Ядерна фізика та енергетика Nuclear Physics and Atomic Energy   ISSN: 1818-331X (Print), 2074-0565 (Online)   Publisher: Institute for Nuclear Research of the National Academy of Sciences of Ukraine   Languages: Ukrainian, English   Periodicity: 4 times per year   Open access peer reviewed journal

Full text (ua)

D. Klekots¹, O. Bezshyyko¹, L. Golinka-Bezshyyko^1,*, V. Kubytskyi², I. Chaikovska<sup>2

1</sup> Taras Shevchenko National University of Kyiv,, Kyiv, Ukraine
² University Paris-Saclay, National Institute for Nuclear and Particle Physics, Laboratory of the Physics of the Two Infinities Irène Joliot-Curie, Orsay, France

^*Corresponding author. E-mail address: lyalkagb@gmail.com

Abstract: The linear optics parameters are one of the most significant properties of the beam, which are controlled at the particle accelerators. Classical methods of analysis, such as component-independent analysis, employ turn-by-turn readings of the beam position monitors. As an alternative to the component-independent analysis, machine learning and neural networks are proposed for determining the beam parameters. This approach relies on the same input data as classical algorithms. This work shows training and usage of the neural network for analysis of the data from the collector ring of the ThomX accelerator facility.

Keywords: linear beam optics, beam position monitor, neural networks, machine learning.

1. X. Huang. Principal component analysis (PCA). In: Beam-Based Correction and Optimization for Accelerators (Taylor & Francis Group, 2020) p. 131. Article

2. X. Huang et al. Application of independent component analysis to Fermilab Booster. Phys. Rev. ST Accel. Beams 8 (2005) 064001. https://doi.org/10.1103/PhysRevSTAB.8.064001

3. X. Yang, X. Huang. A method for simultaneous linear optics and coupling correction for storage rings with turn-by-turn beam position monitor data. Nucl. Instrum. Methods A 828 (2016) 97. https://doi.org/10.1016/j.nima.2016.05.020

4. A. Variola et al. ThomX Technical Design Report. LAL / RT 14-21. Laboratoire de l´accélérateur linéaire (2014) 164 p. https://in2p3.hal.science/file/index/docid/971281/filename/TDR_ThomX.pdf

5. V. Kubytskyi et al. Commissioning of the ThomX Storage Ring. J. Phys.: Conf. Ser. 2687 (2024) 032031. https://doi.org/10.1088/1742-6596/2687/3/032031

6. M. Abadi et al. TensorFlow: Large-scale machine learning on heterogeneous systems. arXiv:1603.04467v2 [cs.DC] (2016). https://doi.org/10.48550/arXiv.1603.04467

7. D.P. Kingma, J. Ba. Adam: A Method for Stochastic Optimization. arXiv:1412.6980v9 [cs.LG] (2017). https://doi.org/10.48550/arXiv.1412.6980