Change search
ReferencesLink to record
Permanent link

Direct link
Bearing fault detection and diagnosis by fusing vibration data
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.
2016 (English)In: 42nd Annual Conference on IEEE Industrial Electronics Society, October 24-27, Florence, Italy, 2016., 2016Conference paper (Refereed)
Abstract [en]

This article presents a simple method for the detection and diagnosis of bearing faults, by fusing the information coming from two accelerometers. The method relies on three simple and intuitive features, extracted from the data coming from accelerometers placed at two different sites of the system under investigation. Our preliminary results indicate that by using simple statistical measures, such as the elements of the covariance matrix of the two sensors, faults at an early stage can be detected. In our the proposed scheme, the extracted features are fed to a k-nearest neighbour classifier for diagnosis purposes or to an ensemble of one-class detectors, if only the information from normal situation is available. As it is proved, based on experimental results, in both scenarios a remarkably high detection/diagnostic performance is achieved.

Place, publisher, year, edition, pages
2016.
Keyword [en]
Information technology - Automatic control
Keyword [sv]
Informationsteknik - Reglerteknik
Research subject
Control Engineering
Identifiers
URN: urn:nbn:se:ltu:diva-39681Local ID: e8630bd5-4600-49a0-b091-35669681f9eaOAI: oai:DiVA.org:ltu-39681DiVA: diva2:1013197
Note
Upprättat; 2016; Nivå 2; 20160628 (geonik)Available from: 2016-10-03 Created: 2016-10-03

Open Access in DiVA

No full text

Search in DiVA

By author/editor
Georgoulas, GeorgiosNikolakopoulos, George
By organisation
Signals and Systems

Search outside of DiVA

GoogleGoogle Scholar

Total: 14 hits
ReferencesLink to record
Permanent link

Direct link