TRANSP-based accelerated predictive models for scenario development and control of NSTX-U and KSTAR
M.D. Boyer, S. Kaye, K. Erickson, X. Yuan, V. Gajaraj, J. Kunimune, F. Poli, M. Zarnstorff, H.S. Kim, S. Morosohk, E. Schuster, S. Sabbagh, J-H. Ahn
KSTAR Conference
Seoul, South Korea, February 20-22, 2019
Model-based control and scenario development for fusion devices rely
on a hierarchy of models of varying fidelity and speed. Integrated
modeling codes, like TRANSP, can provide high-fidelity simulation
capability, but are incompatible with real-time implementation.
Data-driven reduced modeling based on higher fidelity models provides
a path for developing accelerated predictive models for these tasks.
Several such models have been developed for NSTX-U including a
real-time capable neural network beam model, NubeamNet, that calculates
heating, torque, and current drive profiles from equilibrium parameters
and measured profiles. Models have also been developed for real-time
evaluation of plasma conductivity, bootstrap current, and flux surface
averaged geometric quantities for use in current profile control
algorithms. Approaches to hyperparameter tuning have been studied to
enable optimization of generalization and complexity. Hardware-in-the-loop
simulations in the NSTX-U plasma control system show suitability of the
models for real-time applications. Initial applications, including
estimation of anomalous fast ion diffusivity to match measured neutron
rates, will be presented. Progress toward model development for KSTAR
will also be presented. Finally, preliminary results of using a new
method for coupling feedback algorithms designed in Simulink with
high-fidelity TRANSP simulations will be shown. This capability will
enable controller performance to be verified prior to experiments, with
the goal of reducing commissioning time.