通过红外诊断在聚变反应堆中自动探测UFO:在西托卡马克上的应用

IF 2 3区 工程技术 Q1 NUCLEAR SCIENCE & TECHNOLOGY
Erwan Grelier, Julie Bonnail, Xavier Courtois, West Team
{"title":"通过红外诊断在聚变反应堆中自动探测UFO:在西托卡马克上的应用","authors":"Erwan Grelier,&nbsp;Julie Bonnail,&nbsp;Xavier Courtois,&nbsp;West Team","doi":"10.1016/j.fusengdes.2025.115401","DOIUrl":null,"url":null,"abstract":"<div><div>We present UFOund, a deep-learning-based system for the automated detection and localization of moving particles (nicknamed UFOs) in infrared thermography data from the WEST tokamak. UFOs — small particles eroded from plasma-facing components (PFCs) — pose a significant disruption risk during experimental campaigns, accounting for approximately 35% of disruptions in WEST’s March–April 2023 experiments. Our approach processes sequences of infrared frames from WEST’s infrared thermography diagnostic using a spatiotemporal convolutional neural network. The model, trained on a manually annotated dataset of 295 infrared movies, achieves a balanced accuracy of 0.78 and an F1 score of 0.67 on an unseen test set with a detection threshold of 0.95, and gives very good qualitative results during operation at WEST. We further demonstrate a neural activation-based method to extract segmentation masks and approximate particle trajectories without additional manual annotations. Since November 2024, UFOund has been integrated into WEST’s post-pulse analysis pipeline, delivering near-real-time detection across all infrared views and significantly accelerating between-pulse decision making by the PFC Protection Officers.</div></div>","PeriodicalId":55133,"journal":{"name":"Fusion Engineering and Design","volume":"221 ","pages":"Article 115401"},"PeriodicalIF":2.0000,"publicationDate":"2025-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Automated UFO detection via infrared diagnostics in fusion reactors: Application to the WEST tokamak\",\"authors\":\"Erwan Grelier,&nbsp;Julie Bonnail,&nbsp;Xavier Courtois,&nbsp;West Team\",\"doi\":\"10.1016/j.fusengdes.2025.115401\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>We present UFOund, a deep-learning-based system for the automated detection and localization of moving particles (nicknamed UFOs) in infrared thermography data from the WEST tokamak. UFOs — small particles eroded from plasma-facing components (PFCs) — pose a significant disruption risk during experimental campaigns, accounting for approximately 35% of disruptions in WEST’s March–April 2023 experiments. Our approach processes sequences of infrared frames from WEST’s infrared thermography diagnostic using a spatiotemporal convolutional neural network. The model, trained on a manually annotated dataset of 295 infrared movies, achieves a balanced accuracy of 0.78 and an F1 score of 0.67 on an unseen test set with a detection threshold of 0.95, and gives very good qualitative results during operation at WEST. We further demonstrate a neural activation-based method to extract segmentation masks and approximate particle trajectories without additional manual annotations. Since November 2024, UFOund has been integrated into WEST’s post-pulse analysis pipeline, delivering near-real-time detection across all infrared views and significantly accelerating between-pulse decision making by the PFC Protection Officers.</div></div>\",\"PeriodicalId\":55133,\"journal\":{\"name\":\"Fusion Engineering and Design\",\"volume\":\"221 \",\"pages\":\"Article 115401\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2025-08-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Fusion Engineering and Design\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0920379625005976\",\"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":"Fusion Engineering and Design","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0920379625005976","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

我们提出了UFOund,一个基于深度学习的系统,用于自动检测和定位来自西部托卡马克的红外热成像数据中的移动粒子(昵称为ufo)。不明飞行物——从等离子体面组件(pfc)中侵蚀出来的小颗粒——在实验活动中构成了重大的干扰风险,在2023年3月至4月的WEST实验中,约占干扰的35%。我们的方法使用时空卷积神经网络处理来自WEST红外热成像诊断的红外帧序列。该模型在295部红外电影的人工标注数据集上进行训练,在未见测试集(检测阈值为0.95)上达到了0.78的平衡精度和0.67的F1分数,并在WEST运行时给出了非常好的定性结果。我们进一步展示了一种基于神经激活的方法来提取分割掩模和近似粒子轨迹,而无需额外的手动注释。自2024年11月以来,UFOund已集成到WEST的脉冲后分析管道中,在所有红外视图中提供近实时检测,并显着加快了PFC保护官员的脉冲间决策。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Automated UFO detection via infrared diagnostics in fusion reactors: Application to the WEST tokamak
We present UFOund, a deep-learning-based system for the automated detection and localization of moving particles (nicknamed UFOs) in infrared thermography data from the WEST tokamak. UFOs — small particles eroded from plasma-facing components (PFCs) — pose a significant disruption risk during experimental campaigns, accounting for approximately 35% of disruptions in WEST’s March–April 2023 experiments. Our approach processes sequences of infrared frames from WEST’s infrared thermography diagnostic using a spatiotemporal convolutional neural network. The model, trained on a manually annotated dataset of 295 infrared movies, achieves a balanced accuracy of 0.78 and an F1 score of 0.67 on an unseen test set with a detection threshold of 0.95, and gives very good qualitative results during operation at WEST. We further demonstrate a neural activation-based method to extract segmentation masks and approximate particle trajectories without additional manual annotations. Since November 2024, UFOund has been integrated into WEST’s post-pulse analysis pipeline, delivering near-real-time detection across all infrared views and significantly accelerating between-pulse decision making by the PFC Protection Officers.
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
Fusion Engineering and Design
Fusion Engineering and Design 工程技术-核科学技术
CiteScore
3.50
自引率
23.50%
发文量
275
审稿时长
3.8 months
期刊介绍: The journal accepts papers about experiments (both plasma and technology), theory, models, methods, and designs in areas relating to technology, engineering, and applied science aspects of magnetic and inertial fusion energy. Specific areas of interest include: MFE and IFE design studies for experiments and reactors; fusion nuclear technologies and materials, including blankets and shields; analysis of reactor plasmas; plasma heating, fuelling, and vacuum systems; drivers, targets, and special technologies for IFE, controls and diagnostics; fuel cycle analysis and tritium reprocessing and handling; operations and remote maintenance of reactors; safety, decommissioning, and waste management; economic and environmental analysis of components and systems.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信