Automated defect detection in digital radiography of aerospace welds using deep learning

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorTyystjärvi, Topiasen_US
dc.contributor.authorVirkkunen, Iikkaen_US
dc.contributor.authorFridolf, Peteren_US
dc.contributor.authorRosell, Andersen_US
dc.contributor.authorBarsoum, Zuheiren_US
dc.contributor.departmentDepartment of Energy and Mechanical Engineeringen
dc.contributor.groupauthorAdvanced Manufacturing and Materialsen
dc.contributor.organizationGKN Aerospace Engine Systemsen_US
dc.contributor.organizationKTH Royal Institute of Technologyen_US
dc.contributor.organizationTrueflaw Ltd.en_US
dc.date.accessioned2022-04-06T06:30:16Z
dc.date.available2022-04-06T06:30:16Z
dc.date.issued2022-04en_US
dc.descriptionPublisher Copyright: © 2022, The Author(s).
dc.description.abstractAerospace welds are non-destructively evaluated (NDE) during manufacturing to identify defective parts that may pose structural risks, often using digital radiography. The analysis of these digital radiographs is time consuming and costly. Attempts to automate the analysis using conventional computer vision methods or shallow machine learning have not, thus far, provided performance equivalent to human inspectors due to the high reliability requirements and low contrast to noise ratio of the defects. Modern approaches based on deep learning have made considerable progress towards reliable automated analysis. However, limited data sets render current machine learning solutions insufficient for industrial use. Moreover, industrial acceptance would require performance demonstration using standard metrics in non-destructive evaluation, such as probability of detection (POD), which are not commonly used in previous studies. In this study, data augmentation with virtual flaws was used to overcome data scarcity, and compared with conventional data augmentation. A semantic segmentation network was trained to find defects from computed radiography data of aerospace welds. Standard evaluation metrics in non-destructive testing were adopted for the comparison. Finally, the network was deployed as an inspector’s aid in a realistic environment to predict flaws from production radiographs. The network achieved high detection reliability and defect sizing performance, and an acceptable false call rate. Virtual flaw augmentation was found to significantly improve performance, especially for limited data set sizes, and for underrepresented flaw types even at large data sets. The deployed prototype was found to be easy to use indicating readiness for industry adoption.en
dc.description.versionPeer revieweden
dc.format.extent29
dc.format.extent643-671
dc.format.mimetypeapplication/pdfen_US
dc.identifier.citationTyystjärvi, T, Virkkunen, I, Fridolf, P, Rosell, A & Barsoum, Z 2022, ' Automated defect detection in digital radiography of aerospace welds using deep learning ', Welding in the World, vol. 66, no. 4, pp. 643-671 . https://doi.org/10.1007/s40194-022-01257-wen
dc.identifier.doi10.1007/s40194-022-01257-wen_US
dc.identifier.issn0043-2288
dc.identifier.otherPURE UUID: f51c3c67-9d11-4aa4-9923-58cb7d6147dden_US
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/f51c3c67-9d11-4aa4-9923-58cb7d6147dden_US
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85125150233&partnerID=8YFLogxKen_US
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/81293150/Tyystj_rvi2022_Article_AutomatedDefectDetectionInDigi.pdfen_US
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/113904
dc.identifier.urnURN:NBN:fi:aalto-202204062780
dc.language.isoenen
dc.publisherSPRINGER HEIDELBERG
dc.relation.ispartofseriesWelding in the Worlden
dc.relation.ispartofseriesVolume 66, issue 4en
dc.rightsopenAccessen
dc.subject.keywordData augmentationen_US
dc.subject.keywordDeep learningen_US
dc.subject.keywordNon-destructive evaluationen_US
dc.subject.keywordProbability of detectionen_US
dc.subject.keywordWeldingen_US
dc.titleAutomated defect detection in digital radiography of aerospace welds using deep learningen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionpublishedVersion

Files