Digital image correlation (DIC) based damage detection for CFRP laminates by using machine learning based image semantic segmentation

Wang, Y; Luo, Q; Xie, H; Li, Q; Sun, G

Digital image correlation (DIC) based damage detection for CFRP laminates by using machine learning based image semantic segmentation

Wang, Y Luo, Q

Xie, H Li, Q Sun, G

Permalink

Publisher:: PERGAMON-ELSEVIER SCIENCE LTD
Publication Type:: Journal Article
Citation:: International Journal of Mechanical Sciences, 2022, 230
Issue Date:: 2022-09-15

Closed Access

	Filename	Description	Size
	Digital image correlation (DIC) based damage detection for CFRP laminates by using machine learning based image semantic segmentation.pdf		14.38 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, Y
dc.contributor.author	Luo, Q https://orcid.org/0000-0001-5727-9290
dc.contributor.author	Xie, H
dc.contributor.author	Li, Q
dc.contributor.author	Sun, G
dc.date.accessioned	2023-03-15T05:22:09Z
dc.date.available	2023-03-15T05:22:09Z
dc.date.issued	2022-09-15
dc.identifier.citation	International Journal of Mechanical Sciences, 2022, 230
dc.identifier.issn	0020-7403
dc.identifier.issn	1879-2162
dc.identifier.uri	http://hdl.handle.net/10453/167350
dc.description.abstract	Vision-based damage detection in carbon fiber-reinforced plastic (CFRP) composites can be interfered by such factors as surface texture, stains and lighting. A digital image correlation (DIC) based surface strain monitoring technique, on the other hand, enables to track the change of strain distribution. It is promising to develop a new approach for online structural health monitoring (SHM), in which the DIC strain contours can be scrutinized automatically and the results are no longer substantially subjected to human interference. In this study, a convolutional neural network (CNN) based image semantic segmentation technique is proposed for pixel-level classification of DIC strain field images. A DeepLabv3+ encoder-decoder architecture combined with different feature extraction networks is investigated. The training dataset and validation of the model are obtained through finite element (FE) simulation. The images of quasi-static axial tensile strain field obtained from 2D-DIC are used to test the accuracy and efficiency of the trained CNN model. It is found that use of a pre-trained ResNet-50 CNN model as the backbone network of DeepLabv3+ architecture through a transfer learning algorithm can make the semantic segmentation results reach a mean intersection over union of 0.9236. The prediction accuracy of the semantic segmentation model trained from the FE data is comparable with that of the model trained from the experimental data, which demonstrates that the proposed machine learning approach for DIC measurement is cost-effective.
dc.language	English
dc.publisher	PERGAMON-ELSEVIER SCIENCE LTD
dc.relation.ispartof	International Journal of Mechanical Sciences
dc.relation.isbasedon	10.1016/j.ijmecsci.2022.107529
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0905 Civil Engineering, 0910 Manufacturing Engineering, 0913 Mechanical Engineering
dc.subject.classification	Mechanical Engineering & Transports
dc.title	Digital image correlation (DIC) based damage detection for CFRP laminates by using machine learning based image semantic segmentation
dc.type	Journal Article
utslib.citation.volume	230
utslib.for	0905 Civil Engineering
utslib.for	0910 Manufacturing Engineering
utslib.for	0913 Mechanical Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Mechanical and Mechatronic Engineering
utslib.copyright.status	closed_access	*
dc.date.updated	2023-03-15T05:19:30Z
pubs.publication-status	Published
pubs.volume	230

Abstract:

Vision-based damage detection in carbon fiber-reinforced plastic (CFRP) composites can be interfered by such factors as surface texture, stains and lighting. A digital image correlation (DIC) based surface strain monitoring technique, on the other hand, enables to track the change of strain distribution. It is promising to develop a new approach for online structural health monitoring (SHM), in which the DIC strain contours can be scrutinized automatically and the results are no longer substantially subjected to human interference. In this study, a convolutional neural network (CNN) based image semantic segmentation technique is proposed for pixel-level classification of DIC strain field images. A DeepLabv3+ encoder-decoder architecture combined with different feature extraction networks is investigated. The training dataset and validation of the model are obtained through finite element (FE) simulation. The images of quasi-static axial tensile strain field obtained from 2D-DIC are used to test the accuracy and efficiency of the trained CNN model. It is found that use of a pre-trained ResNet-50 CNN model as the backbone network of DeepLabv3+ architecture through a transfer learning algorithm can make the semantic segmentation results reach a mean intersection over union of 0.9236. The prediction accuracy of the semantic segmentation model trained from the FE data is comparable with that of the model trained from the experimental data, which demonstrates that the proposed machine learning approach for DIC measurement is cost-effective.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/167350