Speaker
Jinyu Wan
(Facility for Rare Isotope Beams)
Description
A machine learning-based virtual diagnostic method for measuring the longitudinal phase space is proposed. Utilizing multiple measurements of bunch length from the Facility for Rare Isotope Beams (FRIB) accelerator, beam parameters are fitted with a concrete simulation model. A neural network model is trained to learn the correlations between the signals from beam position monitors (BPMs) and the bunch length. This model enables the rapid prediction of bunch length at BPM locations without compromising beam quality.
Funding Agency
Work supported by the U.S. Department of Energy using resources of the Facility for Rare Isotope Beams, a DOE Office of Science User Facility, under Award Number DE-SC0023633.
Primary authors
Jinyu Wan
(Facility for Rare Isotope Beams)
Alexander Plastun
(Facility for Rare Isotope Beams, Michigan State University)
Peter Ostroumov
(Facility for Rare Isotope Beams, Michigan State University)
