JACoW logo

Joint Accelerator Conferences Website

The Joint Accelerator Conferences Website (JACoW) is an international collaboration that publishes the proceedings of accelerator conferences held around the world.


BiBTeX citation export for MOVIR11: Applying Machine Learning to Stabilize the Source Size in the ALS Storage Ring

@unpublished{leemann:ipac2020-movir11,
  author       = {S.C. Leemann and W.E. Byrne and D.P. Cuneo and M.P. Ehrlichman and T. Hellert and A. Hexemer and Y. Lu and M. Marcus and C.N. Melton and H. Nishimura and G. Penn and F. Sannibale and D.A. Shapiro and C. Sun and D. Ushizima and M. Venturini and E.J. Wallén},
% author       = {S.C. Leemann and W.E. Byrne and D.P. Cuneo and M.P. Ehrlichman and T. Hellert and A. Hexemer and others},
% author       = {S.C. Leemann and others},
  title        = {{Applying Machine Learning to Stabilize the Source Size in the ALS Storage Ring}},
  booktitle    = {Proc. IPAC'20},
  language     = {english},
  intype       = {presented at the},
  series       = {International Particle Accelerator Conference},
  number       = {11},
  venue        = {Caen, France},
  publisher    = {JACoW Publishing, Geneva, Switzerland},
  month        = {oct},
  year         = {2020},
  note         = {presented at IPAC2020 in Caen, France, unpublished},
  abstract     = {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.},
}