Optimisation of used nuclear fuel canister loading using a neural network and genetic algorithm
Tóm tắt
This paper presents an approach for the optimisation of geological disposal canister loadings, combining high resolution simulations of used nuclear fuel characteristics with an articial neural network and a genetic algorithm. The used nuclear fuels (produced in an open fuel cycle without reprocessing) considered in this work come from a Swiss Pressurised Water Reactor, taking into account their realistic lifetime in the reactor core and cooling periods, up to their disposal in the final geological repository. The case of 212 representative used nuclear fuel assemblies is analysed, assuming a loading of 4 fuel assemblies per canister, and optimizing two safety parameters: the fuel decay heat (DH) and the canister effective neutron multiplication factor k
$$_{\mathrm{eff}}$$
. In the present approach, a neural network is trained as a surrogate model to evaluate the k
$$_{\mathrm{eff}}$$
value to substitute the time-consuming-code Monte Carlo transport & depletion SERPENT for specific canister loading calculations. A genetic algorithm is then developed to optimise simultaneously the canister k
$$_{\mathrm{eff}}$$
and DH values. The k
$$_{\mathrm{eff}}$$
computed during the optimisation algorithm is using the previously developed artificial neural network. The optimisation algorithm allows (1) to minimize the number of canisters, given assumed limits for both DH and k
$$_{\mathrm{eff}}$$
quantities and (2) to minimize DH and k
$$_{\mathrm{eff}}$$
differences among canisters. This study represents a proof-of-principle of the neural network and genetic algorithm capabilities, and will be applied in the future to a larger number of cases.
Tài liệu tham khảo
(2008) Sectoral Plan for deep geological repositories—conceptual Part 2008, swiss federal office of energy, Switzerland, available here
(2016) The Nagra research, development and demonstration (RD&D) plan for the disposal of radioactive waste in Switzerland, NAGRA technical report 16–02
Amann F, Löw S, Perras M (2015) Assessment of geomechanical properties, maximum depth below ground surface and EDZ impact on long term safety”, ETH Zürich, October 29, , ENSI Report No. 33/460
(2009) The Nagra research, development and demonstration (RD&D) plan for the disposal of radioactive waste in Switzerland, NAGRA technical report 09–06
(2015) Spent nuclear fuel management in Switzerland. In: Perspective for final disposal international conference on management of spent nuclear fuel from nuclear power reactors: an integrated approach to the back end of the fuel cycle, IAEA, Vienna, June 15–19
Vasiliev A, Herrero J, Pecchia M, Rochman D, Ferroukhi H, Caruso S (2019) Preliminary assessment of criticality safety constraints for swiss spent nuclear fuel loading in disposal canisters. Materials 12:494. https://doi.org/10.3390/ma12030494
(2006) Optimization strategies for cask design and container loading in long term spent fuel storage, IAEA technical report TECDOC-1523. IAEA, Vienna, Austria
(2011) Nuclear criticality risks and their prevention in plants and laboratories, IRSN report DSU/SEC/T/2010-334, available here
(2015) Operational and regulatory aspects of criticality safety, OECD nuclear energy agency NEA/CSNI/R(2016)3
Herrero JJ, Vasiliev A, Pecchia M, Rochman D, Ferroukhi H, Jonhson L and Caruso S (2017) Criticality safety assessment for geological disposal of spent fuel using PSI BUCSS-R methodology, NAGRA technical report NAB 17–23
Zerovnik G, Snoj L, Ravnik M (2009) Optimization of spent nuclear fuel filling in canisters for deep repository. Nucl Sci Eng 163:183
Ranta T, Cameron F (2012) Heuristic methods for assigning spent nuclear fuel assemblies to canisters for final disposal. Nucl Sci Eng 171:41
