AI-Based Control of Differential Vacuum in the MuVacAS Prototype for IFMIF–DONES Particle Accelerator

Abstract

Developing materials capable of withstanding extreme irradiation is a fundamental challenge for realizing nuclear fusion as a sustainable energy source. The IFMIF–DONES facility, currently under construction, will address this need by producing a fusion-relevant neutron flux using a high-power deuteron beam striking a flowing lithium target, enabling accelerated qualification of candidate structural materials. Validating the accelerator and target technologies requires precise control of the ultra-high-vacuum region near the lithium surface, yet direct pressure sensing in this irradiated zone is challenging and conventional controllers can struggle with the associated nonlinear gas-flow dynamics. As part of the DONES–FLUX project, this work introduces a data-driven workflow for indirect pressure estimation and autonomous regulation in the MuVacAS prototype, a dedicated experimental platform that reproduces the final beamline section of IFMIF–DONES. Two Fourier Neural Operator surrogate models are learned from real data: one serves as a virtual sensor to infer chamber pressure from upstream readings, while the other models system dynamics to provide a safe, fast training environment for a Deep Reinforcement Learning controller. The trained agent uses virtual-sensor feedback during deployment and reliably regulates argon injection across operating scenarios, including conditions not seen during training. Experimental campaigns show that the RL-based controller yields promising control results, achieving stable regulation without manual retuning. These results demonstrate a viable pathway for deploying advanced learning-based control in fusion-relevant accelerator systems, supporting the operational readiness of IFMIF–DONES and future fusion technology infrastructures.