Contribution to a conference proceedings/Contribution to a book

PUBDB-2022-02796

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Accelerating Linear Beam Dynamics Simulations for Machine Learning Applications

Stein, O. (Corresponding author)DESY* ; Agapov, I.DESY* ; Eichler, A.XFEL.EU*DESY* ; Kaiser, J.DESY*

2022
JACoW Publishing, Geneva, Switzerland [Geneva]
ISBN: 978-3-95450-227-1

This record in other databases:  

Please use a persistent id in citations: doi:10.18429/JACoW-IPAC2022-WEPOMS036  doi:10.3204/PUBDB-2022-02796

Abstract: 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.

Keyword(s): Accelerator Physics ; MC5: Beam Dynamics and EM Fields ; simulation ; space-charge ; controls ; GPU ; experiment

Note: Literaturangaben;

---

Contributing Institute(s):

1. Strahlkontrollen (MSK)
2. Beschleunigerphysik (MPY)
3. Strahlenschutz (D3)

Research Program(s):

1. 621 - Accelerator Research and Development (POF4-621) (POF4-621)
2. ZT-I-PF-5-6 - Autonomous Accelerator (AA) (2020_ZT-I-PF-5-6) (2020_ZT-I-PF-5-6)

Experiment(s):

1. No specific instrument

Appears in the scientific report 2022

---

Database coverage:
;

---