Automated UFO detection via infrared diagnostics in fusion reactors: Application to the WEST tokamak.
Saved in:
| Title: | Automated UFO detection via infrared diagnostics in fusion reactors: Application to the WEST tokamak. |
|---|---|
| Authors: | Grelier, Erwan1 (AUTHOR) erwan.grelier@cea.fr, Bonnail, Julie1 (AUTHOR), Courtois, Xavier1 (AUTHOR) |
| Source: | Fusion Engineering & Design. Dec2025, Vol. 221, pN.PAG-N.PAG. 1p. |
| Subjects: | Tokamaks, Deep learning, Fusion reactors, Convolutional neural networks, Detection algorithms, Infrared radiometry, Particle detectors |
| Abstract: | 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. • Deep learning model detects flying particles in WEST tokamak infrared sequences. • Weak supervision enables localization without cumbersome manual annotation. • Automated detection supports fast analysis and decisions during WEST operation. • Generic method applicable to other or future fusion devices such as ITER. [ABSTRACT FROM AUTHOR] |
| Copyright of Fusion Engineering & Design is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 187893509 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Automated UFO detection via infrared diagnostics in fusion reactors: Application to the WEST tokamak. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Grelier%2C+Erwan%22">Grelier, Erwan</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> erwan.grelier@cea.fr</i><br /><searchLink fieldCode="AR" term="%22Bonnail%2C+Julie%22">Bonnail, Julie</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Courtois%2C+Xavier%22">Courtois, Xavier</searchLink><relatesTo>1</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Fusion+Engineering+%26+Design%22">Fusion Engineering & Design</searchLink>. Dec2025, Vol. 221, pN.PAG-N.PAG. 1p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Tokamaks%22">Tokamaks</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Fusion+reactors%22">Fusion reactors</searchLink><br /><searchLink fieldCode="DE" term="%22Convolutional+neural+networks%22">Convolutional neural networks</searchLink><br /><searchLink fieldCode="DE" term="%22Detection+algorithms%22">Detection algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Infrared+radiometry%22">Infrared radiometry</searchLink><br /><searchLink fieldCode="DE" term="%22Particle+detectors%22">Particle detectors</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: 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. • Deep learning model detects flying particles in WEST tokamak infrared sequences. • Weak supervision enables localization without cumbersome manual annotation. • Automated detection supports fast analysis and decisions during WEST operation. • Generic method applicable to other or future fusion devices such as ITER. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Fusion Engineering & Design is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=187893509 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1016/j.fusengdes.2025.115401 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 1 StartPage: N.PAG Subjects: – SubjectFull: Tokamaks Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Fusion reactors Type: general – SubjectFull: Convolutional neural networks Type: general – SubjectFull: Detection algorithms Type: general – SubjectFull: Infrared radiometry Type: general – SubjectFull: Particle detectors Type: general Titles: – TitleFull: Automated UFO detection via infrared diagnostics in fusion reactors: Application to the WEST tokamak. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Grelier, Erwan – PersonEntity: Name: NameFull: Bonnail, Julie – PersonEntity: Name: NameFull: Courtois, Xavier IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 12 Text: Dec2025 Type: published Y: 2025 Identifiers: – Type: issn-print Value: 09203796 Numbering: – Type: volume Value: 221 Titles: – TitleFull: Fusion Engineering & Design Type: main |
| ResultId | 1 |
