Preemptive RMP-driven ELM crash suppression automated by a real-time machine-learning classifier in KSTAR

Suppression or mitigation of edge-localized mode (ELM) crashes is necessary for ITER. The strategy to suppress all the ELM crashes by the resonant magnetic perturbation (RMP) should be applied as soon as the first low-to-high confinement (L–H) transition occurs. A control algorithm based on real-tim...

Full description

Saved in:
Bibliographic Details
Published in:Nuclear fusion 2022-02, Vol.62 (2), p.26035
Main Authors: Shin, Giwook, Han, H., Kim, M., Hahn, S.-H., Ko, W.H., Park, G.Y., Lee, Y.H., Lee, M.W., Kim, M.H., Juhn, J.-W., Seo, D.C., Jang, J., Kim, H.S., Lee, J.H., Kim, H.J.
Format: Article
Language:English
Subjects:
ELM-crash suppression
ITER
KSTAR
machine learning
plasma control
preemptive RMP
real-time ELM control
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Suppression or mitigation of edge-localized mode (ELM) crashes is necessary for ITER. The strategy to suppress all the ELM crashes by the resonant magnetic perturbation (RMP) should be applied as soon as the first low-to-high confinement (L–H) transition occurs. A control algorithm based on real-time machine learning (ML) enables such an approach: it classifies the H-mode transition and the ELMy phase in real-time and automatically applies the preemptive RMP. This paper reports the algorithm design, which is now implemented in the KSTAR plasma-control system, and the corresponding experimental demonstration of typical high- δ KSTAR H-mode plasmas. As a result, all initial ELM crashes are suppressed with an acceptable safety factor at the edge ( q 95 ) and with RMP field adjustment. Moreover, the ML-driven ELM crash suppression discharges remain stable without further degradation due to the regularization of the plasma pedestal.
ISSN:0029-5515
1741-4326
DOI:10.1088/1741-4326/ac412d