Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Loading pattern optimization using simulated annealing and binary machine learning pre-screening

  • Ga-Hee Sim (Department of Quantum and Nuclear Engineering, Sejong University) ;
  • Moon-Ghu Park (Department of Quantum and Nuclear Engineering, Sejong University) ;
  • Gyu-ri Bae (Department of Quantum and Nuclear Engineering, Sejong University) ;
  • Jung-Uk Sohn (ZettaCognition)
  • Received : 2023.02.20
  • Accepted : 2023.12.09
  • Published : 2024.05.25
Download PDF
⟨ Previous Next ⟩

Abstract

We introduce a creative approach combining machine learning with optimization techniques to enhance the optimization of the loading pattern (LP). Finding the optimal LP is a critical decision that impacts both the reload safety and the economic feasibility of the nuclear fuel cycle. While simulated annealing (SA) is a widely accepted technique to solve the LP optimization problem, it suffers from the drawback of high computational cost since LP optimization requires three-dimensional depletion calculations. In this note, we introduce a technique to tackle this issue by leveraging neural networks to filter out inappropriate patterns, thereby reducing the number of SA evaluations. We demonstrate the efficacy of our novel approach by constructing a machine learning-based optimization model for the LP data of the Korea Standard Nuclear Power Plant (OPR-1000).

Keywords

Acknowledgement

This work was supported by the KETEP funded by the Korea government Ministry of Trade, Industry and Energy (20206510100040).

References

  1. S. Levine, In-core fuel management of four reactor types, Handbook Nuclear Reactor Calculat. 2 (1986) 87-201.
  2. Y.J. Lee, K.H. Han, A tabu search algorithm for relocation by replacement cycle according to combustion of radioactive nuclear fuel, J. Korean Inst. Intelligent Syst. 28 (2) (2018) 164-169.
  3. T.K. Park, H.G. Joo, C.H. Kim, H.C. Lee, Multiobjective loading pattern optimization by simulated annealing employing discontinuous penalty function and screening technique, Nucl. Sci. Eng. 162 (2) (2009) 134-147.
  4. S. Kirkpatrick, C.D. Gelatt, M.P. Vecchi, Optimization by simulated annealing, Science 220 (1983) 671-680.
  5. H. G. Kim, S. H. Chang, B. H. Lee, Optimal fuel loading pattern design using artificial neural network and a fuzzy rule-based system, Nucl. Sci. Eng. 115 (2) 152-163.
  6. M.G. Lysenko, H.I. Wong, G.I. Maldonado, Neural networkand perturbation theoryhybrid models for eigenvalue prediction, Nucl. Sci. Eng. 132 (1) (1999) 78-89.
  7. H.B. Jang, H.C. Lee, H.C. Shin, Refinement of convolutional neural network for neutronic design parameter prediction of a loading pattern, in: Proceedings of Reactor Physics Asia Conference 2019, RPHA19, 2020.
  8. J.J. Hopfield, Neural networks and physical systems with emergent collective computational abilities, Proc. Natl. Acad. Sci. USA 79 (8) (1982) 2554-2558.
  9. E. Israeli, E. Gilad, Novel genetic algorithm for loading pattern optimization based on core physics heuristics, Ann. Nucl. Energy 118 (2018) 35-48.
  10. H.Y. Jun, J.H. Park, Generation of optimal correlations by simulated annealing for ill-conditioned least-squares solution, J. Nucl. Sci. Technol. 52 (5) (2015) 670-674.
  11. J. Choe, S. Choi, P. Zhang, J. Park, W. Kim, H.C. Shin, H.S. Lee, J.-E. Jung, D. Lee, Verification and validation of stream/rast-k for pwr analysis, Nucl. Eng. Technol. 51 (2) (2019) 356-368.