Show simple item record

dc.contributor.author
Li, Sichen
dc.contributor.author
Zacharias, Mélissa
dc.contributor.author
Snuverink, Jochem
dc.contributor.author
Coello de Portugal, Jaime
dc.contributor.author
Pérez-Cruz, Fernando
dc.contributor.author
Reggiani, Davide
dc.contributor.author
Adelmann, Andreas
dc.date.accessioned
2021-04-19T16:00:35Z
dc.date.available
2021-04-02T02:49:54Z
dc.date.available
2021-04-19T16:00:35Z
dc.date.issued
2021-03
dc.identifier.issn
2078-2489
dc.identifier.other
10.3390/info12030121
en_US
dc.identifier.uri
http://hdl.handle.net/20.500.11850/477339
dc.identifier.doi
10.3929/ethz-b-000477339
dc.description.abstract
The beam interruptions (interlocks) of particle accelerators, despite being necessary safety measures, lead to abrupt operational changes and a substantial loss of beam time. A novel time series classification approach is applied to decrease beam time loss in the High-Intensity Proton Accelerator complex by forecasting interlock events. The forecasting is performed through binary classification of windows of multivariate time series. The time series are transformed into Recurrence Plots which are then classified by a Convolutional Neural Network, which not only captures the inner structure of the time series but also uses the advances of image classification techniques. Our best-performing interlock-to-stable classifier reaches an Area under the ROC Curve value of 0.71±0.01 compared to 0.65±0.01 of a Random Forest model, and it can potentially reduce the beam time loss by 0.5±0.2 s per interlock.
en_US
dc.format
application/pdf
en_US
dc.language.iso
en
en_US
dc.publisher
MDPI
en_US
dc.rights.uri
http://creativecommons.org/licenses/by/4.0/
dc.subject
time series classification
en_US
dc.subject
recurrence plot
en_US
dc.subject
convolutional neural network
en_US
dc.subject
random forest
en_US
dc.subject
charged particle accelerator
en_US
dc.title
A novel approach for classification and forecasting of time series in particle accelerators
en_US
dc.type
Journal Article
dc.rights.license
Creative Commons Attribution 4.0 International
dc.date.published
2021-03-12
ethz.journal.title
Information
ethz.journal.volume
12
en_US
ethz.journal.issue
3
en_US
ethz.pages.start
121
en_US
ethz.size
21 p.
en_US
ethz.version.deposit
publishedVersion
en_US
ethz.identifier.wos
ethz.identifier.scopus
ethz.publication.place
Basel
en_US
ethz.publication.status
published
en_US
ethz.date.deposited
2021-04-02T02:50:02Z
ethz.source
SCOPUS
ethz.eth
yes
en_US
ethz.availability
Open access
en_US
ethz.rosetta.installDate
2021-04-19T16:00:47Z
ethz.rosetta.lastUpdated
2022-03-29T06:39:13Z
ethz.rosetta.versionExported
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=A%20novel%20approach%20for%20classification%20and%20forecasting%20of%20time%20series%20in%20particle%20accelerators&rft.jtitle=Information&rft.date=2021-03&rft.volume=12&rft.issue=3&rft.spage=121&rft.issn=2078-2489&rft.au=Li,%20Sichen&Zacharias,%20M%C3%A9lissa&Snuverink,%20Jochem&Coello%20de%20Portugal,%20Jaime&P%C3%A9rez-Cruz,%20Fernando&rft.genre=article&rft_id=info:doi/10.3390/info12030121&
 Search print copy at ETH Library

Files in this item

Thumbnail

Publication type

Show simple item record