Machine learning-based categorization of source terms for risk assessment of nuclear power plants
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 c...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-09-01
|
| Series: | Nuclear Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573322001917 |
| _version_ | 1818495276285952000 |
|---|---|
| author | Kyungho Jin Jaehyun Cho Sung-yeop Kim |
| author_facet | Kyungho Jin Jaehyun Cho Sung-yeop Kim |
| author_sort | Kyungho Jin |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-10T18:18:21Z |
| format | Article |
| id | doaj.art-434c7f84a1334956ab0ffaa5f535d783 |
| institution | Directory Open Access Journal |
| issn | 1738-5733 |
| language | English |
| last_indexed | 2024-12-10T18:18:21Z |
| publishDate | 2022-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj.art-434c7f84a1334956ab0ffaa5f535d7832022-12-22T01:38:16ZengElsevierNuclear Engineering and Technology1738-57332022-09-0154933363346Machine learning-based categorization of source terms for risk assessment of nuclear power plantsKyungho Jin0Jaehyun Cho1Sung-yeop Kim2Korea Atomic Energy Research Institute, (34057) 111, Daedeok-daero 989, Daejeon, Republic of KoreaCorresponding author.; Korea Atomic Energy Research Institute, (34057) 111, Daedeok-daero 989, Daejeon, Republic of KoreaKorea Atomic Energy Research Institute, (34057) 111, Daedeok-daero 989, Daejeon, Republic of KoreaIn 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.http://www.sciencedirect.com/science/article/pii/S1738573322001917Level 2 probabilistic safety assessmentSource term categoryAccident consequenceAutoencoderClustering |
| spellingShingle | Kyungho Jin Jaehyun Cho Sung-yeop Kim Machine learning-based categorization of source terms for risk assessment of nuclear power plants Nuclear Engineering and Technology Level 2 probabilistic safety assessment Source term category Accident consequence Autoencoder Clustering |
| title | Machine learning-based categorization of source terms for risk assessment of nuclear power plants |
| title_full | Machine learning-based categorization of source terms for risk assessment of nuclear power plants |
| title_fullStr | Machine learning-based categorization of source terms for risk assessment of nuclear power plants |
| title_full_unstemmed | Machine learning-based categorization of source terms for risk assessment of nuclear power plants |
| title_short | Machine learning-based categorization of source terms for risk assessment of nuclear power plants |
| title_sort | machine learning based categorization of source terms for risk assessment of nuclear power plants |
| topic | Level 2 probabilistic safety assessment Source term category Accident consequence Autoencoder Clustering |
| url | http://www.sciencedirect.com/science/article/pii/S1738573322001917 |
| work_keys_str_mv | AT kyunghojin machinelearningbasedcategorizationofsourcetermsforriskassessmentofnuclearpowerplants AT jaehyuncho machinelearningbasedcategorizationofsourcetermsforriskassessmentofnuclearpowerplants AT sungyeopkim machinelearningbasedcategorizationofsourcetermsforriskassessmentofnuclearpowerplants |