Show simple item record

dc.contributor.authorTripathi, Gaurav
dc.contributor.authorAnowarul, Habib
dc.contributor.authorAgarwal, Krishna
dc.contributor.authorPrasad, Dilip K.
dc.date.accessioned2019-11-05T14:15:56Z
dc.date.available2019-11-05T14:15:56Z
dc.date.issued2019-09-28
dc.description.abstractUltrasound based structural health monitoring of piezoelectric material is challenging if a damage changes at a microscale over time. Classifying geometrically similar damages with a difference in diameter as small as 100 m is difficult using conventional sensing and signal analysis approaches. Here, we use an unconventional ultrasound sensing approach that collects information of the entire bulk of the material and investigate the applicability of machine learning approaches for classifying such similar defects.<br> Our results show that appropriate feature design combined with simple k-nearest neighbor classifier can provide up to 98% classification accuracy even though conventional features for time-series data and a variety of classifiers cannot achieve close to 70% accuracy. <br>The newly proposed hybrid feature, which combines frequency domain information in the form of power spectral density and time domain information in the form of sign of slope change, is a suitable feature for achieving the best classification accuracy on this challenging problem.en_US
dc.descriptionPublished version, licensed <a href=http://creativecommons.org/licenses/by-nc-nd/4.0/> CC BY-NC-ND 4.0. </a>, available at: <a href=https://doi.org/10.3390/s19194216>https://doi.org/10.3390/s19194216</a>en_US
dc.identifier.citationTripathi, G., Anowarul, H., Agarwal K., Prasad, D.K.(2019) Classification of Micro-Damage in Piezoelectric Ceramics Using Machine Learning of Ultrasound Signals.<i> Sensors, 19</i>, (19),4216. http://dx.doi.org/10.3390/s19194216en_US
dc.identifier.cristinIDFRIDAID 1733725
dc.identifier.doi10.3390/s19194216
dc.identifier.issn1424-8220
dc.identifier.urihttps://hdl.handle.net/10037/16611
dc.language.isoengen_US
dc.publisherMolecular Diversity Preservation International (MDPI)en_US
dc.relation.journalSensors
dc.rights.accessRightsopenAccessen_US
dc.subjectVDP::Mathematics and natural science: 400::Physics: 430::Electromagnetism, acoustics, optics: 434en_US
dc.subjectVDP::Matematikk og Naturvitenskap: 400::Fysikk: 430::Elektromagnetisme, akustikk, optikk: 434en_US
dc.titleClassification of Micro-Damage in Piezoelectric Ceramics Using Machine Learning of Ultrasound Signalsen_US
dc.typeJournal articleen_US
dc.typePeer revieweden_US


File(s) in this item

Thumbnail

This item appears in the following collection(s)

Show simple item record