Machine Learning based defect detection in Laser Powder Bed Fusion utilizing thermographic feature data
- The formation of irregularities such as keyhole porosity pose a major challenge to the manufacturing of metal parts by laser powder bed fusion (PBF-LB/M). In-situ thermography as a process monitoring technique shows promising potential in this manner since it is able to extract the thermal history of the part which is closely related to the formation of irregularities. In this study, we investigate the utilization of machine learning algorithms to detect keyhole porosity on the base of thermographic features. Here, as a referential technique, x-ray micro computed tomography is utilized to determine the part's porosity. An enhanced preprocessing workflow inspired by the physics of the keyhole irregularity formation is presented in combination with a customized model architecture. Furthermore, experiments were performed to clarify the role of important parameters of the preprocessing workflow for the task of defect detection . Based on the results, future demands on irregularityThe formation of irregularities such as keyhole porosity pose a major challenge to the manufacturing of metal parts by laser powder bed fusion (PBF-LB/M). In-situ thermography as a process monitoring technique shows promising potential in this manner since it is able to extract the thermal history of the part which is closely related to the formation of irregularities. In this study, we investigate the utilization of machine learning algorithms to detect keyhole porosity on the base of thermographic features. Here, as a referential technique, x-ray micro computed tomography is utilized to determine the part's porosity. An enhanced preprocessing workflow inspired by the physics of the keyhole irregularity formation is presented in combination with a customized model architecture. Furthermore, experiments were performed to clarify the role of important parameters of the preprocessing workflow for the task of defect detection . Based on the results, future demands on irregularity prediction in PBF-LB/M are derived.…
Autor*innen: | Simon OsterORCiD |
---|---|
Koautor*innen: | Tina BeckerORCiD, Philipp Peter BreeseORCiD, Nils ScheuschnerORCiD, Simon AltenburgORCiD |
Dokumenttyp: | Vortrag |
Veröffentlichungsform: | Präsentation |
Sprache: | Englisch |
Jahr der Erstveröffentlichung: | 2022 |
Organisationseinheit der BAM: | 8 Zerstörungsfreie Prüfung |
8 Zerstörungsfreie Prüfung / 8.0 Abteilungsleitung und andere | |
DDC-Klassifikation: | Naturwissenschaften und Mathematik / Chemie / Analytische Chemie |
Technik, Medizin, angewandte Wissenschaften / Ingenieurwissenschaften / Ingenieurwissenschaften und zugeordnete Tätigkeiten | |
Freie Schlagwörter: | Convolutional Neural Networks; In-situ Monitoring; Laser Powder Bed Fusion; Thermography |
Themenfelder/Aktivitätsfelder der BAM: | Chemie und Prozesstechnik |
Material | |
Material / Additive Fertigung | |
Veranstaltung: | International Conference on NDE 4.0 |
Veranstaltungsort: | Berlin, Germany |
Beginndatum der Veranstaltung: | 24.10.2022 |
Enddatum der Veranstaltung: | 27.10.2022 |
Verfügbarkeit des Dokuments: | Datei im Netzwerk der BAM verfügbar ("Closed Access") |
Datum der Freischaltung: | 22.11.2022 |
Referierte Publikation: | Nein |
Eingeladener Vortrag: | Nein |