, Principles of Digital Communication: A Top-Down Approach, Cambridge University Press, 2016.