Prediction of secondary circuit power generation for nuclear units based on WSA-VMD-BP approach

IF 2.3 3区工程技术 Q1 NUCLEAR SCIENCE & TECHNOLOGY

Annals of Nuclear Energy Pub Date : 2025-07-07 DOI:10.1016/j.anucene.2025.111721

Desheng Dan , Maobin Hu , Haiyan Liu , Yuanhao Xu , Jie Yu , Gang Pei

{"title":"Prediction of secondary circuit power generation for nuclear units based on WSA-VMD-BP approach","authors":"Desheng Dan , Maobin Hu , Haiyan Liu , Yuanhao Xu , Jie Yu , Gang Pei","doi":"10.1016/j.anucene.2025.111721","DOIUrl":null,"url":null,"abstract":"<div><div>Nuclear energy has been regarded as an environmentally superior and reliable form of energy due to its inherent stability and lengthy operational lifetime. Small modular reactors (SMR) have been positioned as a prominent research focus in recent years, while artificial intelligence has also opened new avenues for exploration the performance of nuclear units. This paper proposes to predict the power generation of nuclear power plants integrating variational modal decomposition (VMD) and back propagation (BP) neural networks to optimize the hyperparameters through the utilization of the wave search algorithm (WSA). The efficacy of the proposed method is validated through the construction of a secondary circuit mathematical model of a nuclear power facility and an in-depth analysis of the thermal parameter relationships. The proposed method demonstrated an MAE of 0.6964 and a WIA of up to 0.99 in the noiseless case, exhibiting a low prediction error. In the context of environmental noise, the prediction accuracy can be maintained at approximately WIA ∼ 0.97. These results demonstrate the high prediction accuracy and strong robustness of the algorithm.</div></div>","PeriodicalId":8006,"journal":{"name":"Annals of Nuclear Energy","volume":"224 ","pages":"Article 111721"},"PeriodicalIF":2.3000,"publicationDate":"2025-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of Nuclear Energy","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0306454925005389","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

Nuclear energy has been regarded as an environmentally superior and reliable form of energy due to its inherent stability and lengthy operational lifetime. Small modular reactors (SMR) have been positioned as a prominent research focus in recent years, while artificial intelligence has also opened new avenues for exploration the performance of nuclear units. This paper proposes to predict the power generation of nuclear power plants integrating variational modal decomposition (VMD) and back propagation (BP) neural networks to optimize the hyperparameters through the utilization of the wave search algorithm (WSA). The efficacy of the proposed method is validated through the construction of a secondary circuit mathematical model of a nuclear power facility and an in-depth analysis of the thermal parameter relationships. The proposed method demonstrated an MAE of 0.6964 and a WIA of up to 0.99 in the noiseless case, exhibiting a low prediction error. In the context of environmental noise, the prediction accuracy can be maintained at approximately WIA ∼ 0.97. These results demonstrate the high prediction accuracy and strong robustness of the algorithm.

查看原文本刊更多论文

基于WSA-VMD-BP方法的核电机组二次回路发电量预测

核能由于其固有的稳定性和较长的使用寿命，一直被认为是一种环境优越和可靠的能源形式。近年来，小型模块化反应堆（SMR）已被定位为一个突出的研究热点，而人工智能也为探索核机组的性能开辟了新的途径。本文提出将变分模态分解（VMD）和反向传播（BP）神经网络相结合，利用波搜索算法（WSA）对超参数进行优化，对核电站发电量进行预测。通过对某核电设施二次回路数学模型的建立和热力参数关系的深入分析，验证了该方法的有效性。在无噪声情况下，该方法的MAE为0.6964，WIA为0.99，预测误差较小。在环境噪声的情况下，预测精度可以保持在大约WIA ~ 0.97。结果表明，该算法具有较高的预测精度和较强的鲁棒性。

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

Annals of Nuclear Energy 工程技术-核科学技术

CiteScore

4.30

自引率

21.10%

发文量

632

审稿时长

7.3 months

期刊介绍： Annals of Nuclear Energy provides an international medium for the communication of original research, ideas and developments in all areas of the field of nuclear energy science and technology. Its scope embraces nuclear fuel reserves, fuel cycles and cost, materials, processing, system and component technology (fission only), design and optimization, direct conversion of nuclear energy sources, environmental control, reactor physics, heat transfer and fluid dynamics, structural analysis, fuel management, future developments, nuclear fuel and safety, nuclear aerosol, neutron physics, computer technology (both software and hardware), risk assessment, radioactive waste disposal and reactor thermal hydraulics. Papers submitted to Annals need to demonstrate a clear link to nuclear power generation/nuclear engineering. Papers which deal with pure nuclear physics, pure health physics, imaging, or attenuation and shielding properties of concretes and various geological materials are not within the scope of the journal. Also, papers that deal with policy or economics are not within the scope of the journal.