Author: Pieloni, T.
Paper Title Page
TUPAB216 Modeling Particle Stability Plots for Accelerator Optimization Using Adaptive Sampling 1923
 
  • M. Schenk, L. Coyle, T. Pieloni
    EPFL, Lausanne, Switzerland
  • M. Giovannozzi, A. Mereghetti
    CERN, Meyrin, Switzerland
  • E. Krymova, G. Obozinski
    SDSC, Lausanne, Switzerland
  
  Funding: This work is partially funded by the Swiss Data Science Center (SDSC), project C18-07.
One key as­pect of ac­cel­er­a­tor op­ti­miza­tion is to max­i­mize the dy­namic aper­ture (DA) of a ring. Given the num­ber of ad­justable pa­ra­me­ters and the com­pute-in­ten­sity of DA sim­u­la­tions, this task can ben­e­fit sig­nif­i­cantly from ef­fi­cient search al­go­rithms of the avail­able pa­ra­me­ter space. We pro­pose to grad­u­ally train and im­prove a sur­ro­gate model of the DA from Six­Track sim­u­la­tions while ex­plor­ing the pa­ra­me­ter space with adap­tive sam­pling meth­ods. Here we re­port on a first model of the par­ti­cle sta­bil­ity plots using con­vo­lu­tional gen­er­a­tive ad­ver­sar­ial net­works (GAN) trained on a sub­set of Six­Track nu­mer­i­cal sim­u­la­tions for dif­fer­ent ring con­fig­u­ra­tions of the Large Hadron Col­lider at CERN. 		 
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-TUPAB216  
About • paper received ※ 19 May 2021       paper accepted ※ 17 June 2021       issue date ※ 22 August 2021  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
THPAB260 Detection and Classification of Collective Beam Behaviour in the LHC 4318
 
  • L. Coyle, F. Blanc, T. Pieloni, M. Schenk
    EPFL, Lausanne, Switzerland
  • X. Buffat, M. Solfaroli Camillocci, J. Wenninger
    CERN, Meyrin, Switzerland
  • E. Krymova, G. Obozinski
    SDSC, Lausanne, Switzerland
  
  Col­lec­tive in­sta­bil­i­ties can lead to a se­vere de­te­ri­o­ra­tion of beam qual­ity, in terms of re­duced beam in­ten­sity and in­creased beam emit­tance, and con­se­quently a re­duc­tion of the col­lider’s lu­mi­nos­ity. It is there­fore cru­cial for the op­er­a­tion of the CERN’s Large Hadron Col­lider to un­der­stand the con­di­tions in which they ap­pear in order to find ap­pro­pri­ate mit­i­ga­tion mea­sures. Using bunch-by-bunch and turn-by-turn beam am­pli­tude data, cour­tesy of the trans­verse damper’s ob­ser­va­tion box (Ob­s­Box), a novel ma­chine learn­ing based ap­proach is de­vel­oped to both de­tect and clas­sify these in­sta­bil­i­ties. By train­ing an au­toen­coder neural net­work on the Ob­s­Box am­pli­tude data and using the model’s re­con­struc­tion error, in­sta­bil­i­ties and other phe­nom­ena are sep­a­rated from nom­i­nal beam be­hav­iour. Ad­di­tion­ally, the la­tent space en­cod­ing of this au­toen­coder of­fers a unique image like rep­re­sen­ta­tion of the beam am­pli­tude sig­nal. Lever­ag­ing this la­tent space rep­re­sen­ta­tion al­lows us to clus­ter the var­i­ous types of anom­alous sig­nals.  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IPAC2021-THPAB260  
About • paper received ※ 19 May 2021       paper accepted ※ 19 July 2021       issue date ※ 27 August 2021  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)