In EDS ansehen

A data-driven algorithm to predict throughput bottlenecks in a production system based on active periods of the machines

Gespeichert in:
Bibliographische Detailangaben
Titel: A data-driven algorithm to predict throughput bottlenecks in a production system based on active periods of the machines
Autoren: Subramaniyan, Mukund, 1989, Skoogh, Anders, 1980, Salomonsson, Hans, 1985, Bangalore, Pramod, 1983, Bokrantz, Jon, 1988
Quelle: DAIMP - Dataanalys inom underhållsplanering Computers and Industrial Engineering. 125:533-544
Schlagwörter: shifting, Real-world, production, smart maintenance, machine learning, Industry 4.0, Predictive analytics, Digitalisation, throughput, managing bottlenecks, Maintenance, smart manufacturing, Bottleneck prediction, ARIMA, active period, constraints, decision-making, bottlenecks, bottleneck, Big data, throughput bottlenecks, prediction, data-driven, Theory of Constraints
Beschreibung: Smart manufacturing is reshaping the manufacturing industry by boosting the integration of information and communication technologies and manufacturing process. As a result, manufacturing companies generate large volumes of machine data which can be potentially used to make data-driven operational decisions using informative computerized algorithms. In the manufacturing domain, it is well-known that the productivity of a production line is constrained by throughput bottlenecks. The operational dynamics of the production system causes the bottlenecks to shift among the production resources between the production runs. Therefore, prediction of the throughput bottlenecks of future production runs allows the production and maintenance engineers to proactively plan for resources to effectively manage the bottlenecks and achieve higher throughput. This paper proposes an active period based data-driven algorithm to predict throughput bottlenecks in the production system for the future production run from the large sets of machine data. To facilitate the prediction, we employ an auto-regressive integrated moving average (ARIMA) method to predict the active periods of the machine. The novelty of the work is the integration of ARIMA methodology with the data-driven active period technique to develop a bottleneck prediction algorithm. The proposed prediction algorithm is tested on real-world production data from an automotive production line. The bottleneck prediction algorithm is evaluated by treating it as a binary classifier problem and adapted the appropriate evaluation metrics. Furthermore, an attempt is made to determine the amount of past data needed for better forecasting the active periods.
Dateibeschreibung: electronic
Zugangs-URL: https://research.chalmers.se/publication/505673
https://research.chalmers.se/publication/505673/file/505673_Fulltext.pdf
Datenbank: SwePub
FullText Text:
  Availability: 0
CustomLinks:
  – Url: https://research.chalmers.se/publication/505673#
    Name: EDS - SwePub (s4221598)
    Category: fullText
    Text: View record in SwePub
  – Url: https://resolver.ebscohost.com/openurl?sid=EBSCO:edsswe&genre=article&issn=03608352&ISBN=&volume=125&issue=&date=20180101&spage=533&pages=533-544&title=DAIMP - Dataanalys inom underhållsplanering Computers and Industrial Engineering&atitle=A%20data-driven%20algorithm%20to%20predict%20throughput%20bottlenecks%20in%20a%20production%20system%20based%20on%20active%20periods%20of%20the%20machines&aulast=Subramaniyan%2C%20Mukund&id=DOI:10.1016/j.cie.2018.04.024
    Name: Full Text Finder
    Category: fullText
    Text: Full Text Finder
    Icon: https://imageserver.ebscohost.com/branding/images/FTF.gif
    MouseOverText: Full Text Finder
  – Url: https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=EBSCO&SrcAuth=EBSCO&DestApp=WOS&ServiceName=TransferToWoS&DestLinkType=GeneralSearchSummary&Func=Links&author=Subramaniyan%20M
    Name: ISI
    Category: fullText
    Text: Nájsť tento článok vo Web of Science
    Icon: https://imagesrvr.epnet.com/ls/20docs.gif
    MouseOverText: Nájsť tento článok vo Web of Science
Header DbId: edsswe
DbLabel: SwePub
An: edsswe.oai.research.chalmers.se.73a63bfa.d381.4a6e.8ef9.96b81f4eea3d
RelevancyScore: 959
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 959.340270996094
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: A data-driven algorithm to predict throughput bottlenecks in a production system based on active periods of the machines
