A Damage Localization Approach for Rahmen Bridge Based on Convolutional Neural Network

Lee, Kanghyeok; Byun, Namju; Shin, Do Hyoung

doi:10.1007/s12205-020-0707-9

Cited by 30 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to [48], it is possible to demonstrate whether each model was well trained with fluctuations in the losses; thus, this study confirmed the training and test losses of all models. Figure 9 illustrates examples of changes in training and test losses as each deep learning model is trained.…”

Section: Resultssupporting

confidence: 71%

“…If the sequence of the acquired data is important information, a recurrent neural network (RNN) may be effective among deep learning techniques, e.g., [43,44]. For 2D image data, a convolutional neural network (CNN) is primarily used, e.g., [45,46]; however, CNNs also demonstrated good performance in analyzing signal data (sequential data), such as audio and signal data, e.g., [47,48]. Contrarily, the weekly meteorological data, which are intended to be used in this study, are measured hourly, and are time series data.…”

Section: Overview Of Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of Heavy Rain Damage Using Deep Learning

Lee

Choi

Shin

et al. 2020

Water

Self Cite

View full text Add to dashboard Cite

Heavy rain damage prediction models were developed with a deep learning technique for predicting the damage to a region before heavy rain damage occurs. As a dependent variable, a damage scale comprising three categories (minor, significant, severe) was used, and meteorological data 7 days before the damage were used as independent variables. A deep neural network (DNN), convolutional neural network (CNN), and recurrent neural network (RNN), which are representative deep learning techniques, were employed for the model development. Each model was trained and tested 30 times to evaluate the predictive performance. As a result of evaluating the predicted performance, the DNN-based model and the CNN-based model showed good performance, and the RNN-based model was analyzed to have relatively low performance. For the DNN-based model, the convergence epoch of the training showed a relatively wide distribution, which may lead to difficulties in selecting an epoch suitable for practical use. Therefore, the CNN-based model would be acceptable for the heavy rain damage prediction in terms of the accuracy and robustness. These results demonstrated the applicability of deep learning in the development of the damage prediction model. The proposed prediction model can be used for disaster management as the basic data for decision making.

show abstract

Section: Resultssupporting

confidence: 71%

Section: Overview Of Deep Learningmentioning

confidence: 99%

Prediction of Heavy Rain Damage Using Deep Learning

Lee

Choi

Shin

et al. 2020

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…5,6 In particular, for the model-based approach, model updating, which calibrates the behavior of the actual structure with an analytic bridge model, has a significant effect on the accuracy of damage detection. 7 In other words, to use the model-based approach, the analytical model must be able to simulate the same behavior as that of the actual bridge; however, the model updating method is unrealistic because of technical limitations of the existing analytical models, that is, analytical models cannot accurately reflect changes in damage or some boundary conditions of the bridge. In view of these technical limitations, this study aimed to develop an approach for damage detection based on a data-driven approach rather than a model-based approach.…”

Section: Related Studiesmentioning

confidence: 99%

“…In addition, several recent studies demonstrate that a CNN can extract appropriate DSFs and performs well in the damage detection of structures. 7,30,31 For example, Lin et al 30 analyzed raw-acceleration data of a simple beam using a convolutional neural network, which is a deep-learning technique, and extracted CNN-based DSF, which was used for damage detection. Particularly, comparing the damage detection performances using both the CNN-based DSF and wavelet coefficients, they showed that more accurate and robust results could be obtained using CNN-based DSF.…”

Section: Related Studiesmentioning

confidence: 99%

“…In addition, based on the results, they generated a DSF that represented the probability of the damage; subsequently, they showed that it was possible to perform damage detection using the aforementioned DSF. Lee et al 7 proposed a CNN-based damage detection approach using the strain data measured by means of static loading on an actual, reinforcement concrete Rahmen bridge. They derived DSF via CNN feature extraction and theoretically verified that the derived DSF could be used for damage detection.…”

Section: Related Studiesmentioning

confidence: 99%

See 1 more Smart Citation

Field experiment on a PSC-I bridge for convolutional autoencoder-based damage detection

Lee

Jeong

Sim

et al. 2020

Structural Health Monitoring

Self Cite

View full text Add to dashboard Cite

In this study, a field experiment was performed for damage detection on a PSC-I bridge based on a convolutional autoencoder using the damage detection approach proposed in a previous study by the authors. The field experiment measured the acceleration and strain data of the PSC-I bridge while a single vehicle passed the bridge; subsequently, these data were used to train and test the convolutional autoencoder–based damage detection model. The results of the test showed that the convolutional autoencoder–based model could perform accurate and robust damage detection. Furthermore, these findings indicate that the convolutional autoencoder–based damage detection could also perform satisfactorily in practice. The results of this study can form the basis to facilitate the adoption of the convolutional autoencoder–based damage detection method to monitor bridges in practice.

show abstract

A Review of the Application of CNN-Based Computer Vision in Civil Infrastructure Maintenance

Cai

et al. 2021

Proceedings of the 25th International Symposium on Advancement of Construction Management and Real Estate

View full text Add to dashboard Cite

A Damage Localization Approach for Rahmen Bridge Based on Convolutional Neural Network

Cited by 30 publications

References 22 publications

Prediction of Heavy Rain Damage Using Deep Learning

Prediction of Heavy Rain Damage Using Deep Learning

Field experiment on a PSC-I bridge for convolutional autoencoder-based damage detection

A Review of the Application of CNN-Based Computer Vision in Civil Infrastructure Maintenance

Contact Info

Product

Resources

About