Optimization of water chemistry to mitigate corrosion products in nuclear power plants using big data and multiple linear regression in machine learning

IF 3.3 3区工程技术 Q1 NUCLEAR SCIENCE & TECHNOLOGY

Progress in Nuclear Energy Pub Date : 2025-02-27 DOI:10.1016/j.pnucene.2025.105685

Jinsoo Choi , Jong-Il Yun

{"title":"Optimization of water chemistry to mitigate corrosion products in nuclear power plants using big data and multiple linear regression in machine learning","authors":"Jinsoo Choi , Jong-Il Yun","doi":"10.1016/j.pnucene.2025.105685","DOIUrl":null,"url":null,"abstract":"<div><div>The primary system of a nuclear power plant operates under high temperature and high pressure conditions, making material integrity crucial to prevent accidents and ensure safe operation. Effective coolant chemistry control is essential for mitigating corrosion product releases, preventing material degradation and minimizing radiation exposure within the plant. To accurately predict corrosion product concentrations, a model was developed using data collected under reactor-critical operating conditions. where consistent parameters like pressure and temperature were maintained. Co-58, a nickel activation product, was selected as a representative corrosion product due to its high concentration and presence in primary materials. Key chemical factors influencing corrosion, such as lithium (Li), pH, and dissolved hydrogen (DH), were analyzed, and operational parameters were verified to confirm reactor-critical conditions. Effects of Li and DH on Co-58 concentration were evaluated using Multiple Linear Regression in Machine Learning. Between Li and pH, Li was ultimately selected for its higher regression coefficient (β) and direct role in controlling pH. Then, Li and DH were used to develop a predictive model for corrosion diagnostics. Findings indicate that Li has a stronger impact on Co-58 reduction than DH, with the β value being 4.01 times higher. The model is statistically significant (F = 282.6, p < 0.000) and demonstrates an adjusted R<sup>2</sup> value of 0.351, with machine learning results achieving an R<sup>2</sup> value of 0.442 on the test set. These results suggest that maintaining Li and DH conditions at the upper allowable ranges can play a crucial role in reducing corrosion products.</div><div>The significance of this study lies in its reliance on operational, reactor-critical data rather than laboratory-only data, offering a robust and practical approach to optimize corrosion management in both existing nuclear power plants (NPPs) and next-generation reactors, including Small Modular Reactors (SMRs). This model provides a novel method that enhances plant safety and operational efficiency by enabling more accurate prediction and control of Co-58 concentrations than traditional approaches.</div></div>","PeriodicalId":20617,"journal":{"name":"Progress in Nuclear Energy","volume":"183 ","pages":"Article 105685"},"PeriodicalIF":3.3000,"publicationDate":"2025-02-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Progress in Nuclear Energy","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0149197025000836","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

The primary system of a nuclear power plant operates under high temperature and high pressure conditions, making material integrity crucial to prevent accidents and ensure safe operation. Effective coolant chemistry control is essential for mitigating corrosion product releases, preventing material degradation and minimizing radiation exposure within the plant. To accurately predict corrosion product concentrations, a model was developed using data collected under reactor-critical operating conditions. where consistent parameters like pressure and temperature were maintained. Co-58, a nickel activation product, was selected as a representative corrosion product due to its high concentration and presence in primary materials. Key chemical factors influencing corrosion, such as lithium (Li), pH, and dissolved hydrogen (DH), were analyzed, and operational parameters were verified to confirm reactor-critical conditions. Effects of Li and DH on Co-58 concentration were evaluated using Multiple Linear Regression in Machine Learning. Between Li and pH, Li was ultimately selected for its higher regression coefficient (β) and direct role in controlling pH. Then, Li and DH were used to develop a predictive model for corrosion diagnostics. Findings indicate that Li has a stronger impact on Co-58 reduction than DH, with the β value being 4.01 times higher. The model is statistically significant (F = 282.6, p < 0.000) and demonstrates an adjusted R² value of 0.351, with machine learning results achieving an R² value of 0.442 on the test set. These results suggest that maintaining Li and DH conditions at the upper allowable ranges can play a crucial role in reducing corrosion products.

The significance of this study lies in its reliance on operational, reactor-critical data rather than laboratory-only data, offering a robust and practical approach to optimize corrosion management in both existing nuclear power plants (NPPs) and next-generation reactors, including Small Modular Reactors (SMRs). This model provides a novel method that enhances plant safety and operational efficiency by enabling more accurate prediction and control of Co-58 concentrations than traditional approaches.

查看原文本刊更多论文

核电站的主系统在高温高压条件下运行，因此材料的完整性对于防止事故和确保安全运行至关重要。有效的冷却剂化学控制对于减轻腐蚀产物释放、防止材料降解和最大限度地减少核电站内的辐射暴露至关重要。为了准确预测腐蚀产物的浓度，我们利用在反应堆临界运行条件下收集的数据开发了一个模型，其中压力和温度等参数保持一致。Co-58 是一种镍活化产物，由于其浓度高且存在于初级材料中，因此被选为具有代表性的腐蚀产物。分析了影响腐蚀的关键化学因素，如锂 (Li)、pH 值和溶解氢 (DH)，并验证了运行参数，以确认反应器的临界状态。使用机器学习中的多元线性回归评估了锂和 DH 对 Co-58 浓度的影响。在锂和 pH 值之间，最终选择了锂，因为其回归系数（β）较高，且直接控制 pH 值。然后，利用锂和 DH 建立了一个用于腐蚀诊断的预测模型。研究结果表明，与 DH 相比，Li 对 Co-58 还原的影响更大，其 β 值是 DH 的 4.01 倍。该模型具有统计学意义（F = 282.6，p <0.000），调整后的 R2 值为 0.351，机器学习结果在测试集上的 R2 值为 0.442。这些结果表明，将 Li 和 DH 条件保持在允许的上限范围内可以在减少腐蚀产物方面发挥至关重要的作用。这项研究的意义在于它依赖于运行中的反应堆关键数据，而非仅有的实验室数据，为优化现有核电站（NPP）和下一代反应堆（包括小型模块化反应堆（SMR））的腐蚀管理提供了一种稳健而实用的方法。与传统方法相比，该模型能更准确地预测和控制 Co-58 的浓度，提供了一种提高核电站安全性和运行效率的新方法。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Progress in Nuclear Energy 工程技术-核科学技术

CiteScore

5.30

自引率

14.80%

发文量

331

审稿时长

3.5 months

期刊介绍： Progress in Nuclear Energy is an international review journal covering all aspects of nuclear science and engineering. In keeping with the maturity of nuclear power, articles on safety, siting and environmental problems are encouraged, as are those associated with economics and fuel management. However, basic physics and engineering will remain an important aspect of the editorial policy. Articles published are either of a review nature or present new material in more depth. They are aimed at researchers and technically-oriented managers working in the nuclear energy field. Please note the following: 1) PNE seeks high quality research papers which are medium to long in length. Short research papers should be submitted to the journal Annals in Nuclear Energy. 2) PNE reserves the right to reject papers which are based solely on routine application of computer codes used to produce reactor designs or explain existing reactor phenomena. Such papers, although worthy, are best left as laboratory reports whereas Progress in Nuclear Energy seeks papers of originality, which are archival in nature, in the fields of mathematical and experimental nuclear technology, including fission, fusion (blanket physics, radiation damage), safety, materials aspects, economics, etc. 3) Review papers, which may occasionally be invited, are particularly sought by the journal in these fields.