Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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
Automatizing the broken bar detection process via Short Time Fourier Transform and two-dimensional Piecewise Aggregate Approximation representation
Laboratory of Knowledge and Intelligent Computing, Department of Computer Engineering, TEI of Epirus, Artas.ORCID iD: 0000-0001-9701-4203
Laboratory of Knowledge and Intelligent Computing, Department of Computer Engineering, TEI of Epirus, Artas.
Laboratory of Knowledge and Intelligent Computing, Department of Computer Engineering, TEI of Epirus, Artas, Kostakioi.
Larges Drives R and D Department, Siemens Industry Sector - Drive Technologies, Nuremberg.
Show others and affiliations
2014 (English)Conference paper, Published paper (Refereed)
Abstract [en]

This work presents an automated approach for detecting broken rotor bars in induction machines using the stator current during startup operation. The currents are analyzed using the well-known Short Time Fourier Transform (STFT) producing a two-dimensional time-frequency representation. This representation contains information regarding the presence of a characteristic transient component but requires further processing before it can be fed into a standard classification algorithm. In this work, this part is performed using the two dimensional extension of Piecewise Aggregate Approximation (PAA) that can deal with the two dimensional representation of STFT. The results (with both simulated and experimental data) suggest that the method can be used for the automatic detection of broken bars and even for determining the fault severity. Moreover, its low computational burden makes it ideal for its future use in online, unsupervised systems, as well as in portable condition monitoring devices.

Place, publisher, year, edition, pages
Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2014. p. 3104-3110, article id 6953822
National Category
Control Engineering
Research subject
Control Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-67889DOI: 10.1109/ECCE.2014.6953822Scopus ID: 2-s2.0-84934300255OAI: oai:DiVA.org:ltu-67889DiVA, id: diva2:1188699
Conference
2014 IEEE Energy Conversion Congress and Exposition, ECCE 2014, Pittsburgh, PA, 14-18 Sept. 2014
Available from: 2018-03-08 Created: 2018-03-08 Last updated: 2018-03-08Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Search in DiVA

By author/editor
Georgoulas, Georgios
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • 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