Author: Ehrlichman, M.P.
Paper Title Page
Applying Machine Learning to Stabilize the Source Size in the ALS Storage Ring  
  • S.C. Leemann, W.E. Byrne, D.P. Cuneo, M.P. Ehrlichman, T. Hellert, A. Hexemer, Y. Lu, M. Marcus, C.N. Melton, H. Nishimura, G. Penn, F. Sannibale, D.A. Shapiro, C. Sun, D. Ushizima, M. Venturini, E.J. Wallén
    LBNL, Berkeley, California, USA
  Funding: This research is funded by the US Department of Energy (BES & ASCR Programs) and supported by the Director of the Office of Science of the US Department of Energy under Contract No. DEAC02-05CH11231.
In state-of-the-art synchrotron light sources the overall source stability is presently limited by the achievable level of electron beam size stability. This source size stability is presently on the few-percent level, which is still 1–2 orders of magnitude larger than already demonstrated stability of source position/angle (slow/fast orbit feedbacks) and current (top-off injection). Until now source size stabilization has been achieved through corrections based on a combination of static predetermined physics models and lengthy calibration measurements (feed-forward tables), periodically repeated to counteract drift in the accelerator and instrumentation. We now demonstrate for the first time* how application of machine learning allows for a physics- and model-independent stabilization of source size relying only on previously existing instrumentation in ALS. Such feed-forward correction based on neural networks that can be continuously online-retrained achieves source size stability as low as 0.2 microns rms (0.4%) which results in overall source stability approaching the sub-percent noise floor of the most sensitive experiments.
*Phys. Rev. Lett. 123, 194801 (2019)
video icon
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)