Autonomous Pressure Control in MuVacAS via Deep Reinforcement Learning and Deep Learning Surrogate Models
Abstract
The development of nuclear fusion requires materials that can withstand extreme conditions. The IFMIF-DONES facility, a high-power particle accelerator, is being designed to qualify these materials. A critical testbed for its development is the MuVacAS prototype, which replicates the final segment of the accelerator beamline. Precise regulation of argon gas pressure within its ultra-high vacuum chamber is vital for this task. This work presents a fully data-driven approach for autonomous pressure control. A Deep Learning Surrogate Model, trained on real operational data, emulates the dynamics of the argon injection system. This high-fidelity digital twin then serves as a fast-simulation environment to train a Deep Reinforcement Learning agent. The results demonstrate that the agent successfully learns a control policy that maintains gas pressure within strict operational limits despite dynamic disturbances. This approach marks a significant step toward the intelligent, autonomous control systems required for the demanding next-generation particle accelerator facilities.
Keywords
Cite
@article{arxiv.2512.15521,
title = {Autonomous Pressure Control in MuVacAS via Deep Reinforcement Learning and Deep Learning Surrogate Models},
author = {Guillermo Rodriguez-Llorente and Galo Gallardo and Rodrigo Morant Navascués and Nikita Khvatkin Petrovsky and Anderson Sabogal and Roberto Gómez-Espinosa Martín},
journal= {arXiv preprint arXiv:2512.15521},
year = {2025}
}
Comments
13 pages, 7 figures, included in Machine Learning and the Physical Sciences Workshop @ NeurIPS 2025