1–6 Jun 2025
Taipei International Convention Center (TICC)
Asia/Taipei timezone

Dynamic aperture prediction based on machine learning

WEPM065
4 Jun 2025, 16:00
2h
Exhibiton Hall A _Magpie (TWTC)

Exhibiton Hall A _Magpie

TWTC

Poster Presentation MC5.D02 Nonlinear Single Particle Dynamics Resonances, Tracking, Higher Order, Dynamic Aperture, Code Developments Wednesday Poster Session

Speaker

Jianhao Xu (University of Science and Technology of China)

Description

The dynamic aperture(DA) is one of the most important parameters of nonlinear beam dynamics in storage rings. It describes the transverse phase space region where the motion of a particle can remain stable. In the design and optimization of storage rings, long-term particle tracking is usually required to ensure an sufficient DA. However this process is very time consuming. This study explores the possibility of using machine learning methods for DA prediction. Firstly, several regression models from magnet strengths to resonance driving terms are constructed using different machine learning methods, showing that the use of machine learning can be applied to the nonlinear performance analysis of storage ring lattice. Then predictive regression models from magnet strength to DA are constructed, and the results show that artificial neural network have better prediction accuracy. The method will be further developed for nonlinear analysis and optimization of storage ring.

Region represented Asia
Paper preparation format LaTeX

Author

Jianhao Xu (University of Science and Technology of China)

Co-authors

Yuejing Huang (University of Science and Technology of China) Xiaoyu Liu (University of Science and Technology of China) Zhenghe Bai (University of Science and Technology of China) Lin Wang (University of Science and Technology of China)

Presentation materials

There are no materials yet.