Author: Chen, Y.W.
Paper Title Page
THPAB311 Using Linear Regression to Model the Parameters of the Flat Wires in TLS-EPU56 4399
 
  • S.J. Huang, Y.H. Chang, T.Y. Chung
    NSRRC, Hsinchu, Taiwan
  • Y.W. Chen
    Academia Sinica, Taipei, Taiwan
 
  Although a theoretical calculation might predict the set currents of the flat wires, which are used to compensate the deviation in the Betatron tune caused by the elliptically polarized undulator (EPU), those set currents must still be tuned in reality. To approach this reality, a strategy of Machine Learning was adopted, which included collecting real-condition data and using a linear-regression model to adjust the parameters of the flat wires. After training the model, the predictions in variables tune x, tune y and beam size x were compared with the required amount of correction of the EPU at various gaps and phases. To prove the feasibility of this method, a test was performed under the real conditions of accelerator Taiwan Light Source (TLS).  
poster icon Poster THPAB311 [1.226 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-THPAB311  
About • paper received ※ 13 May 2021       paper accepted ※ 28 June 2021       issue date ※ 30 August 2021  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)