Deep-Learning Detection of Cracks in In-Situ Computed Tomograms of Nano-Engineered Composites

Publikation: Bidrag til bog/antologi/rapport › Konferenceabstrakt i proceedings › Forskning › fagfællebedømt

Standard

Deep-Learning Detection of Cracks in In-Situ Computed Tomograms of Nano-Engineered Composites. / Mehdikhani, Mahoor; Upadhyay, Shailee; Soete, Jeroen; Swolfs, Yentl; Smith, Abraham George; Aravand, M. Ali; Liotta, Andrew H.; Wicks, Sunny S.; Wardle, Brian L.; Lomov, Stepan V.; Gorbatikh, Larissa.

Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022. red. / Olesya Zhupanska; Erdogan Madenci. DEStech Publications, Inc., 2022.

Publikation: Bidrag til bog/antologi/rapport › Konferenceabstrakt i proceedings › Forskning › fagfællebedømt

Harvard

Mehdikhani, M, Upadhyay, S, Soete, J, Swolfs, Y, Smith, AG, Aravand, MA, Liotta, AH, Wicks, SS, Wardle, BL, Lomov, SV & Gorbatikh, L 2022, Deep-Learning Detection of Cracks in In-Situ Computed Tomograms of Nano-Engineered Composites. i O Zhupanska & E Madenci (red), Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022. DEStech Publications, Inc., 37th Technical Conference of the American Society for Composites, ASC 2022, Tucson, USA, 19/09/2022.

APA

Mehdikhani, M., Upadhyay, S., Soete, J., Swolfs, Y., Smith, A. G., Aravand, M. A., Liotta, A. H., Wicks, S. S., Wardle, B. L., Lomov, S. V., & Gorbatikh, L. (2022). Deep-Learning Detection of Cracks in In-Situ Computed Tomograms of Nano-Engineered Composites. I O. Zhupanska, & E. Madenci (red.), Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022 DEStech Publications, Inc..

Vancouver

Mehdikhani M, Upadhyay S, Soete J, Swolfs Y, Smith AG, Aravand MA o.a. Deep-Learning Detection of Cracks in In-Situ Computed Tomograms of Nano-Engineered Composites. I Zhupanska O, Madenci E, red., Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022. DEStech Publications, Inc. 2022

Author

Mehdikhani, Mahoor ; Upadhyay, Shailee ; Soete, Jeroen ; Swolfs, Yentl ; Smith, Abraham George ; Aravand, M. Ali ; Liotta, Andrew H. ; Wicks, Sunny S. ; Wardle, Brian L. ; Lomov, Stepan V. ; Gorbatikh, Larissa. / Deep-Learning Detection of Cracks in In-Situ Computed Tomograms of Nano-Engineered Composites. Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022. red. / Olesya Zhupanska ; Erdogan Madenci. DEStech Publications, Inc., 2022.

Bibtex

@inbook{f6ba9f07cacd43848ab4550e65d5bacd,

title = "Deep-Learning Detection of Cracks in In-Situ Computed Tomograms of Nano-Engineered Composites",

abstract = "The deformation and damage development of nano-engineered composites have not yet been investigated in 3D, although it can provide a deeper insight into their damage behavior. To fill this gap, we perform a tensile test on a nano-engineered composite with in-situ X-ray micro-Computed Tomography (micro-CT). The composite is made from woven alumina fibers with grafted carbon nanotubes (CNTs) and epoxy. More diffuse damage seems to exist for the materials with CNTs compared to the baseline material. However, at such resolution where individual fibers are vaguely visible, grayscale thresholding does not accurately characterize the matrix cracks due to their small opening and low contrast with the material itself. Thus, we employ a deep-learning tool, called RootPainter, for segmentation of cracks with small opening in relation to the voxel size, in the 3D images. The results show that RootPainter can reliably identify these small cracks. In addition to the investigation of the mechanical performance of the nano-engineered composite, this study provides a novel and reliable method for the characterization of micro-cracks in in-situ tomograms of these composites.",

