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.

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

AU  - Leemann, S.C.
AU  - Byrne, W.E.
AU  - Cuneo, D.P.
AU  - Ehrlichman, M.P.
AU  - Hellert, T.
AU  - Hexemer, A.
AU  - Lu, Y.
AU  - Marcus, M.
AU  - Melton, C.N.
AU  - Nishimura, H.
AU  - Penn, G.
AU  - Sannibale, F.
AU  - Shapiro, D.A.
AU  - Sun, C.
AU  - Ushizima, D.
AU  - Venturini, M.
AU  - Wallén, E.J.
ED  - Seidel, Mike
ED  - Aßmann, Ralph W.
ED  - Chautard, Frédéric
ED  - Schaa, Volker R.W.
TI  - Applying Machine Learning to Stabilize the Source Size in the ALS Storage Ring
J2  - Proc. of IPAC2020, Caen, France, 10-15 May 2020
CY  - Caen, France
T2  - International Particle Accelerator Conference
T3  - 11
LA  - english
AB  - 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.
PB  - JACoW Publishing
CP  - Geneva, Switzerland
ER  -