München 2019 – wissenschaftliches Programm
Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe
P: Fachverband Plasmaphysik
P 18: Postersitzung
P 18.124: Poster
Donnerstag, 21. März 2019, 16:30–18:30, Foyer Audimax
Heat Load Control for Wendelstein 7-X with Machine Learning Approaches — •Daniel Böckenhoff1, Marko Blatzheim1, 2, Roger Labahn2, and Thomas Sunn Pedersen1 for the The Wendelstein 7-X Team collaboration — 1Max-Planck-Institut für Plasmaphysik — 2Institute for Mathematics, University of Rostock
Wendelstein 7-X (W7-X) is a stellarator type nuclear fusion experiment, aiming to confine fusion relevant plasmas in steady state. The plasma-wall contact is realized with plasma facing components (PFCs), which have to withstand heat loads of up to 10 MW/m2. Various mechanisms, like the development of plasma currents, lead to a change in the magnetic topology as well as plasma parameters over time. Therefore the heat load pattern on the PFCs is dynamic. To ensure PFC integrity, mitigate impurity accumulation and more, heat load pattern control is essential for long term operation. Since the physics of the underlying processes is highly complex, we pursue heat load pattern control based on machine learning approaches. As an intermediate step towards this long term objective, we present neural networks capable of reconstructing crucial plasma properties from synthetic PFC heat load patterns.