Advanced search
1 file | 1.63 MB Add to list

Damage detection in structures using modal curvatures gapped smoothing method and deep learning

Author
Organization
Abstract
This paper deals with damage detection using a Gapped Smoothing Method (GSM) combined with deep learning. Convolutional Neural Network (CNN) is a model of deep learning. CNN has an input layer, an output layer, and a number of hidden layers that consist of convolutional layers. The input layer is a tensor with shape (number of images) x (image width) x (image height) x (image depth). An activation function is applied each time to this tensor passing through a hidden layer and the last layer is the fully connected layer. After the fully connected layer, the output layer, which is the final layer, is predicted by CNN. In this paper, a complete machine learning system is introduced. The training data was taken from a Finite Element (FE) model. The input images are the contour plots of curvature gapped smooth damage index. A free-free beam is used as a case study. In the first step, the FE model of the beam was used to generate data. The collected data were then divided into two parts, i.e. 70% for training and 30% for validation. In the second step, the proposed CNN was trained using training data and then validated using available data. Furthermore, a vibration experiment on steel damaged beam in free-free support condition was carried out in the laboratory to test the method. A total number of 15 accelerometers were set up to measure the mode shapes and calculate the curvature gapped smooth of the damaged beam. Two scenarios were introduced with different severities of the damage. The results showed that the trained CNN was successful in detecting the location as well as the severity of the damage in the experimental damaged beam.
Keywords
damage detections, vibration-based, gapped smoothing method (GSM), machine learning, deep learning, convolutional neural network, Finite Element Method (FEM), ARTIFICIAL NEURAL-NETWORK, IDENTIFICATION

Downloads

  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.63 MB

Citation

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

MLA
Nguyen, Huong Duong, et al. “Damage Detection in Structures Using Modal Curvatures Gapped Smoothing Method and Deep Learning.” STRUCTURAL ENGINEERING AND MECHANICS, vol. 77, no. 1, 2021, pp. 47–56, doi:10.12989/sem.2021.77.1.047.
APA
Nguyen, H. D., Bui Tien, T., De Roeck, G., & Abdel Wahab, M. (2021). Damage detection in structures using modal curvatures gapped smoothing method and deep learning. STRUCTURAL ENGINEERING AND MECHANICS, 77(1), 47–56. https://doi.org/10.12989/sem.2021.77.1.047
Chicago author-date
Nguyen, Huong Duong, T. Bui Tien, Guido De Roeck, and Magd Abdel Wahab. 2021. “Damage Detection in Structures Using Modal Curvatures Gapped Smoothing Method and Deep Learning.” STRUCTURAL ENGINEERING AND MECHANICS 77 (1): 47–56. https://doi.org/10.12989/sem.2021.77.1.047.
Chicago author-date (all authors)
Nguyen, Huong Duong, T. Bui Tien, Guido De Roeck, and Magd Abdel Wahab. 2021. “Damage Detection in Structures Using Modal Curvatures Gapped Smoothing Method and Deep Learning.” STRUCTURAL ENGINEERING AND MECHANICS 77 (1): 47–56. doi:10.12989/sem.2021.77.1.047.
Vancouver
1.
Nguyen HD, Bui Tien T, De Roeck G, Abdel Wahab M. Damage detection in structures using modal curvatures gapped smoothing method and deep learning. STRUCTURAL ENGINEERING AND MECHANICS. 2021;77(1):47–56.
IEEE
[1]
H. D. Nguyen, T. Bui Tien, G. De Roeck, and M. Abdel Wahab, “Damage detection in structures using modal curvatures gapped smoothing method and deep learning,” STRUCTURAL ENGINEERING AND MECHANICS, vol. 77, no. 1, pp. 47–56, 2021.
@article{8702884,
  abstract     = {{This paper deals with damage detection using a Gapped Smoothing Method (GSM) combined with deep learning. Convolutional Neural Network (CNN) is a model of deep learning. CNN has an input layer, an output layer, and a number of hidden layers that consist of convolutional layers. The input layer is a tensor with shape (number of images) x (image width) x (image height) x (image depth). An activation function is applied each time to this tensor passing through a hidden layer and the last layer is the fully connected layer. After the fully connected layer, the output layer, which is the final layer, is predicted by CNN. In this paper, a complete machine learning system is introduced. The training data was taken from a Finite Element (FE) model. The input images are the contour plots of curvature gapped smooth damage index. A free-free beam is used as a case study. In the first step, the FE model of the beam was used to generate data. The collected data were then divided into two parts, i.e. 70% for training and 30% for validation. In the second step, the proposed CNN was trained using training data and then validated using available data. Furthermore, a vibration experiment on steel damaged beam in free-free support condition was carried out in the laboratory to test the method. A total number of 15 accelerometers were set up to measure the mode shapes and calculate the curvature gapped smooth of the damaged beam. Two scenarios were introduced with different severities of the damage. The results showed that the trained CNN was successful in detecting the location as well as the severity of the damage in the experimental damaged beam.}},
  author       = {{Nguyen, Huong Duong and Bui Tien, T. and De Roeck, Guido and Abdel Wahab, Magd}},
  issn         = {{1225-4568}},
  journal      = {{STRUCTURAL ENGINEERING AND MECHANICS}},
  keywords     = {{damage detections,vibration-based,gapped smoothing method (GSM),machine learning,deep learning,convolutional neural network,Finite Element Method (FEM),ARTIFICIAL NEURAL-NETWORK,IDENTIFICATION}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{47--56}},
  title        = {{Damage detection in structures using modal curvatures gapped smoothing method and deep learning}},
  url          = {{http://dx.doi.org/10.12989/sem.2021.77.1.047}},
  volume       = {{77}},
  year         = {{2021}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: