Role of Machine Learning Principles for Efficient Nuclear Fuel Management and Design

Year : 2025 | Volume : 15 | Issue : 02 | Page : 22 33
    By

    Mangadevi Atti,

  • Yamuna Mundru,

  • Manas Kumar Yogi,

  1. Assistant Professor, Information Technology Department, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India
  2. Assistant Professor, CSE-AI & ML Department, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India
  3. Assistant Professor, CSE Department, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India

Abstract

The introduction of machine learning (ML) and evolutionary computation methods in addressing complex nuclear fuel management challenges has brought a significant positive change in the domain of nuclear fuel management. Key applications include fuel assembly design optimization, core loading pattern determination, burnup calculation acceleration, fuel performance prediction, and spent fuel characterization. The analysis reveals significant improvements in computational efficiency, prediction accuracy, and optimization capabilities when ML techniques are properly integrated into nuclear fuel management workflows. Current challenges include data quality and availability, model validation and verification requirements, regulatory acceptance, and the need for physics-informed approaches. Future directions point toward the development of hybrid physics-ML models, advanced deep learning architectures, and comprehensive digital twins for nuclear fuel systems. The review demonstrates that machine learning principles offer substantial potential for revolutionizing nuclear fuel management practices while maintaining the stringent safety and reliability standards required in the nuclear industry.

Keywords: Nuclear fuel, machine learning, isotopes, storage, fusion, fission

[This article belongs to Journal of Nuclear Engineering & Technology ]

How to cite this article:
Mangadevi Atti, Yamuna Mundru, Manas Kumar Yogi. Role of Machine Learning Principles for Efficient Nuclear Fuel Management and Design. Journal of Nuclear Engineering & Technology. 2025; 15(02):22-33.
How to cite this URL:
Mangadevi Atti, Yamuna Mundru, Manas Kumar Yogi. Role of Machine Learning Principles for Efficient Nuclear Fuel Management and Design. Journal of Nuclear Engineering & Technology. 2025; 15(02):22-33. Available from: https://journals.stmjournals.com/jonet/article=2025/view=213567


References

1. Allah MA, Toor IU, Shams A, Siddiqui OK. Application of machine learning and deep learning techniques for corrosion and cracks detection in nuclear power plants: a review. Arabian Journal for Science and Engineering. 2025 Mar;50(5):3017-45.
2. Seurin P, Shirvan K. Assessment of reinforcement learning algorithms for nuclear power plant fuel optimization. Applied Intelligence. 2024 Jan;54(2):2100-35.
3. Leniau B, Mouginot B, Thiolliere N, Doligez X, Bidaud A, Courtin F, Ernoult M, David S. A neural network approach for burn-up calculation and its application to the dynamic fuel cycle code CLASS. Annals of Nuclear Energy. 2015 Jul 1;81:125-33.
4. Ejigu DA, Tuo Y, Liu X. Application of artificial intelligence technologies and big data computing for nuclear power plants control: a review. Frontiers in Nuclear Engineering. 2024 Feb23;3:1355630.
5. Ebiwonjumi B, Cherezov A, Dzianisau S, Lee D. Machine learning of LWR spent nuclear fuel assembly decay heat measurements. Nuclear Engineering and Technology. 2021 Nov1;53(11):3563-79.
6. Radaideh MI, Wolverton I, Joseph J, Tusar JJ, Otgonbaatar U, Roy N, Forget B, Shirvan K. Physics informed reinforcement learning optimization of nuclear assembly design. Nuclear Engineering and Design. 2021 Feb 1;372:110966.
7. Huang Q, Peng S, Deng J, Zeng H, Zhang Z, Liu Y, Yuan P. A review of the application of artificial intelligence to nuclear reactors: Where we are and what’s next. Heliyon. 2023 Mar 1;9(3).
8. Afzali M, Allaf MA, Jahanfarnia G, Kheradmand M. Optimization and burnup calculations of
BNPP’s reactor core with the new generation fuels (TVS-2M) by artificial neural network. Progress in Nuclear Energy. 2022 Aug 1;150:104290.
9. Bae JW, Rykhlevskii A, Chee G, Huff KD. Deep learning approach to nuclear fuel transmutation in a fuel cycle simulator. Annals of Nuclear Energy. 2020 May 1;139:107230.
10. Rossa R, Borella A. Inferring initial enrichment, burnup, and cooling time of spent fuel assemblies using artificial neural networks. ESARDA Bull.—Int. J. Nucl. Safeguards Non-Prolif. 2021;63:314.
11. Dim O, Soto C, Cui Y, Cheng LY, Gemmill M, Grice T, Rivers J, Stern W, Todosow M.Verification of Triso Fuel Burnup Using Machine Learning Algorithms. Brookhaven National Lab.(BNL), Upton, NY (United States); 2021 Aug 1.
12. Faria EF, Pereira C. Nuclear fuel loading pattern optimisation using a neural network. Annals of Nuclear Energy. 2003 Mar 1;30(5):603-13.
13. Khuwaileh BA, Almomani B. A once-through artificial neural network approach for used nuclear fuel inverse depletion analysis: A comparative study. Annals of Nuclear Energy. 2024 Sep15;205:110598.

Regular Issue Subscription Review Article
Volume 15
Issue 02
Received 29/05/2025
Accepted 30/05/2025
Published 19/06/2025
Publication Time 21 Days
176

Login


My IP

PlumX Metrics