liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Combining model-based diagnosis and data-driven anomaly classifiers for fault isolation
Linköping University, Department of Electrical Engineering, Vehicular Systems. Linköping University, Faculty of Science & Engineering.ORCID iD: 0000-0003-0808-052X
School of Engineering, Ulster University, Newtownabbey, UK; Electrical and Computer Systems Engineering, School of Engineering, Monash University Malaysia, Malaysia.
Linköping University, Department of Electrical Engineering, Vehicular Systems. Linköping University, Faculty of Science & Engineering.
Linköping University, Department of Electrical Engineering, Computer Engineering. Linköping University, Faculty of Science & Engineering.
2018 (English)In: Control Engineering Practice, ISSN 0967-0661, E-ISSN 1873-6939, Vol. 80, p. 146-156Article in journal (Refereed) Published
Abstract [en]

Machine learning can be used to automatically process sensor data and create data-driven models for prediction and classification. However, in applications such as fault diagnosis, faults are rare events and learning models for fault classification is complicated because of lack of relevant training data. This paper proposes a hybrid diagnosis system design which combines model-based residuals with incremental anomaly classifiers. The proposed method is able to identify unknown faults and also classify multiple-faults using only single-fault training data. The proposed method is verified using a physical model and data collected from an internal combustion engine.

Place, publisher, year, edition, pages
Elsevier, 2018. Vol. 80, p. 146-156
Keywords [en]
Fault diagnosis, Fault isolation, Machine learning, Artificial intelligence, Classification
National Category
Control Engineering
Identifiers
URN: urn:nbn:se:liu:diva-151296DOI: 10.1016/j.conengprac.2018.08.013ISI: 000447483500014OAI: oai:DiVA.org:liu-151296DiVA, id: diva2:1248561
Note

Funding agencies: Volvo Car Corporation in Gothenburg, Sweden

Available from: 2018-09-17 Created: 2018-09-17 Last updated: 2018-10-30

Open Access in DiVA

The full text will be freely available from 2020-09-09 11:37
Available from 2020-09-09 11:37

Other links

Publisher's full text

Authority records BETA

Frisk, ErikKrysander, Mattias

Search in DiVA

By author/editor
Jung, DanielFrisk, ErikKrysander, Mattias
By organisation
Vehicular SystemsFaculty of Science & EngineeringComputer Engineering
In the same journal
Control Engineering Practice
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 94 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf