Author: Coello de Portugal, J.M.
Paper Title Page
TUOA02 Application of Machine Learning to Beam Diagnostics 169
 
  • E. Fol, J.M. Coello de Portugal, R. Tomás
    CERN, Geneva, Switzerland
 
  Machine learning techniques are used in various scientific and industry fields as a powerful tool for data analysis and automatization. The presentation is devoted to exploration of relevant machine learning methods for beam diagnostics. The target is to provide an insight into modern machine learning techniques, which can be applied to improve current beam diagnostics and general applications in accelerators. Possible concepts for future applications are also presented.  
slides icon Slides TUOA02 [2.497 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IBIC2018-TUOA02  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)  
 
TUOB02 Optics Measurements in Storage Rings: Simultaneous 3-Dimensional Beam Excitation and Novel Harmonic Analysis 177
 
  • L. Malina, J.M. Coello de Portugal, J. Dilly, P.K. Skowroński, R. Tomás
    CERN, Geneva, Switzerland
 
  Optics measurements in storage rings employ turn-by-turn data of transversely excited beams. Chromatic parameters need measurements to be repeated at different beam energies, which is time-consuming. We present an optics measurement method based on adiabatic simultaneous 3-dimensional beam excitation, where no repetition at different energies is needed. In the LHC, the method has been successfully demonstrated utilising AC-dipoles combined with RF frequency modulation. It allows measuring the linear optics parameters and chromatic properties at the same time without resolution deterioration. We also present a new accurate harmonic analysis algorithm that exploits the noise cleaning based on singular value decomposition to compress the input data. In the LHC, this sped up harmonic analysis by a factor up to 300. These methods are becoming a "push the button" operational tool to measure the optics.  
slides icon Slides TUOB02 [1.117 MB]  
DOI • reference for this paper ※ https://doi.org/10.18429/JACoW-IBIC2018-TUOB02  
Export • reference for this paper using ※ BibTeX, ※ LaTeX, ※ Text/Word, ※ RIS, ※ EndNote (xml)