Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/162089
Full metadata record
DC FieldValueLanguage
dc.contributor.authorQian, Hanjieen_US
dc.contributor.authorLi, Yeen_US
dc.contributor.authorYang, Jianfeien_US
dc.contributor.authorXie, Lihuaen_US
dc.contributor.authorTan, Kang Haien_US
dc.date.accessioned2022-10-04T02:48:39Z-
dc.date.available2022-10-04T02:48:39Z-
dc.date.issued2022-
dc.identifier.citationQian, H., Li, Y., Yang, J., Xie, L. & Tan, K. H. (2022). Image-based microstructure classification of mortar and paste using convolutional neural networks and transfer learning. Cement and Concrete Composites, 129, 104496-. https://dx.doi.org/10.1016/j.cemconcomp.2022.104496en_US
dc.identifier.issn0958-9465en_US
dc.identifier.urihttps://hdl.handle.net/10356/162089-
dc.description.abstractThe scanning electron microscopy (SEM) is widely applied to analyze the microstructure of concrete. SEM results are generally analyzed by human experts with different levels of expertise, and some tasks are extremely time consuming. In this study, a dataset consisting of 3600 SEM images was first built. Then, a deep-learning framework based on a convolutional neural network (CNN) was implemented for classifying cement paste mixtures with different water-to-cement ratios and different amounts of added silica fume. The accuracy of the classification reaches a high level of 94%. To improve the generality and efficiency of the proposed method, transfer learning technology with three transfer configurations was implemented and tested on a dataset of mortar samples. The result indicated that transfer learning enabled the new model to achieve higher accuracy and generality than training a network with randomly initialized parameters. The model accuracy increases with an increasing number of free convolutional layers, although the training time becomes longer. Finally, the critical features that greatly influence the classification were identified via visualization of the CNN model. Relatively small unhydrated cement particles have higher influence on mixtures with lower water-to-binder ratios, whereas hydration products are more influential in the case of mixtures with higher amounts of water or without silica fume.en_US
dc.description.sponsorshipMinistry of National Development (MND)en_US
dc.language.isoenen_US
dc.relationCOT-V2-2019-1en_US
dc.relation.ispartofCement and Concrete Compositesen_US
dc.rights© 2022 Elsevier Ltd. All rights reserved.en_US
dc.subjectEngineering::Civil engineeringen_US
dc.subjectEngineering::Electrical and electronic engineeringen_US
dc.titleImage-based microstructure classification of mortar and paste using convolutional neural networks and transfer learningen_US
dc.typeJournal Articleen
dc.contributor.schoolSchool of Civil and Environmental Engineeringen_US
dc.contributor.schoolSchool of Electrical and Electronic Engineeringen_US
dc.identifier.doi10.1016/j.cemconcomp.2022.104496-
dc.identifier.scopus2-s2.0-85127198516-
dc.identifier.volume129en_US
dc.identifier.spage104496en_US
dc.subject.keywordsConcrete Microstructureen_US
dc.subject.keywordsConvolutional Neural Networksen_US
dc.description.acknowledgementThis work was partially supported by the Ministry of National Development, Singapore, under its Cities of Tomorrow R&D Programme (CoT Award No. COT-V2-2019-1), the National Natural Science Foundation of China (No. 52008136), the Shenzhen Science and Technology Program (No. GXWD20201230155427003-20200823110420001), and the Foundation of Guangdong Key Laboratory of Oceanic Civil Engineering (No. LMCE202104).en_US
item.grantfulltextnone-
item.fulltextNo Fulltext-
Appears in Collections:CEE Journal Articles
EEE Journal Articles

SCOPUSTM   
Citations 50

3
Updated on Jan 31, 2023

Web of ScienceTM
Citations 50

2
Updated on Jan 28, 2023

Page view(s)

19
Updated on Feb 2, 2023

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.