A machine-learning based closed orbit feedback for a synchrotron light source

Abstract

In order to improve the stability of synchrotron radiation, we developed a new method of machine learning-based closed orbit feedback, and piloted it in the storage ring of the Shanghai Synchrotron Radiation Facility (SSRF). In our experiments, the machine learning-based closed orbit feedback can carry out horizontal, vertical and RF main frequency feedback simultaneously. What's more, the residual values of variations in the correctors' currents before vs. after correction can be almost ignored. This machine learning-based new method is expected to establish a new closed orbit feedback system and improve the orbit stability of the storage ring in daily operation.