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Subramaniyan%2C+Mukund%22">Subramaniyan, Mukund</searchLink>, 1989<br /><searchLink fieldCode="AR" term="%22Skoogh%2C+Anders%22">Skoogh, Anders</searchLink>, 1980<br /><searchLink fieldCode="AR" term="%22Salomonsson%2C+Hans%22">Salomonsson, Hans</searchLink>, 1985<br /><searchLink fieldCode="AR" term="%22Bangalore%2C+Pramod%22">Bangalore, Pramod</searchLink>, 1983<br /><searchLink fieldCode="AR" term="%22Bokrantz%2C+Jon%22">Bokrantz, Jon</searchLink>, 1988
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <i>DAIMP - Dataanalys inom underhållsplanering Computers and Industrial Engineering</i>. 125:533-544
– Name: Subject
  Label: Subject Terms
  Group: Su
  Data: <searchLink fieldCode="DE" term="%22shifting%22">shifting</searchLink><br /><searchLink fieldCode="DE" term="%22Real-world%22">Real-world</searchLink><br /><searchLink fieldCode="DE" term="%22production%22">production</searchLink><br /><searchLink fieldCode="DE" term="%22smart+maintenance%22">smart maintenance</searchLink><br /><searchLink fieldCode="DE" term="%22machine+learning%22">machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Industry+4%2E0%22">Industry 4.0</searchLink><br /><searchLink fieldCode="DE" term="%22Predictive+analytics%22">Predictive analytics</searchLink><br /><searchLink fieldCode="DE" term="%22Digitalisation%22">Digitalisation</searchLink><br /><searchLink fieldCode="DE" term="%22throughput%22">throughput</searchLink><br /><searchLink fieldCode="DE" term="%22managing+bottlenecks%22">managing bottlenecks</searchLink><br /><searchLink fieldCode="DE" term="%22Maintenance%22">Maintenance</searchLink><br /><searchLink fieldCode="DE" term="%22smart+manufacturing%22">smart manufacturing</searchLink><br /><searchLink fieldCode="DE" term="%22Bottleneck+prediction%22">Bottleneck prediction</searchLink><br /><searchLink fieldCode="DE" term="%22ARIMA%22">ARIMA</searchLink><br /><searchLink fieldCode="DE" term="%22active+period%22">active period</searchLink><br /><searchLink fieldCode="DE" term="%22constraints%22">constraints</searchLink><br /><searchLink fieldCode="DE" term="%22decision-making%22">decision-making</searchLink><br /><searchLink fieldCode="DE" term="%22bottlenecks%22">bottlenecks</searchLink><br /><searchLink fieldCode="DE" term="%22bottleneck%22">bottleneck</searchLink><br /><searchLink fieldCode="DE" term="%22Big+data%22">Big data</searchLink><br /><searchLink fieldCode="DE" term="%22throughput+bottlenecks%22">throughput bottlenecks</searchLink><br /><searchLink fieldCode="DE" term="%22prediction%22">prediction</searchLink><br /><searchLink fieldCode="DE" term="%22data-driven%22">data-driven</searchLink><br /><searchLink fieldCode="DE" term="%22Theory+of+Constraints%22">Theory of Constraints</searchLink>
– Name: Abstract
  Label: Description
  Group: Ab
  Data: Smart manufacturing is reshaping the manufacturing industry by boosting the integration of information and communication technologies and manufacturing process. As a result, manufacturing companies generate large volumes of machine data which can be potentially used to make data-driven operational decisions using informative computerized algorithms. In the manufacturing domain, it is well-known that the productivity of a production line is constrained by throughput bottlenecks. The operational dynamics of the production system causes the bottlenecks to shift among the production resources between the production runs. Therefore, prediction of the throughput bottlenecks of future production runs allows the production and maintenance engineers to proactively plan for resources to effectively manage the bottlenecks and achieve higher throughput. This paper proposes an active period based data-driven algorithm to predict throughput bottlenecks in the production system for the future production run from the large sets of machine data. To facilitate the prediction, we employ an auto-regressive integrated moving average (ARIMA) method to predict the active periods of the machine. The novelty of the work is the integration of ARIMA methodology with the data-driven active period technique to develop a bottleneck prediction algorithm. The proposed prediction algorithm is tested on real-world production data from an automotive production line. The bottleneck prediction algorithm is evaluated by treating it as a binary classifier problem and adapted the appropriate evaluation metrics. Furthermore, an attempt is made to determine the amount of past data needed for better forecasting the active periods.
