View source for Publications:Evaluation of Micro-flaws in Metallic Material Based on A Self-Organized Data-driven Approach

<div style='display: none'>
== Do not edit this section ==
</div>
{{PublicationSetupTemplate|PID=948974
|Name=Teng, Xudong (Shanghai University of Engineering Science, Shanghai, China & Nanjing University, Nanjing, China);Fan, Yuantao [yuafan] [0000-0002-3034-6630] (Högskolan i Halmstad [2804], Akademin för informationsteknologi [16904], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], CAISR Centrum för tillämpade intelligenta system (IS-lab) [13650]);Nowaczyk, Sławomir [slanow] [0000-0002-7796-5201] (Högskolan i Halmstad [2804], Akademin för informationsteknologi [16904], Halmstad Embedded and Intelligent Systems Research (EIS) [3938], Laboratoriet för intelligenta system [6703])
|Title=Evaluation of Micro-flaws in Metallic Material Based on A Self-Organized Data-driven Approach
|PublicationType=Conference Paper
|ContentType=Refereegranskat
|Language=eng
|Journal=
|JournalISSN=
|Status=
|Volume=
|Issue=
|HostPublication=2016 IEEE International Conference on Prognostics and Health Management (ICPHM)
|Conference=2016 IEEE International Conference on Prognostics and Health Management, Carleton University, Ottawa, ON, Canada, June 20-22, 2016
|StartPage=
|EndPage=
|Year=2016
|Edition=
|Pages=
|City=
|Publisher=IEEE conference proceedings
|Series=
|SeriesISSN=
|ISBN=978-1-5090-0382-2
|Urls=
|ISRN=
|DOI=http://dx.doi.org/10.1109/ICPHM.2016.7542868
|ISI=
|PMID=
|ScopusId=
|NBN=urn:nbn:se:hh:diva-31646
|LocalId=
|ArchiveNumber=
|Keywords=Non-destructive testing;ultrasonic;micro-defects
|Categories=Annan medicinteknik (20699)
|ResearchSubjects=
|Projects=
|Notes=
|Abstract=<p>Evaluating the health condition of a material that could potentially contain micro-flaws is a common and important application within the field of non-destructive testing. Examples of such micro-defects include dislocation, fatigue cracks or impurities and are often hard to detect. The ability to precisely measure their type, size and position is a prerequisite for estimating the remaining useful life of the component. One technique that was shown successful in the past is based on traditional ultrasonic testing methods. In most cases, inner micro-flaws induce slight changes of acoustic wave spectrum components. However, these changes are often difficult to detect directly, as they tend to exhibit features that are most naturally analyzed using statistical and probabilistic methods. In this paper we apply Consensus Self-Organizing Models (COSMO) method to detect micro-flaws in metallic material. This approach is essentially an unsupervised deviation detection method based on the concept of "wisdom of the crowd". This method is used to analyze the spectrum of acoustic waves received by the transducer attached on the surface of material being analyzed. We have modeled a steel board with micro-cracks and collected time-series of acoustic echo response, at different positions on material's surface. The experimental results show that the COSMO method is able to detect and locate micro-flaws. © 2016 IEEE</p>
|Opponents=
|Supervisors=
|Examiners=
|Patent=
|ThesisLevel=
|Credits=
|Programme=
|Subject=
|Uppsok=
|DefencePlace=
|DefenceLanguage=
|DefenceDate=
|CreatedDate=2016-07-14
|PublicationDate=2016-07-14
|LastUpdated=2016-08-23
|diva=http://hh.diva-portal.org/smash/record.jsf?searchId=1&pid=diva2:948974}}
<div style='display: none'>

== Keep all hand-made modifications below ==
</div>{{PublicationDisplayTemplate}}