Petersen GM (2016) Algorithms and methods for optimizing the spent nuclear fuel allocation strategy. PhD dissertation, University of Tennessee, TN, USA
Shafaei M, Kisi O (2017) Predicting river daily flow using wavelet-artificial neural networks based on regression analyses in comparison with artificial neural networks and support vector machine models. Neural Comput Applic 28:15. https://doi.org/10.1007/s00521-016-2293-9
Terzi S, Karaşahin M, Gökova S et al (2013) Asphalt concrete stability estimation from non-destructive test methods with artificial neural networks. Neural Comput Appl 23:989. https://doi.org/10.1007/s00521-012-1023-1
Barana O, Manduchi G (2002) Application of neural networks for the measurement of electronic temperature in nuclear fusion experiments. Neural Comput Appl 10:351
Ghalandari M, Ziamolki A, Mosavi A, Shamshirband S, Chau KW, Bornassi S (2019) Aeromechanical optimization of first row compressor test stand blades using a hybrid machine learning model of genetic algorithm, artificial neural networks and design of experiments. Eng Appl Comput Fluid Mech 13(1):892–904. https://doi.org/10.1080/19942060.2019.1649196
Fernandes Feria E, Pereira C (2003) Nuclear fuel loading pattern optimisation using a neural network. Ann Nucl Energy 30:603
Nissan E (2019) An overview of AI methods for in-core fuel management: tools for the automatic design of nuclear reactor core configurations for fuel reload, (re)arranging new and partly spent fuel. Designs 3:37
Gomez-Fernandez M, Higley K, Takuhiro A, Welter K, Wong WK, Yang H (2020) Status of research and development of learning-based approaches in nuclear science and engineering: a review. Nucl Eng Design 359:110479
Solans V, Rochman D, Vasiliev A, Ferroukhi H, Pautz A (2020) Loading optimization for Swiss used nuclear fuel assemblies into final disposal canisters. Nucl Eng Design 370:110897
Leray O, Ferroukhi H, Hursin M, Vasiliev A, Rochman D (2017) Methodology for core analyses with nuclear data uncertainty quantification and application to Swiss PWR operated cycles. Ann Nucl Energy 110:547
Ferroukhi H , Hofer K, Hollard JM, Vasiliev A, Zimmermann MA (2008) Core modelling and analysis of the swiss nuclear power plants for qualified R&D applications. In: Proceedings of international conference on the physics of reactors, PHYSOR’08, September 14–19, Interlaken, Switzerland (CD-ROM,FP239)
Rhodes J, Smith K, Lee D (2006) CASMO-5 development and applications proceedings of the PHYSOR-2006 conference, ANS topical meeting on reactor physics, Vancouver, BC, Canada, September 10–14, Vancouver, BC, Canada, p B144
DiGiovine AS, Rhodes III JD, Smith KS, Ver Planck DM and Umbarger JA (1995) SIMULATE-3 users manual, Studsvik/SOA-95/15 Studsvik
Simeonov T, Wemple C (2017) Update and evaluation of decay data for spent nuclear fuel analyses. EPJ Web Conf 146:09011
Rochman D, Vasiliev A, Ferroukhi H, Pecchia M (2018) Consistent criticality and radiation studies of Swiss spent nuclear fuel: the \(\text{ CS}_2\)M approach. J Hazard Mater 357:384
Rochman D, Vasiliev A, Dokhane A, Ferroukhi H (2018) Uncertainties for Swiss LWR spent nuclear fuels due to nuclear data. EPJ Nucl Sci Technol 4:6
Leppänen J (2015) The Serpent Monte Carlo code: status, development and applications in 2013. Ann Nucl Energy 82:142
Pecchia M, Ferroukhi H, Vasiliev A, Grimm P (2019) Studies of intra-pin power distributions in operated BWR fuel assemblies using MCNP with a cycle check-up methodology. Ann Nucl Energy 129:67
(2017b) MATLAB and deep learning toolbox release, The MathWorks Inc. Natick, Massachusetts, United States
Vlassopoulos E, Volmert B, Pautz A (2017) Logistics optimization code for spent fuel assembly loading into final disposal canisters. Nucl Eng Design 325:246
Koning A, Rochman D (2008) Towards sustainable nuclear energy: putting nuclear physics to work. Ann Nucl Energy 35:2024