{"title":"Prediction of steam generator liquid level under main steam line break accident based on wavelet decomposition combined with deep learning","authors":"Biaoxin Wang, Yuang Jiang, Mei Lin, Qiuwang Wang","doi":"10.1016/j.nucengdes.2025.113998","DOIUrl":null,"url":null,"abstract":"<div><div>Liquid level monitoring is essential for maintaining the safe operation of nuclear power circuits. During a Main Steam Line Break (MSLB) accident, significant fluctuations in the liquid level within the steam generator pose challenges for traditional measurement methods, which often fail to accurately capture the true liquid level. This study conducted experiments of MSLB accidents under controlled conditions, with parameters including heating power ranging from 8 to 16 kW, break pressures from 0.05 to 0.1 MPa, and relative break sizes between 20 % and 100 %. In selected conditions, rolling motions were introduced to simulate marine environments. Wavelet decomposition was utilized to extract features at varying frequency levels, and deep learning models were employed to predict each component. The proposed approach achieved a prediction accuracy of 88.3 %, outperforming direct predictions from raw data with improvements of 21.9 % in Mean Squared Error (<em>MSE</em>), 12.3 % in Mean Absolute Error (<em>MAE</em>), and 10.0 % in the coefficient of determination (<em>R</em><sup>2</sup>). The detail component cD1 was found to have the most significant impact on overall prediction accuracy, highlighting it as a key parameter for further optimization. Furthermore, the use of wavelet-decomposed data significantly reduced computational complexity, enhancing time efficiency. These results demonstrate the effectiveness of the proposed method in improving prediction accuracy and operational efficiency, offering valuable support for the safe management of nuclear power systems during MSLB accidents.</div></div>","PeriodicalId":19170,"journal":{"name":"Nuclear Engineering and Design","volume":"436 ","pages":"Article 113998"},"PeriodicalIF":1.9000,"publicationDate":"2025-03-14","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/S002954932500175X","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
Liquid level monitoring is essential for maintaining the safe operation of nuclear power circuits. During a Main Steam Line Break (MSLB) accident, significant fluctuations in the liquid level within the steam generator pose challenges for traditional measurement methods, which often fail to accurately capture the true liquid level. This study conducted experiments of MSLB accidents under controlled conditions, with parameters including heating power ranging from 8 to 16 kW, break pressures from 0.05 to 0.1 MPa, and relative break sizes between 20 % and 100 %. In selected conditions, rolling motions were introduced to simulate marine environments. Wavelet decomposition was utilized to extract features at varying frequency levels, and deep learning models were employed to predict each component. The proposed approach achieved a prediction accuracy of 88.3 %, outperforming direct predictions from raw data with improvements of 21.9 % in Mean Squared Error (MSE), 12.3 % in Mean Absolute Error (MAE), and 10.0 % in the coefficient of determination (R2). The detail component cD1 was found to have the most significant impact on overall prediction accuracy, highlighting it as a key parameter for further optimization. Furthermore, the use of wavelet-decomposed data significantly reduced computational complexity, enhancing time efficiency. These results demonstrate the effectiveness of the proposed method in improving prediction accuracy and operational efficiency, offering valuable support for the safe management of nuclear power systems during MSLB accidents.
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.