Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 4.37 MB
Add to list
  1. Search results
  2. Detection of corrosion on steel struc...

Detection of corrosion on steel structures using an artificial neural network

Mojtaba Khayatazad (UGent) , Matthias Honhon and Wim De Waele (UGent)
(2023) STRUCTURE AND INFRASTRUCTURE ENGINEERING. 19(12). p.1860-1871
Author
Organization
Project
Abstract
Image based-corrosion detection has become a widespread practice for steel structures, but fine-tuning their model parameters is time-consuming. Alternatively, convolutional neural networks (CNNs) can also be trained fast and automatically, but they demand a huge training dataset. In this paper, a corrosion detection approach based on an artificial neural network (ANN) whose training dataset size is less than 0.1% of that of typical CNNs is introduced. The input layer of the proposed ANN consists of textural and color properties. In the present work, different color spaces and textural properties are examined for their impact on the robustness of the ANN. Results reveal that the best color channels can be achieved by combining CIE L*u*v* and YUV color spaces. Moreover, energy is selected as the best texture feature with respect to the ANN robustness. The proposed ANN outperforms an available image processing algorithm from the perspective of both speed and accuracy. In conclusion, this ANN can be used for actual applications after a fast and straightforward training step.
Keywords
Steel structures, image-based corrosion detection, artificial neural networks, deep hidden layers, color space, texture metric, INSPECTION

Downloads

  • Download
    Wim De Waele et Al Accepted Manuscript.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 1.42 MB
  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 2.95 MB

Citation

Please use this url to cite or link to this publication:

MLA
Khayatazad, Mojtaba, et al. “Detection of Corrosion on Steel Structures Using an Artificial Neural Network.” STRUCTURE AND INFRASTRUCTURE ENGINEERING, vol. 19, no. 12, 2023, pp. 1860–71, doi:10.1080/15732479.2022.2069272.
APA
Khayatazad, M., Honhon, M., & De Waele, W. (2023). Detection of corrosion on steel structures using an artificial neural network. STRUCTURE AND INFRASTRUCTURE ENGINEERING, 19(12), 1860–1871. https://doi.org/10.1080/15732479.2022.2069272
Chicago author-date
Khayatazad, Mojtaba, Matthias Honhon, and Wim De Waele. 2023. “Detection of Corrosion on Steel Structures Using an Artificial Neural Network.” STRUCTURE AND INFRASTRUCTURE ENGINEERING 19 (12): 1860–71. https://doi.org/10.1080/15732479.2022.2069272.
Chicago author-date (all authors)
Khayatazad, Mojtaba, Matthias Honhon, and Wim De Waele. 2023. “Detection of Corrosion on Steel Structures Using an Artificial Neural Network.” STRUCTURE AND INFRASTRUCTURE ENGINEERING 19 (12): 1860–1871. doi:10.1080/15732479.2022.2069272.
Vancouver
1.
Khayatazad M, Honhon M, De Waele W. Detection of corrosion on steel structures using an artificial neural network. STRUCTURE AND INFRASTRUCTURE ENGINEERING. 2023;19(12):1860–71.
IEEE
[1]
M. Khayatazad, M. Honhon, and W. De Waele, “Detection of corrosion on steel structures using an artificial neural network,” STRUCTURE AND INFRASTRUCTURE ENGINEERING, vol. 19, no. 12, pp. 1860–1871, 2023.
@article{8743256,
  abstract     = {{Image based-corrosion detection has become a widespread practice for steel structures, but fine-tuning their model parameters is time-consuming. Alternatively, convolutional neural networks (CNNs) can also be trained fast and automatically, but they demand a huge training dataset. In this paper, a corrosion detection approach based on an artificial neural network (ANN) whose training dataset size is less than 0.1% of that of typical CNNs is introduced. The input layer of the proposed ANN consists of textural and color properties. In the present work, different color spaces and textural properties are examined for their impact on the robustness of the ANN. Results reveal that the best color channels can be achieved by combining CIE L*u*v* and YUV color spaces. Moreover, energy is selected as the best texture feature with respect to the ANN robustness. The proposed ANN outperforms an available image processing algorithm from the perspective of both speed and accuracy. In conclusion, this ANN can be used for actual applications after a fast and straightforward training step.}},
  author       = {{Khayatazad, Mojtaba and Honhon, Matthias and De Waele, Wim}},
  issn         = {{1573-2479}},
  journal      = {{STRUCTURE AND INFRASTRUCTURE ENGINEERING}},
  keywords     = {{Steel structures,image-based corrosion detection,artificial neural networks,deep hidden layers,color space,texture metric,INSPECTION}},
  language     = {{eng}},
  number       = {{12}},
  pages        = {{1860--1871}},
  title        = {{Detection of corrosion on steel structures using an artificial neural network}},
  url          = {{http://doi.org/10.1080/15732479.2022.2069272}},
  volume       = {{19}},
  year         = {{2023}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: