Loss of coolant accident diagnosis for large pressurized water reactors based on long short-term memory network

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

Annals of Nuclear Energy Pub Date : 2024-12-30 DOI:10.1016/j.anucene.2024.111167

Ze Zhu, Wenlong Liang, Xianlin Tang, Jiawen Li, Pengfei Wang

{"title":"Loss of coolant accident diagnosis for large pressurized water reactors based on long short-term memory network","authors":"Ze Zhu, Wenlong Liang, Xianlin Tang, Jiawen Li, Pengfei Wang","doi":"10.1016/j.anucene.2024.111167","DOIUrl":null,"url":null,"abstract":"<div><div>Loss of coolant accident (LOCA) is one of the typical accidents in nuclear power plants (NPPs), which is very difficult to diagnosis accurately using traditional equipment alarm mechanisms or expert experience. This paper carries out the LOCA diagnosis study for large pressurized water reactors (PWRs) using long short-term memory (LSTM) networks. Based on a RELAP5-Simulink coupling model, sample datasets of nine types of LOCA for the target PWR were generated. The break locations were selected as the primary-loop hot and cold legs and steam generator heat transfer tubes, with three break sizes set for each break location. Subsequently, an enhanced LSTM network incorporating ReLU and Dropout layers and batch normalization was trained for accident feature extraction. Simulation results show that the developed LSTM model can realize accurate LOCA diagnosis timely, with a diagnostic accuracy of 97.79%. This study can provide methodological support for intelligent accident diagnosis of PWRs.</div></div>","PeriodicalId":8006,"journal":{"name":"Annals of Nuclear Energy","volume":"213 ","pages":"Article 111167"},"PeriodicalIF":1.9000,"publicationDate":"2024-12-30","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/S0306454924008302","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

Loss of coolant accident (LOCA) is one of the typical accidents in nuclear power plants (NPPs), which is very difficult to diagnosis accurately using traditional equipment alarm mechanisms or expert experience. This paper carries out the LOCA diagnosis study for large pressurized water reactors (PWRs) using long short-term memory (LSTM) networks. Based on a RELAP5-Simulink coupling model, sample datasets of nine types of LOCA for the target PWR were generated. The break locations were selected as the primary-loop hot and cold legs and steam generator heat transfer tubes, with three break sizes set for each break location. Subsequently, an enhanced LSTM network incorporating ReLU and Dropout layers and batch normalization was trained for accident feature extraction. Simulation results show that the developed LSTM model can realize accurate LOCA diagnosis timely, with a diagnostic accuracy of 97.79%. This study can provide methodological support for intelligent accident diagnosis of PWRs.

查看原文本刊更多论文

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.