Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of golden time for recovering SISs using deep fuzzy neural networks with rule-dropout

  • Jo, Hye Seon (Department of Nuclear Engineering, Chosun University) ;
  • Koo, Young Do (Korea Atomic Energy Research Institute) ;
  • Park, Ji Hun (Department of Nuclear Engineering, Chosun University) ;
  • Oh, Sang Won (Department of Nuclear Engineering, Chosun University) ;
  • Kim, Chang-Hwoi (Korea Atomic Energy Research Institute) ;
  • Na, Man Gyun (Department of Nuclear Engineering, Chosun University)
  • Received : 2021.04.15
  • Accepted : 2021.06.06
  • Published : 2021.12.25
Download PDF
⟨ Previous Next ⟩

Abstract

If safety injection systems (SISs) do not work in the event of a loss-of-coolant accident (LOCA), the accident can progress to a severe accident in which the reactor core is exposed and the reactor vessel fails. Therefore, it is considered that a technology that provides recoverable maximum time for SIS actuation is necessary to prevent this progression. In this study, the corresponding time was defined as the golden time. To achieve the objective of accurately predicting the golden time, the prediction was performed using the deep fuzzy neural network (DFNN) with rule-dropout. The DFNN with rule-dropout has an architecture in which many of the fuzzy neural networks (FNNs) are connected and is a method in which the fuzzy rule numbers, which are directly related to the number of nodes in the FNN that affect inference performance, are properly adjusted by a genetic algorithm. The golden time prediction performance of the DFNN model with rule-dropout was better than that of the support vector regression model. By using the prediction result through the proposed DFNN with rule-dropout, it is expected to prevent the aggravation of the accidents by providing the maximum remaining time for SIS recovery, which failed in the LOCA situation.

Keywords

Acknowledgement

This work was supported by a National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT) (Grant Nos. NRF-2018M2A8A4025978 and 2018M2B2B1065651).

References

  1. K.H. Yoo, J.H. Back, M.G. Na, J.H. Kim, S. Hur, C.H. Kim, Prediction of golden time using SVR for recovering SIS under severe accidents, Ann. Nucl. Energy 94 (2016) 102-108. https://doi.org/10.1016/j.anucene.2016.02.029
  2. S.H. Yun, Y.D. Koo, M.G. Na, Collapse moment estimation for wall-thinned pipe bends and elbows using deep fuzzy neural networks, Nucl. Eng. Technol. 52 (2020) 2678-2685. https://doi.org/10.1016/j.net.2020.05.006
  3. Y.J. An, K.H. Yoo, M.G. Na, Y.S. Kim, Critical flow prediction using simplified cascade fuzzy neural networks, Ann. Nucl. Energy 136 (2020) 107047. https://doi.org/10.1016/j.anucene.2019.107047
  4. H.S. Jo, Y.D. Koo, K.H. Yoo, M.G. Na, C.H. Kim, Prediction of NPP containment states using deep fuzzy neural networks during LOCAs, in: Proceedings of the Korean Nuclear Society Virtual Autumn Meeting, 17-18, 2020. December.
  5. EPRI, MAAP4 Applications Guidance, Final Report 1020236, Electric Power Research Institute, Palo Alto, CA, USA, 2010.
  6. M. Saghafi, M.B. Ghofrani, Real-time estimation of break sizes during LOCA in nuclear power plants using NARX neural network, Nucl. Eng. Technol. 51 (2019) 702-708. https://doi.org/10.1016/j.net.2018.11.017
  7. K.H. Yoo, Y.D. Koo, J.H. Back, M.G. Na, Identification of LOCA and estimation of its break size by multiconnected support vector machines, IEEE Trans. Nucl. Sci. 64 (2017) 2610-2617. https://doi.org/10.1109/TNS.2017.2743098
  8. Y.D. Koo, Y.J. An, C.H. Kim, M.G. Na, Nuclear reactor vessel water level prediction during severe accidents using deep neural networks, Nucl. Eng. Technol. 51 (2019) 723-730. https://doi.org/10.1016/j.net.2018.12.019
  9. J.H. Park, Y.J. An, K.H. Yoo, M.G. Na, Leak flow prediction during loss of coolant accidents using deep fuzzy neural networks, Nucl. Eng. Technol. 53 (2021) 2547-2555. https://doi.org/10.1016/j.net.2021.01.040
  10. Y.D. Koo, H.S. Jo, M.G. Na, K.H. Yoo, C.H. Kim, Prediction of the internal states of a nuclear power plant containment in LOCAs using rule-dropout deep fuzzy neural networks, Ann. Nucl. Energy 156 (2021) 108180. https://doi.org/10.1016/j.anucene.2021.108180
  11. N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, R. Salakhutdinov, Dropout: a simple way to prevent neural networks from overfitting, J. Mach. Learn. Res. 15 (2014) 1929-1958.
  12. J. McCall, Genetic algorithms for modelling and optimisation, J. Comput. Appl. Math. 184 (2005) 205-222. https://doi.org/10.1016/j.cam.2004.07.034
  13. J.C. Duan, F.L. Chung, Cascaded fuzzy neural network model based on syllogistic fuzzy reasoning, IEEE Trans. Fuzzy Syst. 9 (2001) 293-306. https://doi.org/10.1109/91.919250
  14. T. Takagi, M. Sugeno, Fuzzy identification of systems and its applications to modeling and control, IEEE Trans. Syst. Man Cybern. SMC- 15 (1985) 116-132. https://doi.org/10.1109/TSMC.1985.6313399
  15. N. Dhanachandra, K. Manglem, Y.J. Chanu, Image segmentation using k-means clustering algorithm and subtractive clustering algorithm, Procedia Computer Science 54 (2015) 764-771. https://doi.org/10.1016/j.procs.2015.06.090
  16. K.Y. Chen, C.H. Wang, Support vector regression with genetic algorithms in forecasting tourism demand, Tourism Manag. 28 (2007) 215-226. https://doi.org/10.1016/j.tourman.2005.12.018