Active Disruption Avoidance and Trajectory Design for Tokamak Ramp-downs with Neural Differential Equations and Reinforcement Learning

arXiv:2402.09387v1 Announce Type: cross
Abstract: The tokamak offers a promising path to fusion energy, but plasma disruptions pose a major economic risk, motivating considerable advances in disruption avoidance. This work develops a reinforcement learning approach to this problem by training a policy to safely ramp-down the plasma current while avoiding limits on a number of quantities correlated with disruptions. The policy training environment is a hybrid physics and machine learning model trained on simulations of the SPARC primary reference discharge …

abstract advances arxiv cs.lg design differential disruption economic energy fusion major path physics.plasm-ph plasma policy ramp reinforcement reinforcement learning risk tokamak training trajectory type work