EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Defect Classification for Additive Manufacturing with Machine Learning

Mika León Altmann, Thiemo Benthien, Nils Ellendt iD, Anastasiya Toenjes iD

Materials · 16.09.2023 · 16 (18) · 6242

DOI: 10.3390/ma16186242 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 16.09.2023. Verfasst von Mika León Altmann und 3 weiteren Autor:innen. Beteiligte Einrichtung: Leibniz Institute for Materials Engineering-IWT, Badgasteiner Straße 3, 28359 Bremen, Germany. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: This work is funded by the University of Bremen Research Alliance (UBRA) AI Center for Healthcare within the project ENABLE.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Additive manufacturing offers significant design freedom and the ability to selectively influence material properties. However, conventional processes like laser powder bed fusion for metals may result in internal defects, such as pores, which profoundly affect the mechanical characteristics of the components. The extent of this influence varies depending on the specific defect type, its size, and morphology. Furthermore, a single component may exhibit various defect types due to the manufacturing process. To investigate these occurrences with regard to other target variables, this study presents a random forest tree model capable of classifying defects in binary images derived from micrographs. Our approach demonstrates a classification accuracy of approximately 95% when distinguishing between keyhole and lack of fusion defects, as well as process pores. In contrast, unsupervised models yielded prediction accuracies below 60%. The model’s accuracy in differentiating between lack of fusion and keyhole defects varies based on the manufacturing process’s parameters, primarily due to the irregular shapes of keyhole defects. We provide the model alongside this paper, which can be utilized on a standard computer without the need for in situ monitoring systems during the additive manufacturing process.

Schlagwörter

Stichwörter der Autor:innen

PBF-LB/MTi6Al4Vadditive manufacturingdefect classificationmachine learning

Autor:innen und Institutionen

  • Leibniz Institute for Materials Engineering-IWT, Badgasteiner Straße 3, 28359 Bremen, Germany.
  • Faculty of Production Engineering, University of Bremen, Badgasteiner Straße 1, 28359 Bremen, Germany.

ORCID-Profile: Nils Ellendt, Anastasiya Toenjes

Förderung

  • This work is funded by the University of Bremen Research Alliance (UBRA) AI Center for Healthcare within the project ENABLE

Zitieren

APA

Altmann, M. L., Benthien, T., Ellendt, N., & Toenjes, A. (2023). Defect Classification for Additive Manufacturing with Machine Learning. Materials, 16(18), 6242. https://doi.org/10.3390/ma16186242

Vancouver

Altmann ML, Benthien T, Ellendt N, Toenjes A. Defect Classification for Additive Manufacturing with Machine Learning. Materials. 2023;16(18):6242. doi:10.3390/ma16186242

BibTeX
@article{Altmann2023,
  author = {Altmann, Mika León and Benthien, Thiemo and Ellendt, Nils and Toenjes, Anastasiya},
  title = {Defect Classification for Additive Manufacturing with Machine Learning},
  journal = {Materials},
  year = {2023},
  volume = {16},
  number = {18},
  pages = {6242},
  doi = {10.3390/ma16186242}
}
Kostenlos starten →