Data-Driven Optimisation of Superconducting Magnets at CEA Paris-Saclay

Superconducting magnets for particle accelerators are particularly challenging to design because they involve a large number of coupled physical phenomena and the management of complex datasets. Artificial Intelligence, including machine learning and advanced optimisation techniques, offers promising approaches to address these challenges and accelerate the design process. This paper presents a new advanced optimisation and data management platform, together with its underlying software infrastructure and integration into design simulations. It also highlights several ongoing applications of advanced optimisation methods carried out at CEA Paris-Saclay, including multiphysics optimisation using active learning, topology optimisation, holistic modelling of an Electron Cyclotron Resonance (ERC) ion source, and anomaly detection in quench events.