본문 바로가기
KERD
논문KCI 등재

Using machine learning to forecast and assess the uncertainty in the response of a typical PWR undergoing a steam generator tube rupture accident

Diab Aya|Nguyen Tran Canh Hai
한국원자력학회 (Korean Nuclear Society)|2023.09|Nuclear Engineering and Technology|제55권 제9호|pp. 3423-3440|DOI 10.1016/j.net.2023.05.025

2

조회

0

다운로드

1

인용

0

참고문헌

키워드

Machine learningConvolutional neural networkRecurrent neural networkGated recurrent unitLong short-term memory(RNN)(LSTM)(GRU)(CNN)(BNN)Bayesian neural network(ML)(BEPU)Best estimate plus uncertainty(SGTR)Steam generator tube rupture
주제분류원자력공학

초록

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error

Abstract

In this work, a multivariate time-series machine learning meta-model is developed to predict the transient response of a typical nuclear power plant (NPP) undergoing a steam generator tube rupture (SGTR). The model employs Recurrent Neural Networks (RNNs), including the Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and a hybrid CNN-LSTM model. To address the uncertainty inherent in such predictions, a Bayesian Neural Network (BNN) was implemented. The models were trained using a database generated by the Best Estimate Plus Uncertainty (BEPU) methodology; coupling the thermal hydraulics code, RELAP5/SCDAP/MOD3.4 to the statistical tool, DAKOTA, to predict the variation in system response under various operational and phenomenological uncertainties. The RNN models successfully captures the underlying characteristics of the data with reasonable accuracy, and the BNN-LSTM approach offers an additional layer of insight into the level of uncertainty associated with the predictions. The results demonstrate that LSTM outperforms GRU, while the hybrid CNN-LSTM model is computationally the most efficient. This study aims to gain a better understanding of the capabilities and limitations of machine learning models in the context of nuclear safety. By expanding the application of ML models to more severe accident scenarios, where operators are under extreme stress and prone to errors, ML models can provide valuable support and act as expert systems to assist in decision-making while minimizing the chances of human error

참고문헌 (94)

