Machine learning-based categorization of source terms for risk assessment of nuclear power plants
2
조회
0
다운로드
3
인용
0
참고문헌
키워드
초록
In general, a number of severe accident scenarios derived from Level 2 probabilistic safety assessment (PSA) are typically grouped into several categories to efficiently evaluate their potential impacts on the public with the assumption that scenarios within the same group have similar source term characteristics. To date, however, grouping by similar source terms has been completely reliant on qualitative methods such as logical trees or expert judgements. Recently, an exhaustive simulation approach has been developed to provide quantitative information on the source terms of a large number of severe accident scenarios. With this motivation, this paper proposes a machine learning-based categorization method based on exhaustive simulation for grouping scenarios with similar accident consequences. The proposed method employs clustering with an autoencoder for grouping unlabeled scenarios after dimensionality reductions and feature extractions from the source term data. To validate the suggested method, source term data for 658 severe accident scenarios were used. Results confirmed that the proposed method successfully characterized the severe accident scenarios with similar behavior more precisely than the conventional grouping method
Abstract
In general, a number of severe accident scenarios derived from Level 2 probabilistic safety assessment (PSA) are typically grouped into several categories to efficiently evaluate their potential impacts on the public with the assumption that scenarios within the same group have similar source term characteristics. To date, however, grouping by similar source terms has been completely reliant on qualitative methods such as logical trees or expert judgements. Recently, an exhaustive simulation approach has been developed to provide quantitative information on the source terms of a large number of severe accident scenarios. With this motivation, this paper proposes a machine learning-based categorization method based on exhaustive simulation for grouping scenarios with similar accident consequences. The proposed method employs clustering with an autoencoder for grouping unlabeled scenarios after dimensionality reductions and feature extractions from the source term data. To validate the suggested method, source term data for 658 severe accident scenarios were used. Results confirmed that the proposed method successfully characterized the severe accident scenarios with similar behavior more precisely than the conventional grouping method
참고문헌 (28)
- S. Kaplan, "On the quantitative definition of risk", Risk Anal, 1 (1981)
- CSNI Technical Opinion Papers No. 9 Level-2 PSA for Nuclear Power Plants, "OECD-NEA", ~ (2007)
- IAEA, "Applications of Probabilistic Safety Assessment (PSA) for Nuclear Power Plants", IAEA-TECDOC-1200, ~ (2001)
- EPRI, "PSA Applications Guide", EPRI TR-105396s, ~ (1995)
- U. S. NRC, "Severe Accident Risks: an Assessment for Five U.S. Nuclear Power Plants, NUREG-1150", ~ (1990)
- 조재현, "Multi-unit Level 2 probabilistic safety assessment: Approaches and their application to a six-unit nuclear power plant site", Nuclear Engineering and Technology, 50(8), pp.1234~1245 (2018), 한국원자력학회
- J. Cho, "Exhaustive simulation approach for severe accident scenarios", Transactions of the Korean Nuclear Society Virtual Autumn Meeting (2021)
- EPRI, "Modular Accident Analysis Program (MAAP) Version 5.03 - Windows" (2014), Fauske & Associates, Inc.
- J. A. Hartigan, "Clustering Algorithms" (1975), Wiley
- A. Geron, "Hands-On Machine Learning with Scikit-Learn, Keras, and Tensor-Flow: Concepts, Tools, and Techniques to Build Intelligent Systems" (2019), O'Rreilly Media
- G. E. Hinton, "Reducing the dimensionality of data with neural networks", Science, 313, pp.504~507 (2006)[DOI]
- P. Vincent, "Stacked denoising autoencoders : learning useful representations in a deep network with a local denoising criterion", J. Mach. Learn. Res, 11, pp.3371~3408 (2010)
- D. P. Kingma, "An introduction to variational autoencoders", Found. Trends Mach. Learn, 12, pp.307~392 (2019)[DOI]
- IAEA, "Development and Application of Level 2 Probabilistic Safety Assessment for Nuclear Power Plants (Specific Safety Guide, No. SSG-4)", ~ (2010)
- Nathan E. Bixler, "Performing a multi-unit level-3 PSA with MACCS", Nuclear Engineering and Technology, 53(2), pp.386~392 (2021), 한국원자력학회[DOI]
- S. -Y. Kim, "Development of MUST (Multi-Unit source term) converter version 1.0", Transactions of the Korean Nuclear Society Virtual Autumn Meeting (2021)
- S. -Y. Kim, "Development of Mr. (Multi-run) manager version 1.0", Transactions of the Korean Nuclear Society Virtual Autumn Meeting (2021)
- A. Kianimajd, "Comparison of different methods of measuring similarity in physiologic time series", IFAC-PapersOnLine, 50, pp.11005~11010 (2017)[DOI]
- H. Zhang, "Unsupervised feature extraction for time series clustering using orthogonal wavelet transform", Informatica, 30, pp.305~319 (2006)
- C. M. Bishop, "Pattern Recognition and Machine Learning" (2011), Springer
- P. Rujasiri, "Comparison of clustering techniques for cluster Analysis", Kasetsart J-Nat. Sci, 43, pp.378~388 (2009)
- R. Gelbard, "Investigating diversity of clustering methods : an empirical comparison", Data Knowl. Eng, 63, pp.155~166 (2007)[DOI]
- G. Brock, "clValid , an R package for cluster validation", J. Stat. Software (2008)
- P. J. Rousseeuw, "Silhouettes : a graphical aid to the interpretation and validation of cluster analysis", J. Comput. Appl. Math, 20, pp.53~65 (1987)
- 김동산, "Multi-unit Level 1 probabilistic safety assessment: Approaches and their application to a six-unit nuclear power plant site", Nuclear Engineering and Technology, 50(8), pp.1217~1233 (2018), 한국원자력학회
- Jaehyun Cho, "Identification of Risk-Significant Components in Nuclear Power Plants to Reduce Cs-137 Radioactive Risk", Reliability Engineering & System Safety, 211, pp.107613~ (2021), Elsevier BV[DOI]
- J. Leute, "MACCS (MELCOR Accident Consequence Code System) User Guide-Version 4.0", ~ (2021)
- State-of-the-Art Reactor Consequence Analyses (SOARCA) Report (NUREG-1935), "U.S.NRC", ~ (2021)