Learning Plasma Dynamics and Robust Rampdown Trajectories with Predict-First Experiments at TCV
Authors:
Preprint
Abstract
The rampdown in tokamak operations is a difficult to simulate phase during which the plasma is often pushed towards multiple instability limits. To address this challenge, and reduce the risk of disrupting operations, we leverage recent advances in Scientific Machine Learning (SciML) to develop a neural state-space model (NSSM) that predicts plasma dynamics during Tokamak \`a Configuration Variable (TCV) rampdowns. By integrating simple physics structure and data-driven models, the NSSM efficiently learns plasma dynamics during the rampdown from a modest dataset of 311 pulses with only five pulses in the reactor relevant high performance regime. The NSSM is parallelized across uncertainties, and reinforcement learning (RL) is applied to design trajectories that avoid multiple instability limits with high probability. Experiments at TCV ramping down high performance plasmas show statistically significant improvements in current and energy at plasma termination, with improvements in speed through continuous re-training. A predict-first experiment, increasing plasma current by 20\% from baseline, demonstrates the NSSM's ability to make small extrapolations with sufficient accuracy to design trajectories that successfully terminate the pulse. The developed approach paves the way for designing tokamak controls with robustness to considerable uncertainty, and demonstrates the relevance of the SciML approach to learning plasma dynamics for rapidly developing robust trajectories and controls during the incremental campaigns of upcoming burning plasma tokamaks.Keywords
All Related Versions
This publication has 37 references indexed in Scilit:
- Overview of the TCV digital real-time plasma control system and its applicationsFusion Engineering and Design, 2024
- Overview of the SPARC tokamakJournal of Plasma Physics, 2020
- EU DEMO transient phases: Main constraints and heating mix studies for ramp-up and ramp-downFusion Engineering and Design, 2017
- Geometric formulas for system codes including the effect of negative triangularityFusion Engineering and Design, 2016
- ARC: A compact, high-field, fusion nuclear science facility and demonstration power plant with demountable magnetsFusion Engineering and Design, 2015
- Tokamak equilibrium reconstruction code LIUQE and its real time implementationFusion Engineering and Design, 2015
- Overview of EU DEMO design and R&D activitiesFusion Engineering and Design, 2014
- FBT - a free-boundary tokamak equilibrium code for highly elongated and shaped plasmasComputer Physics Communications, 1988
- Constrained Optimization and Lagrange Multiplier Methods1982
- System identification—A surveyAutomatica, 1971