Machine learning-based non-destructive measurement of bunch length at FRIB
Year: 2024
Type: conference-paper
Abstract: 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.
Source: JACOW
Authors: Wan,Jinyu, Plastun,Alexander, Ostroumov,Peter
Institutions: Facility for Rare Isotope Beams, Michigan State University
Language: English
Subfield: Aerospace Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W6944626839