Machine learning-based real-time kinetic profile reconstruction in DIII-D

Ricardo Shousha, Jaemin Seo, Keith Erickson, Zichuan Xing, Sang Kyeun Kim, Joseph Abbate, Egemen Kolemen

Research output: Contribution to journalArticlepeer-review

9 Scopus citations

Abstract

Kinetic equilibrium reconstruction plays a vital role in the physical analysis of plasma stability and control in fusion tokamaks. However, the traditional approach is subjective and prone to human biases. To address this, the consistent automatic kinetic equilibrium reconstruction (CAKE) method was introduced, providing objective results. Nonetheless, its offline nature limits its application in real-time plasma control systems (PCSs). To address this limitation, we present RTCAKENN, a machine learning model that approximates 7 CAKE-level output profiles, namely pressure, inverse q, toroidal current density, electron temperature and density, carbon ion impurity temperature and rotation profiles, using real-time available inputs. The deep neural network consists of an encoder layer, where the scalars and interdependent inputs such as plasma boundary coordinates and motional Stark effect data are encoded using multi-layer perceptrons (MLPs), while profile inputs are encoded by 1D convolutional layers. The encoded data is passed through a MLP for latent feature extraction, before being decoded in the decoding layers, which consist of upsampling and convolutional layers. RTCAKENN has been implemented in the DIII-D PCS and our model achieves accuracy comparable to CAKE and surpasses existing real-time alternatives. Through clever dropout training, RTCAKENN exhibits robustness and can operate even in the absence of Thomson scattering data or charge exchange recombination data. It executes in under 8 ms in the real-time environment, enabling future application in real-time control and analysis.

Original languageEnglish (US)
Article number026006
JournalNuclear Fusion
Volume64
Issue number2
DOIs
StatePublished - Feb 2024

All Science Journal Classification (ASJC) codes

  • Nuclear and High Energy Physics
  • Condensed Matter Physics

Keywords

  • DIII-D
  • equilibrium reconstruction
  • kinetic
  • machine learning
  • neural net
  • real-time

Fingerprint

Dive into the research topics of 'Machine learning-based real-time kinetic profile reconstruction in DIII-D'. Together they form a unique fingerprint.

Cite this