ANL, Lemont, Illinois, USA
ATLAS (the Argonne Tandem Linac Accelerator Sys-tem) is a superconducting heavy ion accelerator which can accelerate nearly all stable, and some unstable, iso-topes between hydrogen and uranium. Prompt radiation fields from gamma and or neutron are typically below 1 rem/hr at 30 cm, but are permitted up to 300 rem/hr at 30 cm. The original ATLAS Radiation Interlock System (ARIS), hereafter referred to as ARIS 1.0 was installed 30 years ago. While it has been a functional critical safe-ty system, its age has exposed the facility to high risk of temporary shutdown due to failure of obsolete compo-nents. Topics discussed will be architecture, hardware improvements, functional improvements, and operation permitting personnel access to areas with low levels of radiation.
ANL, Lemont, Illinois, USA
The use of artificial intelligence can significantly reduce the time needed to tune an accelerator system such as the Argonne Tandem Linear Accelerator System (ATLAS) where a new beam is tuned once or twice a week. After establishing automatic data collection procedures and having analysed the data, machine learning models were developed and tested to tune subsections of the linac. Models based on Reinforcement Learning (RL) and Bayesian Optimization (BO) were developed, their respec-tive results are discussed and compared. RL and BO are well known AI techniques, often used for control systems. The results were obtained for a subsection of ATLAS that contains complex elements such as the radio-frequency quadrupole (RFQ). The models will be later generalized to the whole ATLAS linac, and similar models can be devel-oped for any accelerator with a modern control system.
