基于神经网络模型的热管冷却堆预测控制

IF 1.9 3区工程技术 Q1 NUCLEAR SCIENCE & TECHNOLOGY

Nuclear Engineering and Design Pub Date : 2025-03-13 DOI:10.1016/j.nucengdes.2025.113983

Xi Bai , Jiajun Huang , Zheyu Chen, Peiwei Sun, Xinyu Wei

{"title":"基于神经网络模型的热管冷却堆预测控制","authors":"Xi Bai , Jiajun Huang , Zheyu Chen, Peiwei Sun, Xinyu Wei","doi":"10.1016/j.nucengdes.2025.113983","DOIUrl":null,"url":null,"abstract":"<div><div>The adoption of heat pipes for heat transfer makes the heat pipe-cooled reactor (HPR) with significant time delays, making it difficult for traditional proportional integral derivative control systems to meet the rapid and precise power control demands. Therefore, neural network-based model predictive control is applied for HPR. NUSTER-100 model predictive control system utilizes a feedforward neural network model as the prediction model. By employing numerical optimization algorithms to obtain the optimal control variables, the system effectively overcomes the impact of significant time delays on the control system, achieving rapid and precise regulation. It can effectively suppress the impact of abnormal states on control performance, and ensure that heat pipe-cooled reactor can operate safely and stably under abnormal conditions.</div></div>","PeriodicalId":19170,"journal":{"name":"Nuclear Engineering and Design","volume":"436 ","pages":"Article 113983"},"PeriodicalIF":1.9000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predictive control of a heat pipe-cooled reactor based on a neural network model\",\"authors\":\"Xi Bai , Jiajun Huang , Zheyu Chen, Peiwei Sun, Xinyu Wei\",\"doi\":\"10.1016/j.nucengdes.2025.113983\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>The adoption of heat pipes for heat transfer makes the heat pipe-cooled reactor (HPR) with significant time delays, making it difficult for traditional proportional integral derivative control systems to meet the rapid and precise power control demands. Therefore, neural network-based model predictive control is applied for HPR. NUSTER-100 model predictive control system utilizes a feedforward neural network model as the prediction model. By employing numerical optimization algorithms to obtain the optimal control variables, the system effectively overcomes the impact of significant time delays on the control system, achieving rapid and precise regulation. It can effectively suppress the impact of abnormal states on control performance, and ensure that heat pipe-cooled reactor can operate safely and stably under abnormal conditions.</div></div>\",\"PeriodicalId\":19170,\"journal\":{\"name\":\"Nuclear Engineering and Design\",\"volume\":\"436 \",\"pages\":\"Article 113983\"},\"PeriodicalIF\":1.9000,\"publicationDate\":\"2025-03-13\",\"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/S0029549325001608\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Nuclear Engineering and Design","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0029549325001608","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

摘要

热管传热的采用使得热管冷却堆（HPR）具有明显的时滞，传统的比例积分导数控制系统难以满足快速、精确的功率控制需求。因此，将基于神经网络的模型预测控制应用于HPR。NUSTER-100模型预测控制系统采用前馈神经网络模型作为预测模型。通过采用数值优化算法获得最优控制变量，有效克服了显著时滞对控制系统的影响，实现了快速、精确的调节。它能有效抑制异常状态对控制性能的影响，保证热管冷却堆在异常工况下安全稳定运行。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Predictive control of a heat pipe-cooled reactor based on a neural network model

The adoption of heat pipes for heat transfer makes the heat pipe-cooled reactor (HPR) with significant time delays, making it difficult for traditional proportional integral derivative control systems to meet the rapid and precise power control demands. Therefore, neural network-based model predictive control is applied for HPR. NUSTER-100 model predictive control system utilizes a feedforward neural network model as the prediction model. By employing numerical optimization algorithms to obtain the optimal control variables, the system effectively overcomes the impact of significant time delays on the control system, achieving rapid and precise regulation. It can effectively suppress the impact of abnormal states on control performance, and ensure that heat pipe-cooled reactor can operate safely and stably under abnormal conditions.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Nuclear Engineering and Design 工程技术-核科学技术

CiteScore

3.40

自引率

11.80%

发文量

377

审稿时长

5 months

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.