2022
DOI: 10.3389/fbuil.2022.816644
|View full text |Cite
|
Sign up to set email alerts
|

Generative Adversarial Networks for Data Generation in Structural Health Monitoring

Abstract: Structural Health Monitoring (SHM) has been continuously benefiting from the advancements in the field of data science. Various types of Artificial Intelligence (AI) methods have been utilized to assess and evaluate civil structures. In AI, Machine Learning (ML) and Deep Learning (DL) algorithms require plenty of datasets to train; particularly, the more data DL models are trained with, the better output it yields. Yet, in SHM applications, collecting data from civil structures through sensors is expensive and… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
7
1

Relationship

1
7

Authors

Journals

citations
Cited by 10 publications
(5 citation statements)
references
References 46 publications
0
5
0
Order By: Relevance
“…In this study, the groove image generated by WGAN-GP is inserted into the disease-free road image to generate new training data. Firstly, the Poisson algorithm is used to output the fused image [ 44 ], and then the synthesized image is output by the color migration algorithm [ 45 ]. When integrating the image, the image should be integrated as real as possible.…”
Section: Methodsmentioning
confidence: 99%
“…In this study, the groove image generated by WGAN-GP is inserted into the disease-free road image to generate new training data. Firstly, the Poisson algorithm is used to output the fused image [ 44 ], and then the synthesized image is output by the color migration algorithm [ 45 ]. When integrating the image, the image should be integrated as real as possible.…”
Section: Methodsmentioning
confidence: 99%
“…To identify and clarify the position of GANs in the civil SHM field, in terms of the type of GAN applications studied by the researchers, an illustrative figure is made (Figure 9) which shows the classification of the applications of GANs in civil SHM and the corresponding studies with the GAN models used in each study. As the main concept of GAN is to learn data domain and data generation, some studies solely studied data generation [ (Kanghyeok and do Hyoung, 2019;Xiong and Chen, 2019;Zhang and Wang, 2019;Tsialiamanis et al, 2020;Xu et al, 2021;Yu et al, 2021;Tsialiamanis et al, 2022a;Heesch et al, 2021;Colombera et al, 2021;Luleci et al, 2022b;Luleci et al, 2023)] (a total of 11 studies) by using original GAN or other GAN variants. Thus, the data generation category is separated from other categories.…”
Section: Generative Adversarial Network In Civil Structural Health Mo...mentioning
confidence: 99%
“…The authors concluded that the reconstructed data is in good agreement with the actual dataset. Luleci et al (2022b) pointed out the problem of data scarcity in SHM and employed the WDCGAN-GP (or Deep Convolutional WGAN-GP) model to tackle the challenge. In that study, they first trained the model with acceleration data whose domain is damaged (bolt-loosening).…”
Section: Studies Published In 2022 (8 Papers)mentioning
confidence: 99%
“…Wang et al monitored the operating status of wind turbines using a least squares GAN [27]. Luleci et al generated vibration datasets related to real damages in civil structures using a one-dimensional GAN with gradient penalty, and they applied this approach to vibration-based damage diagnosis [28]. These applications demonstrate the strength of GAN models.…”
Section: Introductionmentioning
confidence: 99%