Nuclear reactor vessel water level prediction during severe accidents using deep neural networks
Acquiring instrumentation signals generated from nuclear power plants (NPPs) is essential to maintain nuclear reactor integrity or to mitigate an abnormal state under normal operating conditions or severe accident circumstances. However, various safety-critical instrumentation signals from NPPs cann...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2019-06-01
|
| Series: | Nuclear Engineering and Technology |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573318307861 |
| _version_ | 1819077911364239360 |
|---|---|
| author | Young Do Koo Ye Ji An Chang-Hwoi Kim Man Gyun Na |
| author_facet | Young Do Koo Ye Ji An Chang-Hwoi Kim Man Gyun Na |
| author_sort | Young Do Koo |
| collection | DOAJ |
| description | Acquiring instrumentation signals generated from nuclear power plants (NPPs) is essential to maintain nuclear reactor integrity or to mitigate an abnormal state under normal operating conditions or severe accident circumstances. However, various safety-critical instrumentation signals from NPPs cannot be accurately measured on account of instrument degradation or failure under severe accident circumstances. Reactor vessel (RV) water level, which is an accident monitoring variable directly related to reactor cooling and prevention of core exposure, was predicted by applying a few signals to deep neural networks (DNNs) during severe accidents in NPPs. Signal data were obtained by simulating the postulated loss-of-coolant accidents at hot- and cold-legs, and steam generator tube rupture using modular accident analysis program code as actual NPP accidents rarely happen. To optimize the DNN model for RV water level prediction, a genetic algorithm was used to select the numbers of hidden layers and nodes. The proposed DNN model had a small root mean square error for RV water level prediction, and performed better than the cascaded fuzzy neural network model of the previous study. Consequently, the DNN model is considered to perform well enough to provide supporting information on the RV water level to operators. Keywords: Deep neural networks, Genetic algorithm, Reactor vessel water level, Safety-critical instrumentation signals, Severe accident |
| first_indexed | 2024-12-21T19:04:43Z |
| format | Article |
| id | doaj.art-6551099d838649818fa727e4e314154a |
| institution | Directory Open Access Journal |
| issn | 1738-5733 |
| language | English |
| last_indexed | 2024-12-21T19:04:43Z |
| publishDate | 2019-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj.art-6551099d838649818fa727e4e314154a2022-12-21T18:53:23ZengElsevierNuclear Engineering and Technology1738-57332019-06-01513723730Nuclear reactor vessel water level prediction during severe accidents using deep neural networksYoung Do Koo0Ye Ji An1Chang-Hwoi Kim2Man Gyun Na3Department of Nuclear Engineering, Chosun University, 309 Pilmun-daero, Dong-gu, Gwangju, 61452, Republic of KoreaDepartment of Nuclear Engineering, Chosun University, 309 Pilmun-daero, Dong-gu, Gwangju, 61452, Republic of KoreaNuclear ICT Research Division, Korea Atomic Energy Research Institute, 989-111 Daedeok-daero Yuseong-gu, Daejeon, 34039, Republic of KoreaDepartment of Nuclear Engineering, Chosun University, 309 Pilmun-daero, Dong-gu, Gwangju, 61452, Republic of Korea; Corresponding author. Department of Nuclear Engineering, Chosun University, 309 Pilmun-daero, Dong-gu, Gwangju, 61452, Republic of Korea.Acquiring instrumentation signals generated from nuclear power plants (NPPs) is essential to maintain nuclear reactor integrity or to mitigate an abnormal state under normal operating conditions or severe accident circumstances. However, various safety-critical instrumentation signals from NPPs cannot be accurately measured on account of instrument degradation or failure under severe accident circumstances. Reactor vessel (RV) water level, which is an accident monitoring variable directly related to reactor cooling and prevention of core exposure, was predicted by applying a few signals to deep neural networks (DNNs) during severe accidents in NPPs. Signal data were obtained by simulating the postulated loss-of-coolant accidents at hot- and cold-legs, and steam generator tube rupture using modular accident analysis program code as actual NPP accidents rarely happen. To optimize the DNN model for RV water level prediction, a genetic algorithm was used to select the numbers of hidden layers and nodes. The proposed DNN model had a small root mean square error for RV water level prediction, and performed better than the cascaded fuzzy neural network model of the previous study. Consequently, the DNN model is considered to perform well enough to provide supporting information on the RV water level to operators. Keywords: Deep neural networks, Genetic algorithm, Reactor vessel water level, Safety-critical instrumentation signals, Severe accidenthttp://www.sciencedirect.com/science/article/pii/S1738573318307861 |
| spellingShingle | Young Do Koo Ye Ji An Chang-Hwoi Kim Man Gyun Na Nuclear reactor vessel water level prediction during severe accidents using deep neural networks Nuclear Engineering and Technology |
| title | Nuclear reactor vessel water level prediction during severe accidents using deep neural networks |
| title_full | Nuclear reactor vessel water level prediction during severe accidents using deep neural networks |
| title_fullStr | Nuclear reactor vessel water level prediction during severe accidents using deep neural networks |
| title_full_unstemmed | Nuclear reactor vessel water level prediction during severe accidents using deep neural networks |
| title_short | Nuclear reactor vessel water level prediction during severe accidents using deep neural networks |
| title_sort | nuclear reactor vessel water level prediction during severe accidents using deep neural networks |
| url | http://www.sciencedirect.com/science/article/pii/S1738573318307861 |
| work_keys_str_mv | AT youngdokoo nuclearreactorvesselwaterlevelpredictionduringsevereaccidentsusingdeepneuralnetworks AT yejian nuclearreactorvesselwaterlevelpredictionduringsevereaccidentsusingdeepneuralnetworks AT changhwoikim nuclearreactorvesselwaterlevelpredictionduringsevereaccidentsusingdeepneuralnetworks AT mangyunna nuclearreactorvesselwaterlevelpredictionduringsevereaccidentsusingdeepneuralnetworks |