Boost of ALPI superconducting linac performances using AI techniques
The heavy ion superconductive linac ALPI has been operating at the Legnaro National Laboratories since its completion in the 1990s. As the first generation in Europe, it featured several innovative techniques and design weaknesses, such as very small transverse and longitudinal acceptances. This led to long setting times and low transmission rates of 35%, compared to 93% obtained using simulations. Additionally, the machine experienced instabilities, requiring frequent accelerator retuning. From 2011 to 2024, an extensive beam dynamics studies program was conducted, culminating in the introduction of Artificial Intelligence techniques in 2022-2024. These techniques made it possible to accelerate the accelerator setup, counteract instabilities and reach the nominal transmission of the linac, about 85%, in June 2024, 32 years after its construction. This paper presents the AI techniques involved, the studies performed, and how they impact routine operations.
Publication Details
- Journal
- JACOW
- Published
- 2025-10-14
- DOI
- https://doi.org/10.18429/jacow-hiat2025-tux05
- Primary Topic
- Particle accelerators and beam dynamics
- Type
- article
- Field-Weighted Citation Impact
- 0.00