JACoW logo

Journals of Accelerator Conferences Website (JACoW)

JACoW is a publisher in Geneva, Switzerland that publishes the proceedings of accelerator conferences held around the world by an international collaboration of editors.


RIS citation export for TH1I2: Reinforcement Learning and Bayesian Optimization for Ion Linac Operations

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  -