  1. Yeonju Jang, "Social acceptance of nuclear power plants in Korea: The role of public perceptions following the Fukushima accident", Renewable and Sustainable Energy Reviews, 128, pp.109894~ (2020), Elsevier BV[DOI]
  2. H. Zhang, "Multi-Physics Best Estimate Plus Uncertainty (MP-BEPU) Analysis Framework LOTUS and RELAP5-3", IRUG Meeting (2018)
  3. Maria Avramova, "Innovations in Multi-Physics Methods Development, Validation, and Uncertainty Quantification", Journal of Nuclear Engineering, 2(1), pp.44~56 (2021), MDPI AG[DOI]
  4. Development of a Phenomena Identification and Ranking Table for Thermal Hydraulic Phenomena during PWR LBLOCA, "USNRC", United States Nuclear Regulatory Commission, ~ (1988)
  5. Jinzhao Zhang, "Application of the <u>W<", u>COBRA, Nuclear Engineering, pp.1997[DOI]
  6. Ye Yang, "Simulation and uncertainty analysis of main steam line break accident on an integral test facility", Annals of Nuclear Energy, 144, pp.107565~ (2020), Elsevier BV[DOI]
  7. Dabin Sun, "An Improved Best Estimate Plus Uncertainty Method for Small-Break Loss-of-Coolant Accident in Pressurized Water Reactor", Frontiers in Energy Research, 8 (2020), Frontiers Media SA[DOI]
  8. Olivier Marchand, "Uncertainty and sensitivity analysis in reactivity-initiated accident fuel modeling: synthesis of organisation for economic co-operation and development (OECD)", nuclear energy agency (NEA) benchmark on reactivity-initiated accident codes phase-II, 2018, pp.50(2), 280~291[DOI]
  9. E. Castro, "Thermal-hydraulic Uncertainty Propagation in a Main Steam Line Break Scenario", PHYSOR (2016)
  10. Ye Yang, "Best estimate plus uncertainty analysis of a smallbreak LOCA on an advanced generation-III pressurized water reactor", International Journal of Energy Research, 45(8), pp.11916~11929 (2020), Hindawi Limited[DOI]
  11. J. de Sousa, "Best Estimate Plus Uncertainty Analysis for SBO", Transactions of the American Nuclear Society, 121 (2019), AMNS[DOI]
  12. R. Bocanegra Melian, "Towards a BEPU Methodology for Containment Safety Analyses", PhD, pp.2016
  13. C. Queral, "AP1000® Large-Break LOCA BEPU analysis with TRACE code", Annals of Nuclear Energy, 85, pp.576~589 (2015), Elsevier BV[DOI]
  14. Jun Yang, "Best Estimate Plus Uncertainty analysis of a large break LOCA on Generation III reactor with RELAP5", Annals of Nuclear Energy, 127, pp.326~340 (2019), Elsevier BV[DOI]
  15. Eneko Zugazagoitia, "Uncertainty and sensitivity analysis of a PWR LOCA sequence using parametric and non-parametric methods", Reliability Engineering &amp; System Safety, 193, pp.106607~ (2020), Elsevier BV[DOI]
  16. Yourak Choi, "Deep‐learning‐based nuclear power plant fault detection using remote light‐emitting diode array data transmission", Microwave and Optical Technology Letters, 63(12), pp.2909~2915 (2021), Wiley[DOI]
  17. Guang Hu, "Data-Driven Machine Learning for Fault Detection and Diagnosis in Nuclear Power Plants: A Review", Frontiers in Energy Research, 9 (2021), Frontiers Media SA[DOI]
  18. Mario Gomez-Fernandez, "Status of research and development of learning-based approaches in nuclear science and engineering: A review", Nuclear Engineering and Design, 359, pp.110479~ (2020), Elsevier BV[DOI]
  19. Antonios Papaoikonomou, "Deep learning techniques for in-core perturbation identification and localization of time-series nuclear plant measurements", Annals of Nuclear Energy, 178, pp.109373~ (2022), Elsevier BV[DOI]
  20. Francesco Caliva, "A Deep Learning Approach to Anomaly Detection in Nuclear Reactors", 2018 International Joint Conference on Neural Networks (IJCNN) (2018), IEEE
  21. Chandresh Kumar Maurya, "Anomaly detection in nuclear power plant data using support vector data description", Proceedings of the 2014 IEEE Students' Technology Symposium (2014), IEEE
  22. Mario Gomez-Fernandez, "Isotope identification using deep learning: An explanation", Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 988, pp.164925~ (2021), Elsevier BV[DOI]
  23. 박순호, "Prediction of the Reactor Vessel Water Level Using Fuzzy Neural Networks in Severe Accident Circumstances of NPPs", Nuclear Engineering and Technology, 46(3), pp.373~380 (2014), 한국원자력학회
  24. Hae Min Park, "Wall temperature prediction at critical heat flux using a machine learning model", Annals of Nuclear Energy, 141, pp.107334~ (2020), Elsevier BV[DOI]
  25. Wazif Sallehhudin, "Using Machine Learning to Predict the Fuel Peak Cladding Temperature for a Large Break Loss of Coolant Accident", Frontiers in Energy Research, 9 (2021), Frontiers Media SA[DOI]
  26. S. Lee, "Preliminary Prediction of Core Exit Temperature for Severe Accident Using Machine Learning", Transactions of the Korean Nuclear Society Virtual Spring Meeting (2021)
  27. Naseem Ali, "Data-driven machine learning for accurate prediction and statistical quantification of two phase flow regimes", Journal of Petroleum Science and Engineering, 202, pp.108488~ (2021), Elsevier BV[DOI]
  28. M.G. Na, "Prediction of Major Transient Scenarios for Severe Accidents of Nuclear Power Plants", IEEE Transactions on Nuclear Science, 51(2), pp.313~321 (2004), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  29. Chang-Ju Lee, "Application of Bayesian network to the probabilistic risk assessment of nuclear waste disposal", Reliability Engineering &amp; System Safety, 91(5), pp.515~532 (2006), Elsevier BV[DOI]