author = "Mahoor Mehdikhani and Shailee Upadhyay and Jeroen Soete and Yentl Swolfs and Smith, {Abraham George} and Aravand, {M. Ali} and Liotta, {Andrew H.} and Wicks, {Sunny S.} and Wardle, {Brian L.} and Lomov, {Stepan V.} and Larissa Gorbatikh",

note = "Publisher Copyright: {\textcopyright} Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022. All rights reserved.; 37th Technical Conference of the American Society for Composites, ASC 2022 ; Conference date: 19-09-2022 Through 21-09-2022",

year = "2022",

language = "English",

editor = "Olesya Zhupanska and Erdogan Madenci",

booktitle = "Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022",

publisher = "DEStech Publications, Inc.",

}

RIS

TY - ABST

T1 - Deep-Learning Detection of Cracks in In-Situ Computed Tomograms of Nano-Engineered Composites

AU - Mehdikhani, Mahoor

AU - Upadhyay, Shailee

AU - Soete, Jeroen

AU - Swolfs, Yentl

AU - Smith, Abraham George

AU - Aravand, M. Ali

AU - Liotta, Andrew H.

AU - Wicks, Sunny S.

AU - Wardle, Brian L.

AU - Lomov, Stepan V.

AU - Gorbatikh, Larissa

PY - 2022

Y1 - 2022

N2 - The deformation and damage development of nano-engineered composites have not yet been investigated in 3D, although it can provide a deeper insight into their damage behavior. To fill this gap, we perform a tensile test on a nano-engineered composite with in-situ X-ray micro-Computed Tomography (micro-CT). The composite is made from woven alumina fibers with grafted carbon nanotubes (CNTs) and epoxy. More diffuse damage seems to exist for the materials with CNTs compared to the baseline material. However, at such resolution where individual fibers are vaguely visible, grayscale thresholding does not accurately characterize the matrix cracks due to their small opening and low contrast with the material itself. Thus, we employ a deep-learning tool, called RootPainter, for segmentation of cracks with small opening in relation to the voxel size, in the 3D images. The results show that RootPainter can reliably identify these small cracks. In addition to the investigation of the mechanical performance of the nano-engineered composite, this study provides a novel and reliable method for the characterization of micro-cracks in in-situ tomograms of these composites.

AB - The deformation and damage development of nano-engineered composites have not yet been investigated in 3D, although it can provide a deeper insight into their damage behavior. To fill this gap, we perform a tensile test on a nano-engineered composite with in-situ X-ray micro-Computed Tomography (micro-CT). The composite is made from woven alumina fibers with grafted carbon nanotubes (CNTs) and epoxy. More diffuse damage seems to exist for the materials with CNTs compared to the baseline material. However, at such resolution where individual fibers are vaguely visible, grayscale thresholding does not accurately characterize the matrix cracks due to their small opening and low contrast with the material itself. Thus, we employ a deep-learning tool, called RootPainter, for segmentation of cracks with small opening in relation to the voxel size, in the 3D images. The results show that RootPainter can reliably identify these small cracks. In addition to the investigation of the mechanical performance of the nano-engineered composite, this study provides a novel and reliable method for the characterization of micro-cracks in in-situ tomograms of these composites.

UR - http://www.scopus.com/inward/record.url?scp=85139567528&partnerID=8YFLogxK

M3 - Conference abstract in proceedings

AN - SCOPUS:85139567528

BT - Proceedings of the American Society for Composites - 37th Technical Conference, ASC 2022

A2 - Zhupanska, Olesya

A2 - Madenci, Erdogan

PB - DEStech Publications, Inc.

T2 - 37th Technical Conference of the American Society for Composites, ASC 2022

Y2 - 19 September 2022 through 21 September 2022

ER -

ID: 322792396

Datalogisk Institut