– Name: Format
  Label: File Description
  Group: SrcInfo
  Data: electronic
– Name: URL
  Label: Access URL
  Group: URL
  Data: <link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/505673" linkWindow="_blank">https://research.chalmers.se/publication/505673</link><br /><link linkTarget="URL" linkTerm="https://research.chalmers.se/publication/505673/file/505673_Fulltext.pdf" linkWindow="_blank">https://research.chalmers.se/publication/505673/file/505673_Fulltext.pdf</link>
PLink https://erproxy.cvtisr.sk/sfx/access?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsswe&AN=edsswe.oai.research.chalmers.se.73a63bfa.d381.4a6e.8ef9.96b81f4eea3d
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.cie.2018.04.024
    Languages:
      – Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 12
        StartPage: 533
    Subjects:
      – SubjectFull: shifting
        Type: general
      – SubjectFull: Real-world
        Type: general
      – SubjectFull: production
        Type: general
      – SubjectFull: smart maintenance
        Type: general
      – SubjectFull: machine learning
        Type: general
      – SubjectFull: Industry 4.0
        Type: general
      – SubjectFull: Predictive analytics
        Type: general
      – SubjectFull: Digitalisation
        Type: general
      – SubjectFull: throughput
        Type: general
      – SubjectFull: managing bottlenecks
        Type: general
      – SubjectFull: Maintenance
        Type: general
      – SubjectFull: smart manufacturing
        Type: general
      – SubjectFull: Bottleneck prediction
        Type: general
      – SubjectFull: ARIMA
        Type: general
      – SubjectFull: active period
        Type: general
      – SubjectFull: constraints
        Type: general
      – SubjectFull: decision-making
        Type: general
      – SubjectFull: bottlenecks
        Type: general
      – SubjectFull: bottleneck
        Type: general
      – SubjectFull: Big data
        Type: general
      – SubjectFull: throughput bottlenecks
        Type: general
      – SubjectFull: prediction
        Type: general
      – SubjectFull: data-driven
        Type: general
      – SubjectFull: Theory of Constraints
        Type: general
    Titles:
      – TitleFull: A data-driven algorithm to predict throughput bottlenecks in a production system based on active periods of the machines
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Subramaniyan, Mukund
      – PersonEntity:
          Name:
            NameFull: Skoogh, Anders
      – PersonEntity:
          Name:
            NameFull: Salomonsson, Hans
      – PersonEntity:
          Name:
            NameFull: Bangalore, Pramod
      – PersonEntity:
          Name:
            NameFull: Bokrantz, Jon
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 01
              M: 01
              Type: published
              Y: 2018
          Identifiers:
            – Type: issn-print
              Value: 03608352
            – Type: issn-locals
              Value: SWEPUB_FREE
            – Type: issn-locals
              Value: CTH_SWEPUB
          Numbering:
            – Type: volume
              Value: 125
          Titles:
            – TitleFull: DAIMP - Dataanalys inom underhållsplanering Computers and Industrial Engineering
              Type: main
ResultId 1