  30. Y. D. Koo, "Identification of Initial Events in Nuclear Power Plants Using Machine Learning Methods", Transactions of the Korean Nuclear Society Virtual Spring Meeting (2020)
  31. Majdi I. Radaideh, "Neural-based time series forecasting of loss of coolant accidents in nuclear power plants", Expert Systems with Applications, 160, pp.113699~ (2020), Elsevier BV[DOI]
  32. "Steam Generator Tube Rupture Scenarios - Europa" (2000)[URL]
  33. Z. Koszela, "Thermal-hydraulic analysis of single and multiple steam generator tube ruptures in a typical 3-loop PWR", J. Power Technol, 95(3) (2015)
  34. 방정진, "Analysis of Steam Generator Tube Rupture Accidents for the Development of Mitigation Strategies", Nuclear Engineering and Technology, 54(1), pp.152~161 (2022), 한국원자력학회[DOI]
  35. RELAP, "SDAPSIM", MOD3.x User Reference Manual - Volume I - Advanced Fluid Systems Thermal Hydraulics Analysis, Innovative Systems Software LLC, pp.2020, ~
  36. IAEA, "Best Estimate Safety Analysis for Nuclear Power Plants: Uncertainty Evaluation" (2008), IAEA
  37. Andrej Prošek, "The State-of-the-Art Theory and Applications of Best-Estimate Plus Uncertainty Methods", Nuclear Technology, 158(1), pp.69~79 (2007), Informa UK Limited[DOI]
  38. Gary E. Wilson, "The role of the PIRT process in experiments, code development and code applications associated with reactor safety analysis", Nuclear Engineering and Design, 186(1-2), pp.23~37 (1998), Elsevier BV[DOI]
  39. Dakota, a Multilevel Parallel Object-Oriented Framework for Design Optimization, Parameter Estimation, Uncertainty Quantification, and Sensitivity Analysis: Version 6.15 User's Manual, "B. Adams", ~ (2021)
  40. Phenomena Identification and Ranking Tables for Westinghouse AP600 Small Break Loss-Of-Coolant Accident, Main Steam Line Break, and Steam Generator Tube Rupture Scenarios, "G. E. Wilson", ~ (1997)
  41. S. H. Ahn, "Phenomena Identification and Rankings in Domestic PWR Accident Conditions", Transaction of the Korea Nuclear Society, Spring Meeting (2008)
  42. B. -S. Youn, "Development the DEC PIRT for APR1400MSGTR", Transactions of the Korean Nuclear Society Spring Meeting (2017)
  43. Horst Glaeser, "GRS Method for Uncertainty and Sensitivity Evaluation of Code Results and Applications", Science and Technology of Nuclear Installations, 2008, pp.1~7 (2008), Hindawi Limited[DOI]
  44. L. Sabotinov, "Primary LOCA in VVER-1000 by pressurizer PORV failure", BNS International Conference Nuclear Energy in Europe-Present and Future (2013)
  45. M. Marques, "Best estimate plus uncertainty: safety studies at the conceptual design phase of the ASTRID demonstrator", Joint International Conference on Supercomputng in Nuclear Applications + Monte Carlo (2013)
  46. Dong Gu Kang, "Analysis of LBLOCA using best estimate plus uncertainties for three-loop nuclear power plant power uprate", Annals of Nuclear Energy, 90, pp.318~330 (2016), Elsevier BV[DOI]
  47. 이성욱, "Analysis of Uncertainty Quantification Method by Comparing Monte-Carlo Method and Wilks' Formula", Nuclear Engineering and Technology, 46(4), pp.481~488 (2014), 한국원자력학회
  48. Simen Akkermans, "A tutorial on uncertainty propagation techniques for predictive microbiology models: A critical analysis of state-of-the-art techniques", International Journal of Food Microbiology, 282, pp.1~8 (2018), Elsevier BV[DOI]
  49. D.A. Fynan, "Uncertainty Quantification for Reactor Safety Analysis", PhD, pp.2014
  50. A. de Crécy, "Uncertainty and sensitivity analysis of the LOFT L2-5 test: Results of the BEMUSE programme", Nuclear Engineering and Design, 238(12), pp.3561~3578 (2008), Elsevier BV[DOI]
  51. Attila Guba, "Statistical aspects of best estimate method—I", Reliability Engineering &amp; System Safety, 80(3), pp.217~232 (2003), Elsevier BV[DOI]
  52. M. D. McKay, "A Comparison of Three Methods for Selecting Values of Input Variables in the Analysis of Output from a Computer Code", Technometrics, 21(2), pp.239~ (1979), JSTOR[DOI]
  53. USNRC Regulatory Guide 1.157, Best Estimate Calculation of Emergency Core Cooling System Performance, "USNRC", U.S Office of Nuclear Regulatory Research, ~ (1989)
  54. S. S. Wilks, "Determination of Sample Sizes for Setting Tolerance Limits", The Annals of Mathematical Statistics, 12(1), pp.91~96 (1941), Institute of Mathematical Statistics[DOI]
  55. Sima Siami-Namini, "A Comparison of ARIMA and LSTM in Forecasting Time Series", 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) (2018), IEEE
  56. P.J. Werbos, "Backpropagation through time: what it does and how to do it", Proceedings of the IEEE, 78(10), pp.1550~1560 (1990), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  57. A.F. Agarap, "Deep Learning Using Rectified Linear Units (ReLU)", ArXiv, ~ (2018)
  58. Sepp Hochreiter, "Long Short-Term Memory", Neural Computation, 9(8), pp.1735~1780 (1997), MIT Press - Journals[DOI]
  59. Kyunghyun Cho, "On the Properties of Neural Machine Translation: Encoder–Decoder Approaches", Proceedings of SSST-8, Eighth Workshop on Syntax, Semantics and Structure in Statistical Translation (2014), Association for Computational Linguistics
  60. Yann LeCun, "Deep learning", Nature, 521(7553), pp.436~444 (2015), Springer Science and Business Media LLC[DOI]
  61. Tara N. Sainath, "Convolutional, Long Short-Term Memory, fully connected Deep Neural Networks", 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2015), IEEE
  62. Wenjie Lu, "A CNN-LSTM-Based Model to Forecast Stock Prices", Complexity, 2020, pp.1~10 (2020), Hindawi Limited[DOI]
  63. Lei Ji, "Carbon futures price forecasting based with ARIMA-CNN-LSTM model", Procedia Computer Science, 162, pp.33~38 (2019), Elsevier BV[DOI]
  64. Ioannis E. Livieris, "A CNN–LSTM model for gold price time-series forecasting", Neural Computing and Applications, 32(23), pp.17351~17360 (2020), Springer Science and Business Media LLC[DOI]
  65. P. K. Gabriel, "On the application of multivariate times series models", J. Phys. Sci. Technol, 8(10), pp.51~62 (2015)
  66. Johann du Preez, "Univariate versus multivariate time series forecasting: an application to international tourism demand", International Journal of Forecasting, 19(3), pp.435~451 (2003), Elsevier BV[DOI]
  67. (2020)[URL]
  68. "How To Get Reproducible Results with Keras" (2019)[URL]
  69. Moloud Abdar, "A review of uncertainty quantification in deep learning: Techniques, applications and challenges", Information Fusion, 76, pp.243~297 (2021), Elsevier BV[DOI]
  70. Laurent Valentin Jospin, "Hands-On Bayesian Neural Networks—A Tutorial for Deep Learning Users", IEEE Computational Intelligence Magazine, 17(2), pp.29~48 (2022), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  71. Y. Gal, "Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning" (2016)
  72. F. D'Auria, "State of the art in using best estimate calculation tools in nuclear technology", Nucl. Eng. Technol, 38 (2006)
  73. Stéfan van der Walt, "The NumPy Array: A Structure for Efficient Numerical Computation", Computing in Science &amp; Engineering, 13(2), pp.22~30 (2011), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  74. Yagmur Gizem Cinar, "Period-aware content attention RNNs for time series forecasting with missing values", Neurocomputing, 312, pp.177~186 (2018), Elsevier BV[DOI]
  75. Fu-Chen Chen, "NB-CNN: Deep Learning-Based Crack Detection Using Convolutional Neural Network and Naïve Bayes Data Fusion", IEEE Transactions on Industrial Electronics, 65(5), pp.4392~4400 (2018), Institute of Electrical and Electronics Engineers (IEEE)[DOI]
  76. Emerging Technologies Workshop: Insight and Actionable Ideas for Key Safeguards Challenge, "IAEA", International Atomic Energy Agency, ~ (2020)
  77. Sung Il Kim, "Analysis of steam generator tube rupture accident for OPR 1000 nuclear power plant", Nuclear Engineering and Design, 382, pp.111403~ (2021), Elsevier BV[DOI]
  78. Sung Il Kim, "Evaluation of aerosol retention inside a steam generator under steam generator tube rupture accident conditions", Nuclear Engineering and Design, 396, pp.111899~ (2022), Elsevier BV[DOI]
  79. Youho Lee, "Improving safety margin of LWRs by rethinking the emergency core cooling system criteria and safety system capacity", Nuclear Engineering and Design, 307, pp.402~410 (2016), Elsevier BV[DOI]
  80. 이병희, "Separate and integral effect tests of aerosol retention in steam generator during tube rupture accident", Nuclear Engineering and Technology, 54(7), pp.2702~2713 (2022), 한국원자력학회[DOI]
  81. T. Lind, "A summary of fission-product-transport phenomena during SGTR severe accidents", Nuclear Engineering and Design, 363, pp.110635~ (2020), Elsevier BV[DOI]
  82. Robert P. Martin, "AREVA's realistic large break LOCA analysis methodology", Nuclear Engineering and Design, 235(16), pp.1713~1725 (2005), Elsevier BV[DOI]
  83. Piotr Mazgaj, "Demonstration of the E-BEPU methodology for SL-LOCA in a Gen-III PWR reactor", Reliability Engineering &amp; System Safety, 226, pp.108707~ (2022), Elsevier BV[DOI]
  84. S.Gopal Krishna Patro, "Normalization: A Preprocessing Stage", IARJSET, pp.20~22 (2015), Tejass Publishers[DOI]
  85. P. Razvan, "On the Difficulty of Training Recurrent Neural Networks", International Conference on Machine Learning (2013)
  86. Salama Alketbi, "Using artificial intelligence to identify the success window of FLEX strategy under an extended station blackout", Nuclear Engineering and Design, 382, pp.111368~ (2021), Elsevier BV[DOI]
  87. Kun Zhou, "Comparison of Time Series Forecasting Based on Statistical ARIMA Model and LSTM with Attention Mechanism", Journal of Physics: Conference Series, 1631(1), pp.012141~ (2020), IOP Publishing[DOI]
  88. Siniša Šadek, "Uncertainty Study of the In-Vessel Phase of a Severe Accident in a Pressurized Water Reactor", Energies, 15(5), pp.1842~ (2022), MDPI AG[DOI]
  89. B.E. Boyack, "Quantifying reactor safety margins part 1: An overview of the code scaling, applicability, and uncertainty evaluation methodology", Nuclear Engineering and Design, 119(1), pp.1~15 (1990), Elsevier BV[DOI]
  90. JinHo Song, "An analysis on the steam generator tube rupture events with core damage", Annals of Nuclear Energy, 150, pp.107877~ (2021), Elsevier BV[DOI]
  91. Zixiao Yang, "Nuclear power plant sensor signal reconstruction based on deep learning methods", Annals of Nuclear Energy, 167, pp.108765~ (2022), Elsevier BV[DOI]
  92. Diederik P. Kingma, "Adam: A Method for Stochastic Optimization", The 3rd International Conference for Learning Representations (2015)
  93. C. S. Lee, "Best Estimate Evaluation of Steam Line Break Accident Using Uncertainty Quantification Method", Proceedings of the Korean Nuclear Society Autumn Meeting Yongpyong (2003)
  94. Design Control Document Chapter 15: Transient and Accident Analysis, "Korea Electric Power Corporation", ~, pp.APR1400-K-X-FS-14002-NP (2018)

