Towards material and process agnostic features for the classification of pore types in metal additive manufacturing
- Author
- Mathieu Vandecasteele (UGent) , Rob Heylen, Domenico Iuso, Aditi Thanki, Wilfried Philips (UGent) , Ann Witvrouw, Dries Verhees and Brian Booth (UGent)
- Organization
- Abstract
- The manufacturing of metal parts via powder-bed fusion is often still facing quality issues due to microstructural porosity. Minimizing this porosity remains a priority and requires the optimization of printing process parameters. While the analysis of printed parts using X-ray computed tomography can localize and identify the pore types (e.g. keyhole or lack-of-fusion pores), these pore types can be difficult to identify across printer settings and print materials. Therefore, there is a need for a material and process agnostic approach. This work presents such an approach by considering a set of geometric pore features that do not differ considerably across print scenarios. These features are then leveraged for supervised pore type classification. The distributions of pore features were analyzed in different materials and under varying laser parameters, showing that they behave in a generic way. For classification, it is observed that they outperform other features leveraged in the state-of-the-art for pore classification in a single material, reaching up to 93.0% accuracy. Additionally, accuracies up to 90.2% for cross-material classification were observed by training on pores of one material and validating on another. These results pave the way to a general-purpose pore classification method usable across materials and process conditions.
- Keywords
- Mechanical Engineering, Mechanics of Materials, General Materials Science, X-ray tomography, Pore classification, Porosity, Powder -bed fusion, Metal additive manufacturing
Downloads
-
1-s2.0-S0264127523001727-main.pdf
- full text (Published version)
- |
- open access
- |
- |
- 6.22 MB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01GTXV0WYHJ6AVNAX0Q5X7B80A
- MLA
- Vandecasteele, Mathieu, et al. “Towards Material and Process Agnostic Features for the Classification of Pore Types in Metal Additive Manufacturing.” MATERIALS & DESIGN, vol. 227, 2023, doi:10.1016/j.matdes.2023.111757.
- APA
- Vandecasteele, M., Heylen, R., Iuso, D., Thanki, A., Philips, W., Witvrouw, A., … Booth, B. (2023). Towards material and process agnostic features for the classification of pore types in metal additive manufacturing. MATERIALS & DESIGN, 227. https://doi.org/10.1016/j.matdes.2023.111757
- Chicago author-date
- Vandecasteele, Mathieu, Rob Heylen, Domenico Iuso, Aditi Thanki, Wilfried Philips, Ann Witvrouw, Dries Verhees, and Brian Booth. 2023. “Towards Material and Process Agnostic Features for the Classification of Pore Types in Metal Additive Manufacturing.” MATERIALS & DESIGN 227. https://doi.org/10.1016/j.matdes.2023.111757.
- Chicago author-date (all authors)
- Vandecasteele, Mathieu, Rob Heylen, Domenico Iuso, Aditi Thanki, Wilfried Philips, Ann Witvrouw, Dries Verhees, and Brian Booth. 2023. “Towards Material and Process Agnostic Features for the Classification of Pore Types in Metal Additive Manufacturing.” MATERIALS & DESIGN 227. doi:10.1016/j.matdes.2023.111757.
- Vancouver
- 1.Vandecasteele M, Heylen R, Iuso D, Thanki A, Philips W, Witvrouw A, et al. Towards material and process agnostic features for the classification of pore types in metal additive manufacturing. MATERIALS & DESIGN. 2023;227.
- IEEE
- [1]M. Vandecasteele et al., “Towards material and process agnostic features for the classification of pore types in metal additive manufacturing,” MATERIALS & DESIGN, vol. 227, 2023.
@article{01GTXV0WYHJ6AVNAX0Q5X7B80A,
abstract = {{The manufacturing of metal parts via powder-bed fusion is often still facing quality issues due to microstructural porosity. Minimizing this porosity remains a priority and requires the optimization of printing process parameters. While the analysis of printed parts using X-ray computed tomography can localize and identify the pore types (e.g. keyhole or lack-of-fusion pores), these pore types can be difficult to identify across printer settings and print materials. Therefore, there is a need for a material and process agnostic approach. This work presents such an approach by considering a set of geometric pore features that do not differ considerably across print scenarios. These features are then leveraged for supervised pore type classification. The distributions of pore features were analyzed in different materials and under varying laser parameters, showing that they behave in a generic way. For classification, it is observed that they outperform other features leveraged in the state-of-the-art for pore classification in a single material, reaching up to 93.0% accuracy. Additionally, accuracies up to 90.2% for cross-material classification were observed by training on pores of one material and validating on another. These results pave the way to a general-purpose pore classification method usable across materials and process conditions.}},
articleno = {{111757}},
author = {{Vandecasteele, Mathieu and Heylen, Rob and Iuso, Domenico and Thanki, Aditi and Philips, Wilfried and Witvrouw, Ann and Verhees, Dries and Booth, Brian}},
issn = {{0264-1275}},
journal = {{MATERIALS & DESIGN}},
keywords = {{Mechanical Engineering,Mechanics of Materials,General Materials Science,X-ray tomography,Pore classification,Porosity,Powder -bed fusion,Metal additive manufacturing}},
language = {{eng}},
pages = {{20}},
title = {{Towards material and process agnostic features for the classification of pore types in metal additive manufacturing}},
url = {{http://doi.org/10.1016/j.matdes.2023.111757}},
volume = {{227}},
year = {{2023}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: