Autonomous Pressure Control in MuVacAS via Deep Reinforcement Learning and Deep Learning Surrogate Models
By: Guillermo Rodriguez-Llorente , Galo Gallardo , Rodrigo Morant Navascués and more
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.
Similar Papers
Nuclear Microreactor Control with Deep Reinforcement Learning
Systems and Control
Makes tiny nuclear power plants run smarter.
Enhancing Nuclear Reactor Core Simulation through Data-Based Surrogate Models
Machine Learning (CS)
Makes nuclear power plants adjust to renewable energy.
Machine Learning-Integrated Hybrid Fluid-Kinetic Framework for Quantum Electrodynamic Laser Plasma Simulations
Plasma Physics
Makes laser-plasma simulations faster and more accurate.