The complexity of the GSI/FAIR accelerator facility demands a high level of automation in order to maximize time for physics experiments. Accelerator laboratories world-wide are exploring a large variety of techniques to achieve this, from classical optimization to reinforcement learning. This paper reports on the first results of using Geoff at GSI for automatic optimization of various beam manipulations. Geoff (Generic Optimization Framework & Frontend) is an open-source framework that harmonizes access to the above automation techniques and simplifies the transition towards and between them. It is maintained as part of the EURO-LABS project in cooperation between CERN and GSI. In dedicated beam experiments, the beam loss of the multi-turn injection into the SIS18 synchrotron has been reduced from 40% to 10% in about 15 minutes, where manual adjustment can take up to 2 hours. Geoff has also been used successfully at the GSI Fragment Separator (FRS) for beam steering. Further experimental activities include closed orbit correction for specific broken-symmetry high-transition-energy SIS18 optics with Bayesian optimization in comparison to traditional SVD-based correction.

The CERN Super Proton Synchrotron (SPS) offers slow-extracted, high-intensity proton beams at 400 GeV/c for 3 fixed targets in the CERN North Experimental Area (NA) with a spill length of about 5 seconds. Since first commissioning in the late seventies, the NA has seen a steady increase in users, many of which requiring improved spill quality control. Slow extraction is sensitive to small perturbations with the effect of reduced spill quality. While some of these effects have been addressed in recent years, continuous compensation of intensity fluctuations at 50 Hz harmonics originating from power converter ripple has been particularly difficult to achieve. In 2023, the deployment of two techniques - "Empty-Bucket Channeling" and active control with Adaptive Bayesian Optimization – resulted in a significant suppression of these intensity modulations. This paper focuses on using Adaptive Bayesian Optimization for 50 Hz harmonic control. The chosen algorithm is described, together with details of integration in the CERN control system. The 2023 results are presented and complemented with an overview of the next steps.

In accelerator labs like GSI/FAIR, automating complex systems is key for maximizing physics experiment time. This study explores the application of a data-driven model predictive control (MPC) to refine the multi-turn injection (MTI) process into the SIS18 synchrotron, departing from conventional numerical optimization methods. MPC is distinguished by its reduced number of optimization steps and superior ability to control performance criteria, effectively addressing issues like delayed outcomes and safety concerns, including septum protection. The study focuses on a highly sample-efficient MPC approach based on Gaussian processes, which lies at the intersection of model-based reinforcement learning and control theory. This approach merges the strengths of both fields, offering a unified and optimized solution and yielding a safe and fast state-based optimization approach beyond classical reinforcement learning and Bayesian optimization. Our study lays the groundwork for enabling safe online training for the SS18 MTI issue, showing great potential for applying data-driven control in similar scenarios.