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.

Title Achieving Optimal Control of LLRF Control System with Artificial Intelligence
  • R. Pirayesh, S. Biedron, J.A. Diaz Cruz, M. Martinez-Ramon, S.I. Sosa Guitron
    University of New Mexico, Albuquerque, New Mexico, USA
Abstract Artificial Intelligence is a versatile tool to make machines learn the characteristics of a device or a system. In this research, we will be investigating applying deep learning and Gaussian process learning to make a machine learn the optimal settings of a low-level RF (LLRF) control system for particle accelerators. These settings include the multiple controllers’ parameters and the parameters of the LLRF that result in an optimal target function applied to the LLRF. Finding this target function, finding the right machine learning algorithm with the lowest error, and finding the best controller that result in the most optimal target function is the goal of this research.
Paper download MOPHA114.PDF [0.831 MB / 5 pages]
Poster download MOPHA114_POSTER.PDF [0.847 MB]
Export download ※ BibTeX LaTeXText/WordRISEndNote
Conference ICALEPCS2019
Series International Conference on Accelerator and Large Experimental Physics Control Systems (17th)
Location New York, NY, USA
Date 05-11 October 2019
Publisher JACoW Publishing, Geneva, Switzerland
Editorial Board Karen S. White (ORNL, Oak Ridge, TN, USA); Kevin A. Brown (BNL, Upton, NY, USA); Philip S. Dyer (BNL, Upton, NY, USA); Volker RW Schaa (GSI, Darmstadt, Germany)
Online ISBN 978-3-95450-209-7
Online ISSN 2226-0358
Received 09 October 2019
Accepted 10 October 2019
Issue Date 30 August 2020
DOI doi:10.18429/JACoW-ICALEPCS2019-MOPHA114
Pages 488-492
Creative Commons CC logoPublished by JACoW Publishing under the terms of the Creative Commons Attribution 3.0 International license. Any further distribution of this work must maintain attribution to the author(s), the published article's title, publisher, and DOI.