Robust impurity detection and tracking for tokamaks
| Autor: | Jet Contributors, Brandon Harris, C. Cowley, D. Rudakov, M. Sertoli, J.W.M. Vernimmen, L. James, Magnum-PSI Collaborations, Igor Bykov, S. Brons, Anna Widdowson, L. Simons, P. Fuller, J. Scholten, Thomas Hunt Morgan, Paul M. Bryant, S. A. Silburn, Diii-D Jet, Y. Andrew |
|---|---|
| Přispěvatelé: | Science and Technology of Nuclear Fusion |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
Tokamak
business.industry Computer science Dust particles Joint European Torus ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Stereoscopy Tracking (particle physics) 01 natural sciences 010305 fluids & plasmas law.invention Single camera law Impurity 0103 physical sciences Code (cryptography) Computer vision Artificial intelligence 010306 general physics business |
| Zdroj: | Physical Review E Physical Review E, 102, 043311 Physical Review E, 102(4):043311. American Physical Society |
| ISSN: | 2470-0045 |
| DOI: | 10.1103/physreve.102.043311 |
| Popis: | A robust impurity detection and tracking code, able to generate large sets of dust tracks from tokamak camera footage, is presented. This machine learning-based code is tested with cameras from the Joint European Torus, Doublet-III-D, and Magnum-PSI and is able to generate dust tracks with a 65-100% classification accuracy. Moreover, the number dust particles detected from a single camera shot can be up to the order of 1000. Several areas of improvement for the code are highlighted, such as generating more significant training data sets and accounting for selection biases. Although the code is tested with dust in single two-dimensional camera views, it could easily be applied to multiple-camera stereoscopic reconstruction or nondust impurities. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|