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
Detecting Broken Rotor Bars in Induction Motors with Model-Based Support Vector Classifiers
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.
Luleå University of Technology, Department of Computer Science, Electrical and Space Engineering, Signals and Systems.ORCID iD: 0000-0002-4310-7938
2016 (English)In: IEEE transactions on industrial electronics (1982. Print), ISSN 0278-0046, E-ISSN 1557-9948, article id 18Article in journal (Refereed) Submitted
Abstract [en]

We propose a methodology for testing the sanity ofmotors when both healthy and faulty data are unavailable. Moreprecisely, we consider a model-based Support Vector Classification(SVC) method for the detection of broken bars in threephase asynchronous motors at full load conditions, using featuresbased on the spectral analysis of the stator’s steady state current(more specifically, the amplitude of the lift sideband harmonicand the amplitude at fundamental frequency). We diverge fromthe mainstream focus on using SVCs trained from measureddata, and instead derive a classifier that is constructed entirelyusing theoretical considerations. The advantage of this approachis that it does not need training steps (an expensive, timeconsuming and often practically in feasible task), i.e., operatorsare not required to have both healthy and faulty data from asystem for checking it. We describe what are the theoreticalproperties and fundamental limitations of using model based SVCmethodologies, provide conditions under which using SVC testsis statistically optimal, and present some experimental results toprove the effectiveness of the suggested scheme.

Place, publisher, year, edition, pages
2016. article id 18
National Category
Control Engineering
Research subject
Control Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-4336Local ID: 243f1f78-da1f-4b7c-957c-4b9c77ab45d5OAI: oai:DiVA.org:ltu-4336DiVA: diva2:977200
Note

Upprättat; 2015; 20150115 (mohoba)

Available from: 2016-09-29 Created: 2016-09-29 Last updated: 2017-11-24

Open Access in DiVA

No full text in DiVA

Search in DiVA

By author/editor
Mustafa, Mohammed ObaidVaragnolo, Damiano
By organisation
Signals and Systems
In the same journal
IEEE transactions on industrial electronics (1982. Print)
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 239 hits
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