Abstract
Preliminary assessment of the seismic performance of reinforced concrete (RC) buildings with placards can reduce the number of buildings that require a detailed and costly assessment. Although existing image-processing-based techniques can detect the existence of cracks and spalling in concrete, it remains difficult to define with damage levels of the damaged vertical members based on these techniques. This study aims to fill this gap by exploiting convolutional neural network (CNN) techniques for damage level classification of vertical components in RC buildings. The preliminary seismic assessment approach of existing RC buildings developed by the National Center for Research on Earthquake Engineering, Taiwan is employed in this study, and the residual strength factors for damage levels of vertical members are identified. The proposed CNN technique can estimate the damage levels of the vertical members, and the seismic capacity reduction of these damaged vertical members can be graded accordingly. Hence, the seismic resistance of the RC buildings with damaged members caused by an earthquake can be estimated. The earthquake reconnaissance data collected after recent earthquakes are used to train and validate the CNN network. The performance of the proposed approach is verified using the earthquake data with the necessary information for the preliminary seismic assessment approach. In general, the precision and recall values that we obtain for the identification of the damage in vertical members are acceptable. Based on the results of this study, performing a seismic evaluation of RC buildings by calculating the residual seismic capacity ratio with the help of machine learning appears to be an effective strategy.
Similar content being viewed by others
Data availability
Data from the Hualian and Meinong earthquakes can be downloaded from the NCREE database (https://www.ncree.org/recce/20160206/https://www.ncree.org/recce/20180206/), whereas the data from the other earthquakes can be downloaded from Datacenterhub.org (https://datacenterhub.org/post-nees.html).
References
Abdelqader I, Abudayyeh O, Kelly M (2003) Analysis of edge-detection techniques for crack identification IN bridges. J Comput Civ Eng 17:255–263
Zhu Z, German S, Brilakis I (2011) Visual retrieval of concrete crack properties for automated post-earthquake structural safety evaluation. Autom Constr 20(7):874–883
Chen FC, Jahanshahi MRNB-CNN (2018) Deep learning-based crack detection using convolutional neural network and Naïve Bayes data fusion. IEEE Trans Ind Electron 65(5):4392–4400
Kim H, Ahn E, Shin M, Sim SH (2018) Crack and noncrack classification from concrete surface images using machine learning. Struct Health Monit 18:725–738
Yeum CM, Dyke SJ, Ramirez J (2018) Visual data classification in post-event building reconnaissance. Eng Struct 155:16–24
Hoskere V, Narazaki Y, Hoang T, Spencer Jr B (2018) Vision-based structural inspection using multiscale deep convolutional neural networks. arXiv preprint arXiv:1805.01055
Gao Y, Mosalam KM (2018) Deep transfer learning for image-based structural damage recognition. Comput Aided Civ Infrastr Eng 33:748–768
Ghosh Mondal T, Jahanshahi M, Wu RT, Wu Z (2020) Deep learning-based multi-class damage detection for autonomous post-disaster reconnaissance. Struct Control Health Monit 27:e2507. https://doi.org/10.1002/stc.2507
Ye XW, Ma S, Liu ZX, Ding YL, Zhe X, Jin T (2022) Post-earthquake damage recognition and condition assessment of bridges using UAV integrated with deep learning approach. Struct Control Health Monit. https://doi.org/10.1002/stc.3128
JBDPA (Japan Building Disaster Prevention Association), Standard for Seismic Evaluation of Existing Reinforced Concrete Buildings, Guidelines for Seismic Retrofit of Existing Reinforced Concrete Buildings, and Technical Manual for Seismic Evaluation and Seismic Retrofit of Existing Reinforced Concrete buildings (2015), Tokyo, Japan
Maeda M, Kang DE (2014) Post earthquake damage evaluation of reinforced concrete buildings. J Adv Concr Technol 7(3):327–335. https://doi.org/10.3151/jact.7.327
Chiou TC, Hwang SJ, Chung LL, Tu YS, Shen WC, Weng PW. (2017) preliminary seismic assessment of low-rise reinforced concrete buildings in Taiwan. In: 16th World Conference on Earthquake Engineering, 16WCEE 2017, Santiago, Chile/Paper No. 2977
Puranam A, Irfanoglu A, Pujol S, Chiou TC, Hwang SJ (2018) Evaluation of Seismic Vulnerability Indices using data from the Taiwan Earthquake of 6 February 2016. Bull Earthq Engineering. https://doi.org/10.1007/s10518-018-0519-1
Chiu CK, Sung HF, Chiou TC (2021) Quantification of the reduction factors of seismic capacity for damaged RC column members using the experiment database. Earthq Eng Struct Dyn 50(3):756–776
Chiu CK, Sung HF, Chiou TC (2022) Experimental quantification of seismic damage for RC infill walls using static and dynamic loading test. J Build Eng 50:104177
NCREE and Purdue University. Building Data of the 20160206 Meinong Earthquake in Taiwan (2018). https://www.ncree.org/recce/20160206/. Accessed 30 June 2021
Chiou TC, Tu YH, Tu YS, Chung LL, Huang CT (2018) Verification on seismic assessment model of masonry infill with openings. In: The 10th Australasian Masonry Conference, Sydney, Australia/Paper No. 26.
Yeh RL, Tseng CC, Hwang SJ (2018) Shear Strength of Reinforced Concrete Vertical Wall Segments under Seismic Loading. ACI Struct J 115(5):1485–1494
Chiou TC, Hwang SJ (2015) Tests on cyclic behavior of reinforced concrete frames with brick infill. Earthq Eng Struct Dyn 44(12):1939–1958
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. (2015) Going deeper with convolutions. In: Proceedings of the ieee Conference on computer vision and pattern recognition, pp 1–9
Sim C, Laughery L, Chiou TC, Weng P-w (2017) Pohang Earthquake (2018) https://datacenterhub.org/deedsdv/publications/view/296. Accessed 30 June 2021
Purdue University. Buildings Surveyed after the 2017 Mexico City Earthquakes (2018). https://datacenterhub.org/deedsdv/publications/view/536. Accessed 30 June 2021
Sim C, Villalobos E, Smith JP, Rojas P, Puranam AY, Laughery L (2016) Ecuador Earthquake. Santiago Pujol https://datacenterhub.org/deedsdv/publications/view/535. Accessed 30 June 2021
Shah P, Pujol S, Puranam A, Laughery L (2015) Nepal Earthquake Building Performance Database (2016) https://datacenterhub.org/deedsdv/publications/view/537. Accessed 30 June 2021
Chiou TC, Ho YS, Weng PW, Shen WC (2018) Building Data of the 20180206 Hualien Earthquake in Taiwan. https://www.ncree.org/recce/20180206/. Accessed 30 June 2021
Acknowledgements
This research was funded by the Ministry of Science and Technology, Taiwan under grant No. MOST 108-2221-E-492-004.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Hsu, TY., Wu, CF. & Chiou, TC. Post-earthquake preliminary estimation of residual seismic capacity of RC buildings based on deep learning. J Civil Struct Health Monit (2024). https://doi.org/10.1007/s13349-024-00805-w
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s13349-024-00805-w