Deep-learning versus greyscale segmentation of voids in X-ray computed tomography images of filament-wound composites
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Deep-learning versus greyscale segmentation of voids in X-ray computed tomography images of filament-wound composites. / Upadhyay, Shailee; George Smith, Abraham; Vandepitte, Dirk; Lomov, Stepan V.; Swolfs, Yentl; Mehdikhani, Mahoor.
I: Composites Part A: Applied Science and Manufacturing, Bind 177, 107937, 2024.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Deep-learning versus greyscale segmentation of voids in X-ray computed tomography images of filament-wound composites
AU - Upadhyay, Shailee
AU - George Smith, Abraham
AU - Vandepitte, Dirk
AU - Lomov, Stepan V.
AU - Swolfs, Yentl
AU - Mehdikhani, Mahoor
N1 - Publisher Copyright: © 2023 Elsevier Ltd
PY - 2024
Y1 - 2024
N2 - Filament-wound composites (FWC) are prone to high void contents, with large and complex-shape voids. It is critical to characterise these voids accurately to understand their effect on part strength. The characterization depends on the accuracy of the analysis technique, for example X-ray computed tomography and the subsequent void segmentation. This paper compares conventional greyscale thresholding to deep-learning (DL) based segmentation. The processing steps for both techniques are discussed. The greyscale thresholding contains segmentation errors due to the simple one-parameter algorithm and the pre-processing operations required for segmentation. This reduces the accuracy of void characterisation. The DL-based segmentation is found to be more accurate for characterisation of void size, shape, and location. The processing-time and system requirements are discussed, helping to determine the suitable segmentation technique based on desired results.
AB - Filament-wound composites (FWC) are prone to high void contents, with large and complex-shape voids. It is critical to characterise these voids accurately to understand their effect on part strength. The characterization depends on the accuracy of the analysis technique, for example X-ray computed tomography and the subsequent void segmentation. This paper compares conventional greyscale thresholding to deep-learning (DL) based segmentation. The processing steps for both techniques are discussed. The greyscale thresholding contains segmentation errors due to the simple one-parameter algorithm and the pre-processing operations required for segmentation. This reduces the accuracy of void characterisation. The DL-based segmentation is found to be more accurate for characterisation of void size, shape, and location. The processing-time and system requirements are discussed, helping to determine the suitable segmentation technique based on desired results.
KW - A. Carbon fibre
KW - B. Porosity
KW - D. CT analysis
KW - E. Filament winding
U2 - 10.1016/j.compositesa.2023.107937
DO - 10.1016/j.compositesa.2023.107937
M3 - Journal article
AN - SCOPUS:85180375861
VL - 177
JO - Composites Part A: Applied Science and Manufacturing
JF - Composites Part A: Applied Science and Manufacturing
SN - 1359-835X
M1 - 107937
ER -
ID: 378176718