IPAC2019 - List of Authors (Melton, C.N.)

Paper	Title	Page
TUPGW094	First Attempts at Applying Machine Learning to ALS Storage Ring Stabilization	1631
	S.C. Leemann, Ph. Amstutz, M.P. Ehrlichman, T. Hellert, A. Hexemer, S. Liu, M. Marcus, C.N. Melton, H. Nishimura, G. Penn, F. Sannibale, D.A. Shapiro, C. Sun, D. Ushizima, M. Venturini LBNL, Berkeley, California, USA
	Funding: This research is funded by 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. The ALS storage ring operates multiple feedbacks and feed-forwards during user operations to ensure that various source properties such as beam position, beam angle, and beam size are maintained constant. Without these active corrections, strong perturbations of the electron beam would result from constantly varying ID gaps and phases. An important part of the ID gap/phase compensation requires recording feed-forward tables. While recording such tables takes a lot of time during dedicated machine shifts, the resulting compensation data is imperfect due to machine drift both during and after recording of the table. Since it is impractical to repeat recording feed-forward tables on a more frequent basis, we have decided to employ Machine Learning techniques to improve ID compensation in order to stabilize electron beam properties at the source points.
DOI •	reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2019-TUPGW094
About •	paper received ※ 14 May 2019 paper accepted ※ 22 May 2019 issue date ※ 21 June 2019
Export •	reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)

Paper

Title

Page

First Attempts at Applying Machine Learning to ALS Storage Ring Stabilization

1631

S.C. Leemann, Ph. Amstutz, M.P. Ehrlichman, T. Hellert, A. Hexemer, S. Liu, M. Marcus, C.N. Melton, H. Nishimura, G. Penn, F. Sannibale, D.A. Shapiro, C. Sun, D. Ushizima, M. Venturini
LBNL, Berkeley, California, USA

Funding: This research is funded by 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.
The ALS storage ring operates multiple feedbacks and feed-forwards during user operations to ensure that various source properties such as beam position, beam angle, and beam size are maintained constant. Without these active corrections, strong perturbations of the electron beam would result from constantly varying ID gaps and phases. An important part of the ID gap/phase compensation requires recording feed-forward tables. While recording such tables takes a lot of time during dedicated machine shifts, the resulting compensation data is imperfect due to machine drift both during and after recording of the table. Since it is impractical to repeat recording feed-forward tables on a more frequent basis, we have decided to employ Machine Learning techniques to improve ID compensation in order to stabilize electron beam properties at the source points.

DOI •

reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2019-TUPGW094

About •

paper received ※ 14 May 2019 paper accepted ※ 22 May 2019 issue date ※ 21 June 2019

Export •

reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)