Zitieren Sie bitte immer diesen URN: urn:nbn:de:kobv:b43-570565
Strain Prediction Using Deep Learning during Solidification Crack Initiation and Growth in Laser Beam Welding of Thin Metal Sheets
- The strain field can reflect the initiation time of solidification cracks during the welding process. The traditional strain measurement is to first obtain the displacement field through digital image correlation (DIC) or optical flow and then calculate the strain field. The main disadvantage is that the calculation takes a long time, limiting its suitability to real-time applications. Recently, convolutional neural networks (CNNs) have made impressive achievements in computer vision. To build a good prediction model, the network structure and dataset are two key factors. In this paper, we first create the training and test sets containing welding cracks using the controlled tensile weldability (CTW) test and obtain the real strain fields through the Lucas–Kanade algorithm. Then, two new networks using ResNet and DenseNet as encoders are developed for strain prediction, called StrainNetR and StrainNetD. The results show that the average endpoint error (AEE) of the two networks on ourThe strain field can reflect the initiation time of solidification cracks during the welding process. The traditional strain measurement is to first obtain the displacement field through digital image correlation (DIC) or optical flow and then calculate the strain field. The main disadvantage is that the calculation takes a long time, limiting its suitability to real-time applications. Recently, convolutional neural networks (CNNs) have made impressive achievements in computer vision. To build a good prediction model, the network structure and dataset are two key factors. In this paper, we first create the training and test sets containing welding cracks using the controlled tensile weldability (CTW) test and obtain the real strain fields through the Lucas–Kanade algorithm. Then, two new networks using ResNet and DenseNet as encoders are developed for strain prediction, called StrainNetR and StrainNetD. The results show that the average endpoint error (AEE) of the two networks on our test set is about 0.04, close to the real strain value. The computation time could be reduced to the millisecond level, which would greatly improve efficiency.…
Autor*innen: | W. Huo, Nasim Bakir, Andrey Gumenyuk, Michael RethmeierORCiD, K. Wolter |
---|---|
Dokumenttyp: | Zeitschriftenartikel |
Veröffentlichungsform: | Verlagsliteratur |
Sprache: | Englisch |
Titel des übergeordneten Werkes (Englisch): | Applied sciences |
Jahr der Erstveröffentlichung: | 2023 |
Organisationseinheit der BAM: | 9 Komponentensicherheit |
9 Komponentensicherheit / 9.3 Schweißtechnische Fertigungsverfahren | |
Veröffentlichende Institution: | Bundesanstalt für Materialforschung und -prüfung (BAM) |
Verlag: | MDPI |
Jahrgang/Band: | 13 |
Ausgabe/Heft: | 5 |
Aufsatznummer: | 2930 |
Erste Seite: | 1 |
Letzte Seite: | 15 |
DDC-Klassifikation: | Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Ingenieurwissenschaften und zugeordnete Tätigkeiten |
Freie Schlagwörter: | Convolutional neural network; Laser beam welding; Solidification cracking; Strain fields prediction |
Themenfelder/Aktivitätsfelder der BAM: | Material |
Material / Additive Fertigung | |
DOI: | 10.3390/app13052930 |
URN: | urn:nbn:de:kobv:b43-570565 |
Verfügbarkeit des Dokuments: | Datei für die Öffentlichkeit verfügbar ("Open Access") |
Lizenz (Deutsch): | Creative Commons - CC BY - Namensnennung 4.0 International |
Datum der Freischaltung: | 01.03.2023 |
Referierte Publikation: | Ja |
Datum der Eintragung als referierte Publikation: | 03.04.2023 |
Schriftenreihen ohne Nummerierung: | Wissenschaftliche Artikel der BAM |