> Merkliste Sie können Bookmarks mittels Listen verwalten, loggen Sie sich dafür bitte in Ihr SLUB Benutzerkonto ein.
Medientyp: Sonstige Veröffentlichung; E-Artikel Titel: Deep Learning-Based Weld Contour and Defect Detection from Micrographs of Laser Beam Welded Semi-Finished Products Beteiligte: Nowroth, Christian [VerfasserIn]; Gu, Tiansheng [VerfasserIn]; Grajczak, Jan [VerfasserIn]; Nothdurft, Sarah [VerfasserIn]; Twiefel, Jens [VerfasserIn]; Hermsdorf, Jörg [VerfasserIn]; Kaierle, Stefan [VerfasserIn]; Wallaschek, Jörg [VerfasserIn] Erschienen: Basel : MDPI, 2022 Erschienen in: Applied Sciences : open access journal 12 (2022), Nr. 9 ; Applied Sciences : open access journal Ausgabe: published Version Sprache: Englisch DOI: https://doi.org/10.15488/12835; https://doi.org/10.3390/app12094645 Schlagwörter: weld seam ; deep learning ; weld defects ; quantization ; semantic segmentation ; automatic detection ; dataset creation Entstehung: Anmerkungen: Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen. Beschreibung: Laser beam welding is used in many areas of industry and research. There are many strategies and approaches to further improve the weld seam properties in laser beam welding. Metallography is often needed to evaluate welded seams. Typically, the images are examined and evaluated by experts. The evaluation process qualitatively provides the properties of the welds. Particularly in times when artificial intelligence is being used more and more in processes, the quantization of properties that could previously only be determined qualitatively is gaining importance. In this contribution, we propose to use deep learning to perform semantic segmentation of micrographs of complex weld areas to achieve the automatic detection and quantization of weld seam properties. A semantic segmentation dataset is created containing 282 labeled images. The training process is performed with DeepLabv3+. The trained model achieves a value of around 95% for weld contour detection and 76.88% of mean intersection over union (mIoU). © 2022 by the authors. Licensee MDPI, Basel, Switzerland. Zugangsstatus: Freier Zugang Rechte-/Nutzungshinweise: Namensnennung (CC BY)