Condition monitoring using pattern recognition techniques on data from acoustic emissions

Document identifier: oai:dalea.du.se:2707
Access full text here:10.1109/ICMLA.2006.19
Keyword: Natural Sciences, Computer and Information Sciences, Naturvetenskap, Data- och informationsvetenskap, Automatisk inspektion av järnvägsslipers
Publication year: 2006
Relevant Sustainable Development Goals (SDGs):

The SDG label(s) above have been assigned by OSDG.ai

Abstract:

Condition monitoring applications deploying the usage of impact acoustic techniques are mostly done intuitively by skilled personnel. In this article, a pattern recognition approach is taken to automate such intuitive human skills for the development of more robust and reliable testing methods. The focus of this work is to use the approach as a part of a major research project in the rail inspection area, within the domain of Intelligent Transport Systems. Data from impact acoustic tests made on wooden beams have been used. The relation between condition of the wooden beams and respective sounds they make when struck, has been analyzed experimentally. Features were extracted from the acoustic emissions of wooden beams and were used for pattern classification. Features such as magnitude of the signal, natural logarithm of the magnitude and Mel-frequency cepstral coefficients, yielded good results. The extracted feature vectors were used as input to various pattern classifiers for further pattern recognition task. The effect of using classifiers like Support vector machines and Multi-layer perceptron has been tested and compared. Results obtained experimentally, demonstrate that Support vector machines provide good detection rates for the classification of impact acoustic signals in the NDT domain.

Authors

Siril Yella

Högskolan Dalarna; Datateknik
Other publications >>

Naren Gupta

Other publications >>

Mark Dougherty

Högskolan Dalarna; Datateknik
Other publications >>

Record metadata

Click to view metadata

	
    header: 
        identifier: oai:dalea.du.se:2707
        datestamp: 2021-04-15T13:28:19Z
        setSpec: SwePub-du
    metadata: 
        mods: 
            @attributes: 
                version: 3.7
            recordInfo: 
                recordContentSource: du
                recordCreationDate: 2007-04-10
            identifier: 
                http://urn.kb.se/resolve?urn=urn:nbn:se:du-2707
                doi.ieeecomputersociety.org/10.1109/ICMLA.2006.19
            titleInfo: 
                @attributes: 
                    lang: eng
                title: Condition monitoring using pattern recognition techniques on data from acoustic emissions
            abstract: 
Condition monitoring applications deploying the usage of impact acoustic techniques are mostly done intuitively by skilled personnel. In this article a pattern recognition approach is taken to automate such intuitive human skills for the development of more robust and reliable testing methods. The focus of this work is to use the approach as a part of a major research project in the rail inspection area within the domain of Intelligent Transport Systems. Data from impact acoustic tests made on wooden beams have been used. The relation between condition of the wooden beams and respective sounds they make when struck has been analyzed experimentally. Features were extracted from the acoustic emissions of wooden beams and were used for pattern classification. Features such as magnitude of the signal natural logarithm of the magnitude and Mel-frequency cepstral coefficients yielded good results. The extracted feature vectors were used as input to various pattern classifiers for further pattern recognition task. The effect of using classifiers like Support vector machines and Multi-layer perceptron has been tested and compared. Results obtained experimentally demonstrate that Support vector machines provide good detection rates for the classification of impact acoustic signals in the NDT domain.

            subject: 
                    @attributes: 
                        lang: eng
                        authority: uka.se
                    topic: 
                        Natural Sciences
                        Computer and Information Sciences
                    @attributes: 
                        lang: swe
                        authority: uka.se
                    topic: 
                        Naturvetenskap
                        Data- och informationsvetenskap
                    @attributes: 
                        lang: swe
                        authority: du
                    topic: Automatisk inspektion av järnvägsslipers
                    genre: Research subject
            language: 
                languageTerm: eng
            genre: 
                conference/other
                vet
            note: 
                Published
                3
            name: 
                    @attributes: 
                        type: personal
                        authority: du
                    namePart: 
                        Yella
                        Siril
                    role: 
                        roleTerm: aut
                    affiliation: 
                        Högskolan Dalarna
                        Datateknik
                    nameIdentifier: sye
                    @attributes: 
                        type: personal
                    namePart: 
                        Gupta
                        Naren
                    role: 
                        roleTerm: aut
                    @attributes: 
                        type: personal
                        authority: du
                    namePart: 
                        Dougherty
                        Mark
                    role: 
                        roleTerm: aut
                    affiliation: 
                        Högskolan Dalarna
                        Datateknik
                    nameIdentifier: mdo
            originInfo: 
                dateIssued: 2006
            relatedItem: 
                @attributes: 
                    type: host
                titleInfo: 
                    title: ICMLA 2006: 4th International Conference on Machine Learning and Applications Proceedings
            location: 
                url: http://www.computer.org/csdl/proceedings/icmla/2006/2735/00/27350003-abs.html
            physicalDescription: 
                form: print
            typeOfResource: text