AI-Assisted Forecasting of a Mitigated Multiple Steam Generator Tube Rupture Scenario in a Typical Nuclear Power Plant
This study is focused on developing a machine learning (ML) meta-model to predict the progression of a multiple steam generator tube rupture (MSGTR) accident in the APR1400 reactor. The accident was simulated using the thermal–hydraulic code RELAP5/SCDAPSIM/MOD3.4. The model incorporates a mitigatio...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/18/2/250 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588620819595264 |
|---|---|
| author | Sonia Spisak Aya Diab |
| author_facet | Sonia Spisak Aya Diab |
| author_sort | Sonia Spisak |
| collection | DOAJ |
| description | This study is focused on developing a machine learning (ML) meta-model to predict the progression of a multiple steam generator tube rupture (MSGTR) accident in the APR1400 reactor. The accident was simulated using the thermal–hydraulic code RELAP5/SCDAPSIM/MOD3.4. The model incorporates a mitigation strategy executed through operator interventions. Following this, uncertainty quantification employing the Best Estimate Plus Uncertainty (BEPU) methodology was undertaken by coupling RELAP5/SCDAPSIM/MOD3.4 with the statistical software, DAKOTA 6.14.0. The analysis concentrated on critical safety parameters, including Reactor Coolant System (RCS) pressure and temperature, as well as reactor vessel upper head (RVUH) void fraction. These simulations generated a comprehensive dataset, which served as the foundation for training three ML architectures: Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Convolutional LSTM (CNN+LSTM). Among these models, the CNN+LSTM hybrid configuration demonstrated superior performance, excelling in both predictive accuracy and computational efficiency. To bolster the model’s transparency and interpretability, Integrated Gradients (IGs)—an advanced Explainable AI (XAI) technique—was applied, elucidating the contribution of input features to the model’s predictions and enhancing its trustworthiness. |
| format | Article |
| id | doaj-art-524e21a432fd426092beacdf07e2ff80 |
| institution | Kabale University |
| issn | 1996-1073 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj-art-524e21a432fd426092beacdf07e2ff802025-01-24T13:30:47ZengMDPI AGEnergies1996-10732025-01-0118225010.3390/en18020250AI-Assisted Forecasting of a Mitigated Multiple Steam Generator Tube Rupture Scenario in a Typical Nuclear Power PlantSonia Spisak0Aya Diab1Department of Nuclear Power Plant Engineering, KEPCO International Nuclear Graduate School, Ulsan 45014, Republic of KoreaDepartment of Nuclear Power Plant Engineering, KEPCO International Nuclear Graduate School, Ulsan 45014, Republic of KoreaThis study is focused on developing a machine learning (ML) meta-model to predict the progression of a multiple steam generator tube rupture (MSGTR) accident in the APR1400 reactor. The accident was simulated using the thermal–hydraulic code RELAP5/SCDAPSIM/MOD3.4. The model incorporates a mitigation strategy executed through operator interventions. Following this, uncertainty quantification employing the Best Estimate Plus Uncertainty (BEPU) methodology was undertaken by coupling RELAP5/SCDAPSIM/MOD3.4 with the statistical software, DAKOTA 6.14.0. The analysis concentrated on critical safety parameters, including Reactor Coolant System (RCS) pressure and temperature, as well as reactor vessel upper head (RVUH) void fraction. These simulations generated a comprehensive dataset, which served as the foundation for training three ML architectures: Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), and Convolutional LSTM (CNN+LSTM). Among these models, the CNN+LSTM hybrid configuration demonstrated superior performance, excelling in both predictive accuracy and computational efficiency. To bolster the model’s transparency and interpretability, Integrated Gradients (IGs)—an advanced Explainable AI (XAI) technique—was applied, elucidating the contribution of input features to the model’s predictions and enhancing its trustworthiness.https://www.mdpi.com/1996-1073/18/2/250multiple steam generator tube ruptureoperator actionsmitigationdesign extension conditionsmachine learning |
| spellingShingle | Sonia Spisak Aya Diab AI-Assisted Forecasting of a Mitigated Multiple Steam Generator Tube Rupture Scenario in a Typical Nuclear Power Plant Energies multiple steam generator tube rupture operator actions mitigation design extension conditions machine learning |
| title | AI-Assisted Forecasting of a Mitigated Multiple Steam Generator Tube Rupture Scenario in a Typical Nuclear Power Plant |
| title_full | AI-Assisted Forecasting of a Mitigated Multiple Steam Generator Tube Rupture Scenario in a Typical Nuclear Power Plant |
| title_fullStr | AI-Assisted Forecasting of a Mitigated Multiple Steam Generator Tube Rupture Scenario in a Typical Nuclear Power Plant |
| title_full_unstemmed | AI-Assisted Forecasting of a Mitigated Multiple Steam Generator Tube Rupture Scenario in a Typical Nuclear Power Plant |
| title_short | AI-Assisted Forecasting of a Mitigated Multiple Steam Generator Tube Rupture Scenario in a Typical Nuclear Power Plant |
| title_sort | ai assisted forecasting of a mitigated multiple steam generator tube rupture scenario in a typical nuclear power plant |
| topic | multiple steam generator tube rupture operator actions mitigation design extension conditions machine learning |
| url | https://www.mdpi.com/1996-1073/18/2/250 |
| work_keys_str_mv | AT soniaspisak aiassistedforecastingofamitigatedmultiplesteamgeneratortuberupturescenarioinatypicalnuclearpowerplant AT ayadiab aiassistedforecastingofamitigatedmultiplesteamgeneratortuberupturescenarioinatypicalnuclearpowerplant |