Dr Xiaodong Xu Xiaodong.Xu@uwe.ac.uk
Senior Lecturer in Engineering Principles
Identifying fibre orientations for fracture process zone characterization in scaled centre-notched quasi-isotropic carbon/epoxy laminates with a convolutional neural network
Xu, Xiaodong; Abbas, Aser; Lee, Juhyeong
Authors
Aser Abbas
Juhyeong Lee
Abstract
This paper presents a novel X-ray Computed Tomography (CT) image analysis method to characterize the Fracture Process Zone (FPZ) in scaled centre-notched quasi-isotropic carbon/epoxy laminates. A total of 61 CT images of a small specimen were used to fine-tune a pre-trained Convolutional Neural Network (CNN) (i.e., VGG16) to classify fibre orientations. The proposed CNN model achieves a 100% accuracy when tested on the CT images of the same scale as the training set. However, the accuracy drops to a maximum of 84% when tested on unlabelled images of the specimens having larger scales potentially due to their lower resolutions. Another code was developed to automatically measure the size of the FPZ based on the CNN identified 0°plies in the largest specimen which agrees well with the manual measurement (on average within 3.3%). The whole classification and measurement process can be automated without human intervention.
Citation
Xu, X., Abbas, A., & Lee, J. (2022). Identifying fibre orientations for fracture process zone characterization in scaled centre-notched quasi-isotropic carbon/epoxy laminates with a convolutional neural network. Engineering Fracture Mechanics, 274, 108768. https://doi.org/10.1016/j.engfracmech.2022.108768
Journal Article Type | Article |
---|---|
Acceptance Date | Aug 29, 2022 |
Online Publication Date | Sep 2, 2022 |
Publication Date | Oct 15, 2022 |
Deposit Date | Aug 29, 2022 |
Publicly Available Date | Oct 3, 2022 |
Journal | Engineering Fracture Mechanics |
Print ISSN | 0013-7944 |
Electronic ISSN | 1873-7315 |
Publisher | Elsevier |
Peer Reviewed | Peer Reviewed |
Volume | 274 |
Pages | 108768 |
DOI | https://doi.org/10.1016/j.engfracmech.2022.108768 |
Keywords | Laminates; Fracture; X-ray Computed Tomography; Convolutional Neural Network |
Public URL | https://uwe-repository.worktribe.com/output/9911107 |
Publisher URL | https://www.sciencedirect.com/science/article/pii/S0013794422004878 |
Files
Identifying fibre orientations for fracture process zone characterisation in scaled centre-notched quasi-isotropic carbon/epoxy laminates with a convolutional neural network
(908 Kb)
PDF
Licence
http://creativecommons.org/licenses/by-nc-nd/4.0/
Publisher Licence URL
http://creativecommons.org/licenses/by-nc-nd/4.0/
Copyright Statement
This is the author’s accepted manuscript. The final published version is available here: URL
Identifying fibre orientations for fracture process zone characterisation in scaled centre-notched quasi-isotropic carbon/epoxy laminates with a convolutional neural network Picture Identifying fibre orientations for fracture process zone characterisati
(2 Mb)
PDF
Licence
http://creativecommons.org/licenses/by/4.0/
Publisher Licence URL
http://creativecommons.org/licenses/by/4.0/
You might also like
Developing test methods for compression after lightning strikes
(2023)
Journal Article
Experimental study on the mechanical behaviour of Carbon-fibre z-pin reinforced curved composite laminates under four-point bending
(2022)
Presentation / Conference
Numerical investigation of compression-after-lightning strike characteristics of Carbon/epoxy laminates
(2022)
Presentation / Conference
An Experimental Study of Crack Propagation in Stiffened Over height Compact Tension (SOCT) Specimens
(2022)
Presentation / Conference
Downloadable Citations
About UWE Bristol Research Repository
Administrator e-mail: repository@uwe.ac.uk
This application uses the following open-source libraries:
SheetJS Community Edition
Apache License Version 2.0 (http://www.apache.org/licenses/)
PDF.js
Apache License Version 2.0 (http://www.apache.org/licenses/)
Font Awesome
SIL OFL 1.1 (http://scripts.sil.org/OFL)
MIT License (http://opensource.org/licenses/mit-license.html)
CC BY 3.0 ( http://creativecommons.org/licenses/by/3.0/)
Powered by Worktribe © 2024
Advanced Search