TY  - CONF
AU  - Stein, Oliver
AU  - Agapov, Ilya
AU  - Eichler, Annika
AU  - Kaiser, Jan
TI  - Accelerating Linear Beam Dynamics Simulations for Machine Learning Applications
CY  - [Geneva]
PB  - JACoW Publishing, Geneva, Switzerland
M1  - PUBDB-2022-02796
SN  - 978-3-95450-227-1
SP  - 2330-2333
PY  - 2022
N1  - Literaturangaben;
AB  - Machine learning has proven to be a powerful tool with many applications in the field of accelerator physics. Training machine learning models is a highly iterative process that requires large numbers of samples. However, beam time is often limited and many of the available simulation frameworks are not optimized for fast computation. As a result, training complex models can be infeasible. In this contribution, we introduce Cheetah, a linear beam dynamics framework optimized for fast computations. We show that Cheetah outperforms existing simulation codes in terms of speed and furthermore demonstrate the application of Cheetah to a reinforcement-learning problem as well as the successful transfer of the Cheetah-trained model to the real world. We anticipate that Cheetah will allow for faster development of more capable machine learning solutions in the field, one day enabling the development of autonomous accelerators.
T2  - 13th International Particle Accelerator Conference
CY  - 12 Jun 2022 - 17 Jun 2022, Bangkok (Thailand)
Y2  - 12 Jun 2022 - 17 Jun 2022
M2  - Bangkok, Thailand
KW  - Accelerator Physics (Other)
KW  - MC5: Beam Dynamics and EM Fields (Other)
KW  - simulation (autogen)
KW  - space-charge (autogen)
KW  - controls (autogen)
KW  - GPU (autogen)
KW  - experiment (autogen)
LB  - PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
DO  - DOI:10.18429/JACoW-IPAC2022-WEPOMS036
UR  - https://bib-pubdb1.desy.de/record/478846
ER  -