Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants
The correct situation awareness (SA) of operators is important for managing nuclear power plants (NPPs), particularly in accident-related situations. Among the three levels of SA suggested by Ensley, Level 3 SA (i.e., projection of the future status of the situation) is challenging because of the co...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-05-01
|
| Series: | Nuclear Engineering and Technology |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573323000682 |
| _version_ | 1797823788519260160 |
|---|---|
| author | Hyojin Kim Jonghyun Kim |
| author_facet | Hyojin Kim Jonghyun Kim |
| author_sort | Hyojin Kim |
| collection | DOAJ |
| description | The correct situation awareness (SA) of operators is important for managing nuclear power plants (NPPs), particularly in accident-related situations. Among the three levels of SA suggested by Ensley, Level 3 SA (i.e., projection of the future status of the situation) is challenging because of the complexity of NPPs as well as the uncertainty of accidents. Hence, several prediction methods using artificial intelligence techniques have been proposed to assist operators in accident prediction. However, these methods only predict short-term plant status (e.g., the status after a few minutes) and do not provide information regarding the uncertainty associated with the prediction. This paper proposes an algorithm that can predict the multivariate and long-term behavior of plant parameters for 2 h with 120 steps and provide the uncertainty of the prediction. The algorithm applies bidirectional long short-term memory and an attention mechanism, which enable the algorithm to predict the precise long-term trends of the parameters with high prediction accuracy. A conditional variational autoencoder was used to provide uncertainty information about the network prediction. The algorithm was trained, optimized, and validated using a compact nuclear simulator for a Westinghouse 900 MWe NPP. |
| first_indexed | 2024-03-13T10:29:11Z |
| format | Article |
| id | doaj.art-ade43c5ae7d14e8d8fe7f3ef4f525db5 |
| institution | Directory Open Access Journal |
| issn | 1738-5733 |
| language | English |
| last_indexed | 2024-03-13T10:29:11Z |
| publishDate | 2023-05-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Nuclear Engineering and Technology |
| spelling | doaj.art-ade43c5ae7d14e8d8fe7f3ef4f525db52023-05-19T04:45:14ZengElsevierNuclear Engineering and Technology1738-57332023-05-0155516301643Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plantsHyojin Kim0Jonghyun Kim1Department of Nuclear Engineering, Chosun University, 10, Chosundae 1-gil, Dong-gu, Gwangju, Republic of KoreaCorresponding author.; Department of Nuclear Engineering, Chosun University, 10, Chosundae 1-gil, Dong-gu, Gwangju, Republic of KoreaThe correct situation awareness (SA) of operators is important for managing nuclear power plants (NPPs), particularly in accident-related situations. Among the three levels of SA suggested by Ensley, Level 3 SA (i.e., projection of the future status of the situation) is challenging because of the complexity of NPPs as well as the uncertainty of accidents. Hence, several prediction methods using artificial intelligence techniques have been proposed to assist operators in accident prediction. However, these methods only predict short-term plant status (e.g., the status after a few minutes) and do not provide information regarding the uncertainty associated with the prediction. This paper proposes an algorithm that can predict the multivariate and long-term behavior of plant parameters for 2 h with 120 steps and provide the uncertainty of the prediction. The algorithm applies bidirectional long short-term memory and an attention mechanism, which enable the algorithm to predict the precise long-term trends of the parameters with high prediction accuracy. A conditional variational autoencoder was used to provide uncertainty information about the network prediction. The algorithm was trained, optimized, and validated using a compact nuclear simulator for a Westinghouse 900 MWe NPP.http://www.sciencedirect.com/science/article/pii/S1738573323000682Bidirectional long short-term memoryAttention mechanismConditional variational autoencoderLong-term predictionUncertainty estimation |
| spellingShingle | Hyojin Kim Jonghyun Kim Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants Nuclear Engineering and Technology Bidirectional long short-term memory Attention mechanism Conditional variational autoencoder Long-term prediction Uncertainty estimation |
| title | Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants |
| title_full | Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants |
| title_fullStr | Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants |
| title_full_unstemmed | Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants |
| title_short | Long-term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants |
| title_sort | long term prediction of safety parameters with uncertainty estimation in emergency situations at nuclear power plants |
| topic | Bidirectional long short-term memory Attention mechanism Conditional variational autoencoder Long-term prediction Uncertainty estimation |
| url | http://www.sciencedirect.com/science/article/pii/S1738573323000682 |
| work_keys_str_mv | AT hyojinkim longtermpredictionofsafetyparameterswithuncertaintyestimationinemergencysituationsatnuclearpowerplants AT jonghyunkim longtermpredictionofsafetyparameterswithuncertaintyestimationinemergencysituationsatnuclearpowerplants |