A machine-learning based closed orbit feedback for the SSRF storage ring

TL;DR

This paper introduces a machine learning-based closed orbit feedback method for the SSRF storage ring, demonstrating improved stability, faster convergence, and reduced residual errors compared to traditional systems.

Contribution

The paper presents a novel machine learning approach for closed orbit feedback that enhances stability and convergence speed in synchrotron storage rings.

Findings

Better convergence and speed than traditional SOFB

Simultaneous horizontal, vertical, and RF frequency feedback

Residual corrector current variations are negligible

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, not only can the machine learning-based closed orbit feedback carry out horizontal, vertical and RF frequency feedback simultaneously, but it also has better convergence and convergence speed than the traditional Slow Orbit Feed Back (SOFB) system. What's more, the residual values of the correctors' currents variations 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.