{"title":"Uncertainty-aware prediction of Peak Cladding Temperature during extended station blackout using Transformer-based machine learning","authors":"Tran C.H. Nguyen , Aya Diab","doi":"10.1016/j.nucengdes.2025.113984","DOIUrl":null,"url":null,"abstract":"<div><div>Accurate prediction of the Peak Clad Temperature (PCT) may be used to evaluate the efficacy of operator mitigation actions during extended Station Blackout (SBO) scenarios. In this study, we propose a two-stage machine learning (ML) framework that integrates classification and regression to forecast PCT. While the classification stage identifies whether mitigation efforts succeed or fail, the regression stage provides precise multi-step PCT predictions. Our framework leverages advanced ML models, including Transformer architectures, Attention mechanism, and Long Short-Term Memory (LSTM) networks, alongside the Best Estimate Plus Uncertainty (BEPU) approach. To account for the underlying uncertainty and generate confidence intervals, we incorporate Monte Carlo (MC) Dropout. By integrating BEPU with machine learning and uncertainty quantification, our model produces reliable temperature forecasts despite the system’s inherent complexity and nonlinearity with R<sup>2</sup> values exceeding 0.98 for 60-, 120-, and 240-step time frames. Notably, the LSTM-Transformer model proves to be the most effective, even for longer prediction horizons. The developed framework serves as a powerful real-time decision support tool for operators, for accurate prediction and effective mitigation of critical conditions like extended SBO events.</div></div>","PeriodicalId":19170,"journal":{"name":"Nuclear Engineering and Design","volume":"437 ","pages":"Article 113984"},"PeriodicalIF":1.9000,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nuclear Engineering and Design","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S002954932500161X","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"NUCLEAR SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Accurate prediction of the Peak Clad Temperature (PCT) may be used to evaluate the efficacy of operator mitigation actions during extended Station Blackout (SBO) scenarios. In this study, we propose a two-stage machine learning (ML) framework that integrates classification and regression to forecast PCT. While the classification stage identifies whether mitigation efforts succeed or fail, the regression stage provides precise multi-step PCT predictions. Our framework leverages advanced ML models, including Transformer architectures, Attention mechanism, and Long Short-Term Memory (LSTM) networks, alongside the Best Estimate Plus Uncertainty (BEPU) approach. To account for the underlying uncertainty and generate confidence intervals, we incorporate Monte Carlo (MC) Dropout. By integrating BEPU with machine learning and uncertainty quantification, our model produces reliable temperature forecasts despite the system’s inherent complexity and nonlinearity with R2 values exceeding 0.98 for 60-, 120-, and 240-step time frames. Notably, the LSTM-Transformer model proves to be the most effective, even for longer prediction horizons. The developed framework serves as a powerful real-time decision support tool for operators, for accurate prediction and effective mitigation of critical conditions like extended SBO events.
期刊介绍:
Nuclear Engineering and Design covers the wide range of disciplines involved in the engineering, design, safety and construction of nuclear fission reactors. The Editors welcome papers both on applied and innovative aspects and developments in nuclear science and technology.
Fundamentals of Reactor Design include:
• Thermal-Hydraulics and Core Physics
• Safety Analysis, Risk Assessment (PSA)
• Structural and Mechanical Engineering
• Materials Science
• Fuel Behavior and Design
• Structural Plant Design
• Engineering of Reactor Components
• Experiments
Aspects beyond fundamentals of Reactor Design covered:
• Accident Mitigation Measures
• Reactor Control Systems
• Licensing Issues
• Safeguard Engineering
• Economy of Plants
• Reprocessing / Waste Disposal
• Applications of Nuclear Energy
• Maintenance
• Decommissioning
Papers on new reactor ideas and developments (Generation IV reactors) such as inherently safe modular HTRs, High Performance LWRs/HWRs and LMFBs/GFR will be considered; Actinide Burners, Accelerator Driven Systems, Energy Amplifiers and other special designs of power and research reactors and their applications are also encouraged.