Unsupervised Learning Techniques for Tune Cleaning Measurement

Precise measurements of tune and its stability are crucial for various optics analyses in the LHC, e.g. for the determination of the beta star using K-modulation. LHC BBQ system provides tune measurements online and stores the tune data. We apply unsupervised machine learning techniques on BBQ tune...

Descripción completa

Detalles Bibliográficos
Autores principales: García Morales, Hector, Fol, Elena, Tomás García, Rogelio
Lenguaje:eng
Publicado: JACoW 2021
Materias:
Accelerators and Storage Rings
Acceso en línea:https://dx.doi.org/10.18429/JACoW-IPAC2021-MOPAB184
http://cds.cern.ch/record/2808471
_version_ 1780973100252266496
author García Morales, Hector
Fol, Elena
Tomás García, Rogelio
author_facet García Morales, Hector
Fol, Elena
Tomás García, Rogelio
author_sort García Morales, Hector
collection CERN
description Precise measurements of tune and its stability are crucial for various optics analyses in the LHC, e.g. for the determination of the beta star using K-modulation. LHC BBQ system provides tune measurements online and stores the tune data. We apply unsupervised machine learning techniques on BBQ tune data in order to provide an automatic outlier detection method for better measurements of tune shifts and unexpected tune jitters.
id cern-2808471
institution Organización Europea para la Investigación Nuclear
language eng
publishDate 2021
publisher JACoW
record_format invenio
spelling cern-28084712022-05-04T20:45:03Zdoi:10.18429/JACoW-IPAC2021-MOPAB184http://cds.cern.ch/record/2808471engGarcía Morales, HectorFol, ElenaTomás García, RogelioUnsupervised Learning Techniques for Tune Cleaning MeasurementAccelerators and Storage RingsPrecise measurements of tune and its stability are crucial for various optics analyses in the LHC, e.g. for the determination of the beta star using K-modulation. LHC BBQ system provides tune measurements online and stores the tune data. We apply unsupervised machine learning techniques on BBQ tune data in order to provide an automatic outlier detection method for better measurements of tune shifts and unexpected tune jitters.JACoWoai:cds.cern.ch:28084712021
spellingShingle Accelerators and Storage Rings
García Morales, Hector
Fol, Elena
Tomás García, Rogelio
Unsupervised Learning Techniques for Tune Cleaning Measurement
title Unsupervised Learning Techniques for Tune Cleaning Measurement
title_full Unsupervised Learning Techniques for Tune Cleaning Measurement
title_fullStr Unsupervised Learning Techniques for Tune Cleaning Measurement
title_full_unstemmed Unsupervised Learning Techniques for Tune Cleaning Measurement
title_short Unsupervised Learning Techniques for Tune Cleaning Measurement
title_sort unsupervised learning techniques for tune cleaning measurement
topic Accelerators and Storage Rings
url https://dx.doi.org/10.18429/JACoW-IPAC2021-MOPAB184
http://cds.cern.ch/record/2808471
work_keys_str_mv AT garciamoraleshector unsupervisedlearningtechniquesfortunecleaningmeasurement
AT folelena unsupervisedlearningtechniquesfortunecleaningmeasurement
AT tomasgarciarogelio unsupervisedlearningtechniquesfortunecleaningmeasurement

Ejemplares similares