딥러닝 기반 교량 손상추정을 위한 Generative Adversarial Network를 이용한 가속도 데이터 생성 모델 = Generative Model of Acceleration Data for Deep Learning-based Damage Detection for Bridges Using Generative Adversarial Network

다국어 초록 (Multilingual Abstract)

Maintenance of aging structures has attracted societal attention. Maintenance of the aging structure can be efficiently performed with a digital twin. In order to maintain the structure based on the digital twin, it is required to accurately detect the damage of the structure. Meanwhile, deep learning-based damage detection approaches have shown good performance for detecting damage of structures. However, in order to develop such deep learning-based damage detection approaches, it is necessary to use a large number of data before and after damage, but there is a problem that the amount of data before and after the damage is unbalanced in reality.
In order to solve this problem, this study proposed a method based on Generative adversarial network, one of Generative Model, for generating acceleration data usually used for damage detection approaches. As results, it is confirmed that the acceleration data generated by the GAN has a very similar pattern to the acceleration generated by the simulation with structural analysis software. These results show that not only the pattern of the macroscopic data but also the frequency domain of the acceleration data can be reproduced. Therefore, these findings show that the GAN model can analyze complex acceleration data on its own, and it is thought that this data can help training of the deep learning-based damage detection approaches.

참고문헌 (Reference)

1 MOLIT (Ministry of Land, Infrastructure and Transport), "Yearbook of Road Bridge and Tunnel Statistics" 2018

2 Hou, Z., "Wavelet-based approach for structural damage detection" 126 (126): 677-683, 2000

3 Noh, H. Y., "Use of wavelet-based damage-sensitive features for structural damage diagnosis using strong motion data" 137 (137): 1215-1228, 2011

4 Radford, A., "Unsupervised representation learning with deep convolutional generative adversarial networks"

5 Nair, K. K., "Time series based structural damage detection algorithm using Gaussian mixtures modeling" 129 (129): 285-293, 2007

6 Padil, K. H., "The use of a non-probabilistic artificial neural network to consider uncertainties in vibration-based-damage detection" 83 : 194-209, 2017

7 Kullaa, J, "Structural health monitoring under nonlinear environmental or operational influences" 2014 : 1-9, 2014

8 Lin, Y. Z., "Structural damage detection with automatic feature extraction through deep learning" 32 (32): 1025-1046, 2017

9 Park, J. H., "Sequential damage detection approaches for beams using time-modal features and artificial neural networks" 323 (323): 451-474, 2009

10 Pascual, S., "SEGAN: Speech enhancement generative adversarial network"

11 Abdeljaber, O., "Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks" 388 : 154-170, 2017

12 Banerjee, S., "Prediction of progressive damage state at the hot spots using statistical estimation" 21 (21): 595-605, 2010

13 Soman, R., "Numerical evaluation of multi-metric data fusion based structural health monitoring of long span bridge structures" 14 (14): 673-684, 2018

14 Deng, L., "New types of deep neural network learning for speech recognition and related applications : An overview" 8599-8603, 2013

15 Park, K. Y., "Narrowband to wideband conversion of speech using GMM based transformation" 3 : 1843-1846, 2000

16 Oh, B. K., "Modal Response Based Visual System Identification and Model Updating Methods for Building Structures" 32 (32): 34-56, 2017

17 Yang, L. C., "MidiNet: A convolutional generative adversarial network for symbolicdomain music generation"

18 Lee, K., "Methodology for the damage detection of aging bridges based on multi-data and deep learning" 1725-1731, 2018

19 Mao, X., "Least squares generative adversarial networks" 2794-2802, 2017

20 Goodfellow, I., "Generative adversarial nets" 2672-2680, 2014

21 Hakim, S. J. S., "Fault diagnosis on beam-like structures from modal parameters using artificial neural networks" 76 : 45-61, 2015

22 Glowacz, A., "Early fault diagnosis of bearing and stator faults of the single-phase induction motor using acoustic signals" 113 : 1-9, 2018

23 Wakita, T., "Driver identification using driving behavior signals" 89 (89): 1188-1194, 2006

24 Mehrjoo, M., "Damage detection of truss bridge joints using Artificial Neural Networks" 35 (35): 1122-1131, 2008

25 Pnevmatikos, N. G., "Damage detection of framed structures subjected to earthquake excitation using discrete wavelet analysis" 15 (15): 227-248, 2017

26 Bruno, B., "Analysis of human behavior recognition algorithms based on acceleration data" 1602-1607, 2013

27 Mayorga, P., "Acoustics based assessment of respiratory diseases using GMM classification" 6312-6316, 2010

28 Lee, Y., "A Study of Improvement and Longevity of the Aging Urban Infrastructure in Korea" 63 (63): 10-19, 2015