Estimating Compressive Strength of Concrete Using Deep Convolutional Neural Networks with Digital Microscope Images

Youjin Jang, Yonghan Ahn, Ha Young Kim

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Compressive strength is a critical indicator of concrete quality for ensuring the safety of existing concrete structures. As an alternative to existing nondestructive testing methods, image-based concrete compressive strength estimation models using three deep convolutional neural networks (DCNNs), namely AlexNet, GoogLeNet, and ResNet, were developed for this study. Images of the surfaces of specially produced specimens were obtained using a portable digital microscope, after which the samples were subjected to destructive tests to evaluate their compressive strength. The results were used to create a dataset linking the experimentally determined compressive strength with the image data recorded for each. The results of training, validation, and testing showed that DCNN models largely outperformed the recently proposed image processing-based ANN model. Overall, the ResNet-based model exhibited greater compressive strength estimation accuracy than either the AlexNet- or GoogLeNet-based models. These finding indicate that image data obtained using a portable digital microscope contain patterns that can be correlated with the concrete's compressive strength, enabling the proposed DCNN models to use these patterns to estimate compressive strength. The results of this study demonstrate the applicability of DCNN models using microstructure images as an auxiliary method for the nondestructive evaluation of concrete compressive strength.

Original languageEnglish
Article number04019018
JournalJournal of Computing in Civil Engineering
Volume33
Issue number3
DOIs
Publication statusPublished - 2019 May 1

Fingerprint

Compressive strength
Microscopes
Concretes
Neural networks
Nondestructive examination
Concrete construction
Image processing
Microstructure
Testing

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Computer Science Applications

Cite this

@article{dd46ee84543045efbf7775c81a9e1f9d,
title = "Estimating Compressive Strength of Concrete Using Deep Convolutional Neural Networks with Digital Microscope Images",
abstract = "Compressive strength is a critical indicator of concrete quality for ensuring the safety of existing concrete structures. As an alternative to existing nondestructive testing methods, image-based concrete compressive strength estimation models using three deep convolutional neural networks (DCNNs), namely AlexNet, GoogLeNet, and ResNet, were developed for this study. Images of the surfaces of specially produced specimens were obtained using a portable digital microscope, after which the samples were subjected to destructive tests to evaluate their compressive strength. The results were used to create a dataset linking the experimentally determined compressive strength with the image data recorded for each. The results of training, validation, and testing showed that DCNN models largely outperformed the recently proposed image processing-based ANN model. Overall, the ResNet-based model exhibited greater compressive strength estimation accuracy than either the AlexNet- or GoogLeNet-based models. These finding indicate that image data obtained using a portable digital microscope contain patterns that can be correlated with the concrete's compressive strength, enabling the proposed DCNN models to use these patterns to estimate compressive strength. The results of this study demonstrate the applicability of DCNN models using microstructure images as an auxiliary method for the nondestructive evaluation of concrete compressive strength.",
author = "Youjin Jang and Yonghan Ahn and Kim, {Ha Young}",
year = "2019",
month = "5",
day = "1",
doi = "10.1061/(ASCE)CP.1943-5487.0000837",
language = "English",
volume = "33",
journal = "Journal of Computing in Civil Engineering",
issn = "0887-3801",
publisher = "American Society of Civil Engineers (ASCE)",
number = "3",

}

Estimating Compressive Strength of Concrete Using Deep Convolutional Neural Networks with Digital Microscope Images. / Jang, Youjin; Ahn, Yonghan; Kim, Ha Young.

In: Journal of Computing in Civil Engineering, Vol. 33, No. 3, 04019018, 01.05.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Estimating Compressive Strength of Concrete Using Deep Convolutional Neural Networks with Digital Microscope Images

AU - Jang, Youjin

AU - Ahn, Yonghan

AU - Kim, Ha Young

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Compressive strength is a critical indicator of concrete quality for ensuring the safety of existing concrete structures. As an alternative to existing nondestructive testing methods, image-based concrete compressive strength estimation models using three deep convolutional neural networks (DCNNs), namely AlexNet, GoogLeNet, and ResNet, were developed for this study. Images of the surfaces of specially produced specimens were obtained using a portable digital microscope, after which the samples were subjected to destructive tests to evaluate their compressive strength. The results were used to create a dataset linking the experimentally determined compressive strength with the image data recorded for each. The results of training, validation, and testing showed that DCNN models largely outperformed the recently proposed image processing-based ANN model. Overall, the ResNet-based model exhibited greater compressive strength estimation accuracy than either the AlexNet- or GoogLeNet-based models. These finding indicate that image data obtained using a portable digital microscope contain patterns that can be correlated with the concrete's compressive strength, enabling the proposed DCNN models to use these patterns to estimate compressive strength. The results of this study demonstrate the applicability of DCNN models using microstructure images as an auxiliary method for the nondestructive evaluation of concrete compressive strength.

AB - Compressive strength is a critical indicator of concrete quality for ensuring the safety of existing concrete structures. As an alternative to existing nondestructive testing methods, image-based concrete compressive strength estimation models using three deep convolutional neural networks (DCNNs), namely AlexNet, GoogLeNet, and ResNet, were developed for this study. Images of the surfaces of specially produced specimens were obtained using a portable digital microscope, after which the samples were subjected to destructive tests to evaluate their compressive strength. The results were used to create a dataset linking the experimentally determined compressive strength with the image data recorded for each. The results of training, validation, and testing showed that DCNN models largely outperformed the recently proposed image processing-based ANN model. Overall, the ResNet-based model exhibited greater compressive strength estimation accuracy than either the AlexNet- or GoogLeNet-based models. These finding indicate that image data obtained using a portable digital microscope contain patterns that can be correlated with the concrete's compressive strength, enabling the proposed DCNN models to use these patterns to estimate compressive strength. The results of this study demonstrate the applicability of DCNN models using microstructure images as an auxiliary method for the nondestructive evaluation of concrete compressive strength.

UR - http://www.scopus.com/inward/record.url?scp=85062354215&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062354215&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)CP.1943-5487.0000837

DO - 10.1061/(ASCE)CP.1943-5487.0000837

M3 - Article

AN - SCOPUS:85062354215

VL - 33

JO - Journal of Computing in Civil Engineering

JF - Journal of Computing in Civil Engineering

SN - 0887-3801

IS - 3

M1 - 04019018

ER -