Document Type : Research Paper

Authors

• Mohammad Sadegh Yazdani ¹
• seyed farhad masoudi ¹
• Javad ًRahighi ²
• Sara Dastan ³

¹ Physics Department, KN Toosi University of Technology

² Iranian Light Source Facility (ILSF), Institute of research in fundamental Sciences (IPM), P.O. Box: 19395-5746, Tehran – Iran

³ Elettra Sincrotrone Trieste

Abstract

In recent years, the advance of electron synchrotron light sources has been of central importance to synchrotron radiation users. In particular, improving electron beam qualities such as beam stability and intensity has been pivotal to the generation of high-brightness photon beams. As a result, in order to achieve a brighter photon beam, electron synchrotron accelerators have been undergoing significant changes in design. A crucial aspect of their design is precise control of particle trajectories and correction of any errors to achieve a stable electron beam and, consequently, a high-intensity photon beam. One intriguing approach in this field is the use of neural networks for correcting the electron beam position in the storage ring; a process commonly known as beam control. In this study, a convolutional neural network model has been developed to control the ELETTRA 2.0 storage ring (a synchrotron light source in Italy) for the first time. The performance of this model, based on machine learning techniques, is about 6% better than the ISVD method, while benefiting from its high robustness to real-world data.

Keywords

• Machine Learning
• Convolutional Neural Network
• Artificial Neural Controller
• Orbit Control
• Elettra 2.0 Storage Ring

Main Subjects

• PARTICLE ACCELERATORS