Generative adversarial networks for labeled acceleration data augmentation for structural damage detection

Luleci, Furkan; Çatbaş, F. Necati; Avcı, Onur

doi:10.1007/s13349-022-00627-8

Cited by 25 publications

(11 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Data domain translation [ (Tsialiamanis et al, 2022b;Luleci et al, 2022c;Zhang et al, 2020;Yasuno et al, 2020;Bianchi et al, 2021)] (a total of five studies) is seen less frequently than the other applications in the literature but could be very promising and advantageous to many other problems in civil SHM. The core research problem of domain translation applications is learning the distinct mapping between the data domains.…”

Section: Frontiers In Built Environmentmentioning

confidence: 99%

“…In another study, the same authors of the previous studies introduced another concept (Luleci et al, 2022c). In that study, the authors used CycleGAN, which is built on convolutions, and adopted the WGAN-GP model.…”

Section: Studies Published In 2022 (8 Papers)mentioning

confidence: 99%

“…FIGURE 13(A) Frequency domains of real and synthetic (translated from damaged) undamaged acceleration response signal at joint 1, (B) Frequency domains of real and synthetic (translated from undamaged) damaged acceleration response signal at Joint 1(Luleci et al, 2022c).…”

mentioning

confidence: 99%

See 2 more Smart Citations

A literature review: Generative adversarial networks for civil structural health monitoring

Luleci

Çatbaş

Avcı

2022

Front. Built Environ.

Self Cite

View full text Add to dashboard Cite

Structural Health Monitoring (SHM) of civil structures has been constantly evolving with novel methods, advancements in data science, and more accessible technology to address issues related to structural safety, operations, and resiliency. Research and development in the civil SHM field during the last few decades have been progressive due to the increasing use of Artificial Intelligence (AI) methods such as Machine Learning (ML) and Deep Learning (DL). Particularly, Generative Adversarial Networks (GAN), which is a subfamily of Deep Learning has been highly favored in the SHM community within the last couple of years. After its release in 2014, GANs (original GAN and other GAN variants) have been in use for a wide variety of applications in various disciplines, and it has been one of the most popular research topics in the AI-ML domain. While there has not been a review study on the applications of GAN in the civil SHM field, this paper aims to fill this gap by presenting a literature review of the studies that employed GAN specifically in civil SHM applications from 2014 to date, in a condensed format. This study intends to inform SHM practitioners and researchers about GANs and present the highlights of the published work on GANs in the civil SHM field.

show abstract

Section: Frontiers In Built Environmentmentioning

confidence: 99%

Section: Studies Published In 2022 (8 Papers)mentioning

confidence: 99%

See 1 more Smart Citation

A literature review: Generative adversarial networks for civil structural health monitoring

Luleci

Çatbaş

Avcı

2022

Front. Built Environ.

Self Cite

View full text Add to dashboard Cite

show abstract

“…However, DL-based classifiers can only identify the vibration data as a pre-defined static label, during which procedure many dynamic features of the structure are ignored by the network. The issue can be addressed by the unsupervised DL method, which uses the generative network to automatically learn the important features from the input data [15]. Guo et al [16] used a convolutional autoencoder to compress and reconstruct the vibrational response of a gymnasium and proposed a score function to quantify the input data.…”

Section: Introductionmentioning

confidence: 99%

Physics-informed deep learning for structural vibration identification and its application on a benchmark structure

Zhang,

Guo,

Zhang

et al. 2023

Phil. Trans. R. Soc. A.

View full text Add to dashboard Cite

Structural vibration identification is an important task in civil engineering that is based on processing measured data from structural monitoring. However, predicting the response at unsensed locations based on limited sensor data can be challenging. Deep learning (DL) methods have shown promise in vibration data feature extraction and generation, but they struggle to capture the underlying physics laws and dynamic equations that govern vibration identification. This paper presents a novel framework called physics-informed deep learning (PIDL) that combines deep generative networks with structural dynamics knowledge to address these challenges. The PIDL framework consists of a data-driven convolutional neural network for structural excitation identification and a physics-informed variational autoencoder for explicit time-domain (ETD) vibration analysis with the generated unit impulse response (UIR) signal of the measured structure. The proposed framework is evaluated on a benchmark structure for structural health monitoring, demonstrating its effectiveness in extracting physics-related dynamics features and accurately identifying excitation signals and latent physics parameters across different damage patterns. Additionally, the incorporation of an ETD method-aided convolution function in the loss function aligns the generated UIR signals with the dynamic properties of the measured structure. Compared with conventional DL-based vibration analysis methods, the PIDL framework offers improved accuracy and reliability by integrating structural dynamics knowledge. This study contributes to the advancement of structural vibration identification and showcases the potential of the PIDL framework in civil structure monitoring applications. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 2)'.

show abstract

“…Generative adversarial networks (GAN) have been recently explored in the civil SHM domain [ 14 ]. They were investigated to address the data scarcity problem [ 15 , 16 , 17 ] and used for the first time in undamaged-to-damaged domain translation applications where the aim is to obtain the damaged response while the civil structure is intact or vice versa [ 18 , 19 ]. Members of the CITRS group are motivated to present some of the recent advances in SHM and other notable studies from the literature.…”

Section: Introductionmentioning

confidence: 99%

Extended Reality (XR) for Condition Assessment of Civil Engineering Structures: A Literature Review

Çatbaş

Luleci

Zakaria

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Condition assessment of civil engineering structures has been an active research area due to growing concerns over the safety of aged as well as new civil structures. Utilization of emerging immersive visualization technologies such as Virtual Reality (VR), Augmented Reality (AR), and Mixed Reality (MR) in the architectural, engineering, and construction (AEC) industry has demonstrated that these visualization tools can be paradigm-shifting. Extended Reality (XR), an umbrella term for VR, AR, and MR technologies, has found many diverse use cases in the AEC industry. Despite this exciting trend, there is no review study on the usage of XR technologies for the condition assessment of civil structures. Thus, the present paper aims to fill this gap by presenting a literature review encompassing the utilization of XR technologies for the condition assessment of civil structures. This study aims to provide essential information and guidelines for practitioners and researchers on using XR technologies to maintain the integrity and safety of civil structures.

show abstract

Generative adversarial networks for labeled acceleration data augmentation for structural damage detection

Cited by 25 publications

References 44 publications

A literature review: Generative adversarial networks for civil structural health monitoring

A literature review: Generative adversarial networks for civil structural health monitoring

Physics-informed deep learning for structural vibration identification and its application on a benchmark structure

Extended Reality (XR) for Condition Assessment of Civil Engineering Structures: A Literature Review

Contact Info

Product

Resources

About