Status of the Deep Learning-Based Shattered Pellet Injection Shard Tracking at ASDEX Upgrade

IF 1.9 4区 工程技术 Q1 NUCLEAR SCIENCE & TECHNOLOGY Journal of Fusion Energy Pub Date : 2024-05-14 DOI:10.1007/s10894-024-00406-x
Johannes Illerhaus, W. Treutterer, P. Heinrich, M. Miah, G. Papp, T. Peherstorfer, B. Sieglin, U. v. Toussaint, H. Zohm, F. Jenko, the ASDEX Upgrade Team
{"title":"Status of the Deep Learning-Based Shattered Pellet Injection Shard Tracking at ASDEX Upgrade","authors":"Johannes Illerhaus,&nbsp;W. Treutterer,&nbsp;P. Heinrich,&nbsp;M. Miah,&nbsp;G. Papp,&nbsp;T. Peherstorfer,&nbsp;B. Sieglin,&nbsp;U. v. Toussaint,&nbsp;H. Zohm,&nbsp;F. Jenko,&nbsp;the ASDEX Upgrade Team","doi":"10.1007/s10894-024-00406-x","DOIUrl":null,"url":null,"abstract":"<div><p>Plasma disruptions pose an intolerable risk to large tokamaks, such as ITER. If a disruption can no longer be avoided, ITER’s last line of defense will be the Shattered Pellet Injection. An experimental test bench was created at ASDEX Upgrade to inform the design decisions for controlling the shattering of the pellets and develop the techniques for the generation of the fragment distributions necessary for optimal disruption mitigation. In an effort to analyze the videos resulting from the more than 1000 tests and determine the impact of different settings on the resulting shard cloud, an analysis pipeline, based on traditional computer vision (CV), was created. This pipeline enabled the analysis of 173 of the videos, but at the same time showed the limits of traditional CV when applied in applications with a highly heterogeneous dataset such as this. We created a machine learning-based (ML) alternative as a drop-in replacement to the original image processing code using a semantic segmentation model to exploit the innate adaptability and robustness of deep learning models. This model is capable of labeling the entire dataset quickly, accurately and reliably. This contribution details the implementation of the ML model and the current state and future plans of the project.</p></div>","PeriodicalId":634,"journal":{"name":"Journal of Fusion Energy","volume":null,"pages":null},"PeriodicalIF":1.9000,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10894-024-00406-x.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Fusion Energy","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s10894-024-00406-x","RegionNum":4,"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

Plasma disruptions pose an intolerable risk to large tokamaks, such as ITER. If a disruption can no longer be avoided, ITER’s last line of defense will be the Shattered Pellet Injection. An experimental test bench was created at ASDEX Upgrade to inform the design decisions for controlling the shattering of the pellets and develop the techniques for the generation of the fragment distributions necessary for optimal disruption mitigation. In an effort to analyze the videos resulting from the more than 1000 tests and determine the impact of different settings on the resulting shard cloud, an analysis pipeline, based on traditional computer vision (CV), was created. This pipeline enabled the analysis of 173 of the videos, but at the same time showed the limits of traditional CV when applied in applications with a highly heterogeneous dataset such as this. We created a machine learning-based (ML) alternative as a drop-in replacement to the original image processing code using a semantic segmentation model to exploit the innate adaptability and robustness of deep learning models. This model is capable of labeling the entire dataset quickly, accurately and reliably. This contribution details the implementation of the ML model and the current state and future plans of the project.

Abstract Image

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
ASDEX 升级版中基于深度学习的碎丸注射碎片追踪技术的现状
等离子体中断对热核实验堆等大型托卡马克构成不可容忍的风险。如果干扰无法避免,热核实验堆的最后一道防线将是碎裂颗粒注入。在 ASDEX 升级版上创建了一个实验测试台,以便为控制颗粒碎裂的设计决策提供信息,并开发出产生碎片分布的技术,这些碎片分布是实现最佳中断缓解所必需的。为了分析 1000 多次试验产生的视频并确定不同设置对产生的碎片云的影响,基于传统计算机视觉(CV)创建了一个分析管道。该管道能够对 173 个视频进行分析,但同时也显示出传统 CV 在这种高度异构数据集应用中的局限性。我们创建了一个基于机器学习(ML)的替代方案,作为原始图像处理代码的直接替代,使用语义分割模型来利用深度学习模型与生俱来的适应性和鲁棒性。该模型能够快速、准确、可靠地标记整个数据集。这篇论文详细介绍了 ML 模型的实施以及该项目的现状和未来计划。
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 去求助
来源期刊
Journal of Fusion Energy
Journal of Fusion Energy 工程技术-核科学技术
CiteScore
2.20
自引率
0.00%
发文量
24
审稿时长
2.3 months
期刊介绍: The Journal of Fusion Energy features original research contributions and review papers examining and the development and enhancing the knowledge base of thermonuclear fusion as a potential power source. It is designed to serve as a journal of record for the publication of original research results in fundamental and applied physics, applied science and technological development. The journal publishes qualified papers based on peer reviews. This journal also provides a forum for discussing broader policies and strategies that have played, and will continue to play, a crucial role in fusion programs. In keeping with this theme, readers will find articles covering an array of important matters concerning strategy and program direction.
期刊最新文献
Research on Insulation Technology for Nb3Sn Layer Coil of Superconducting Conductor Testing Facility Preliminary Control-Oriented Modeling of the ITER Steering Mirror Assembly and Local Control System in the Electron Cyclotron Heating & Current Drive Actuator High Energy Density Radiative Transfer in the Diffusion Regime with Fourier Neural Operators Retraction Note: Determination of the Plasma Internal Inductance and Evaluation of its Effects on Plasma Horizontal Displacement in IR-T1 Tokamak Effects of Injected Current Streams on MHD Equilibrium Reconstruction of Local Helicity Injection Plasmas in a Spherical Tokamak
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1