View in EDS

Automated UFO detection via infrared diagnostics in fusion reactors: Application to the WEST tokamak.

Saved in:
Bibliographic Details
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
Description
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]
ISSN:09203796
DOI:10.1016/j.fusengdes.2025.115401