관련 논문AI추천

A machine learning informed prediction of severe accident progressions in nuclear power plants김성중, 송진호한국원자력학회 · Nuclear Engineering and Technology2024 · 제56권 제6호A simple accident management support tool based on source-term category using RNN-LSTM김성중, 최원준한국원자력학회 · Nuclear Engineering and Technology2025 · 제57권 제10호RNN-based integrated system for real-time sensor fault detection and fault-informed accident diagnosis in nuclear power plant accidents이승준, 최정훈한국원자력학회 · Nuclear Engineering and Technology2023 · 제55권 제3호Physics informed neural networks for surrogate modeling of accidental scenarios in nuclear power plantsAntonello Federico, Buongiorno Jacopo, Zio Enrico한국원자력학회 · Nuclear Engineering and Technology2023 · 제55권 제9호Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants김종현, 김효진한국원자력학회 · Nuclear Engineering and Technology2023 · 제55권 제5호A recurrent neural network for modeling natural circulation density wave instabilitiesDuarte Juliana Pacheco, Hurley Paul한국원자력학회 · Nuclear Engineering and Technology2025 · 제57권 제6호

이 간행물의 다른 논문 (39건)

Structural and component characterization of the B4C neutron conversion layer deposited by magnetron sputteringZhu Jingtao, Cui Mingqi, Zhu Hangyu, Yang Zehua, Sun Zhijia, Zhou Xiaojuan, Tan Jinhao, Zhou Jianrong, Liu Yangpp. 3121-3125Research of aluminum nitride water load for the 4.6 GHz 500 kW LHCD system of the CFETRLi Dingzhen, Zhou Taian, Cheng Min, Zhao Lianmin, Zhang Liyuan, Hu Huaichuan, Liu Fukunpp. 3126-3132Simulation of a neutron imaging detector prototype based on SiPM array readoutTang Mengjiao, Zhang Lianjun, He Gaokui, Huang Chang, Zhao Jiangbin, Liu Yang, Tang Binpp. 3133-3139Tackling range uncertainty in proton therapy: Development and evaluation of a new multi-slit prompt-gamma camera (MSPGC) system김성훈, 조성구, 김찬형, 장세현, 조재호, 최세훈, 정종휘, 구영모pp. 3140-3149An intelligent optimization method for the HCSB blanket based on an improved multi-objective NSGA-III algorithm and an adaptive BP neural networkZhang Di, Yang Zihui, Miwa Shuichiro, Sun Guomin, Zhou Wen, Wang Jianye, Li Zhuangpp. 3150-3163
원문 보기