JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.
TY - CONF AU - Martinez Marin, J.L. AU - Blomberg, B.R. AU - Bunnell, K.J. AU - Dunn, G.M. AU - Letcher, E. AU - Mustapha, B. AU - Stanton, D. ED - Herfurth, Frank ED - Schaa, Volker RW TI - Reinforcement Learning and Bayesian Optimization for Ion Linac Operations J2 - Proc. of HIAT2022, Darmstadt, Germany, 27 June-01 July 2022 CY - Darmstadt, Germany T2 - International Conference on Heavy Ion Accelerator Technology T3 - 15 LA - english AB - 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. PB - JACoW Publishing CP - Geneva, Switzerland SP - 130 EP - 135 KW - controls KW - simulation KW - quadrupole KW - rfq KW - experiment DA - 2022/08 PY - 2022 SN - 2673-5547 SN - 978-3-95450-240-0 DO - doi:10.18429/JACoW-HIAT2022-TH1I2 UR - https://jacow.org/hiat2022/papers/th1i2.pdf ER -