Journal of Concrete Structures and Materials

Journal of Concrete Structures and Materials

Performance and Reliability Assessment of Machine and Ensemble Learning Methods for Damage Detection of Reinforced Concrete Buildings

Document Type : Original Article

Authors
Pouya Mousavian 1
Razi Sheikholeslami 2
Shariar Tavousi Tafreshi 1
1 Islamic Azad University Central Tehran Branch
2 Sharif University of Technology
10.30478/jcsm.2024.446297.1364
Abstract
Traditional methods for detecting damage, reliant on experts and human resources both before and after earthquakes, represent a time-consuming, costly, and inherently uncertain process. However, this process is pivotal for bolstering societal resilience. The field of structural health monitoring has witnessed significant advancement in recent years, attributed to the proliferation and refinement of Machine Learning (ML) methodologies. In this study, we leverage machine learning techniques, specifically focusing on Ensemble Learning (EL) methods, to improve the efficacy of building damage detection. Our investigation involves employing Support Vector Machine (SVM) and the Bagging methods to assess the extent of damage using datasets from earthquake-affected reinforced concrete buildings in South Korea, Nepal, Ecuador, and Haiti. The outcomes highlight the notable potential of the bagging algorithm, achieving an accuracy rate of 73% in one of the models. Beyond evaluating the performance of ML algorithms, we introduce an innovative Probabilistic Uncertainty Measure (PUM) to quantify the reliability of each method across various damage grades. The results from this analysis underscore the substantial reliability of EL methods, reaching a minimum of 84% in this critical domain. This research signifies a promising step towards more efficient, accurate, and reliable damage detection processes, with the potential to significantly impact disaster resilience initiatives.
Keywords
Damage Detection
Machine Learning
Probabilistic Uncertainty Measure
RC Buildings
Reliability

Subjects

[1]           S. Mangalathu, H. Sun, C.C. Nweke, Z. Yi, H.V. Burton, Classifying earthquake damage to buildings using machine learning, Earthquake Spectra. 36 (2020) 183–208. https://doi.org/10.1177/8755293019878137.
[2]           O. Avci, O. Abdeljaber, S. Kiranyaz, M. Hussein, M. Gabbouj, D.J. Inman, A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications, Mechanical Systems and Signal Processing. 147 (2021) 107077. https://doi.org/10.1016/j.ymssp.2020.107077.
[3]           Y. Zhang, H.V. Burton, H. Sun, M. Shokrabadi, A machine learning framework for assessing post-earthquake structural safety, Structural Safety. 72 (2018) 1–16. https://doi.org/10.1016/j.strusafe.2017.12.001.
[4]           A. Abasi, V. Harsij, A. Soraghi, Damage detection of 3D structures using nearest neighbor search method, Earthq. Eng. Eng. Vib. 20 (2021) 705–725. https://doi.org/10.1007/s11803-021-2048-1.
[5]           M.H. Chegeni, M.K. Sharbatdar, R. Mahjoub, M. Raftari, New supervised learning classifiers for structural damage diagnosis using time series features from a new feature extraction technique, Earthq. Eng. Eng. Vib. 21 (2022) 169–191. https://doi.org/10.1007/s11803-022-2079-2.
[6]       Alcantara EAM, Saito T. Machine Learning-Based Rapid Post-Earthquake Damage Detection of RC Resisting-Moment Frame Buildings. Sensors. 2023; 23(10):4694. https://doi.org/10.3390/s23104694
[7]           S. Ghaffarian, N. Kerle, E. Pasolli, J. Jokar Arsanjani, Post-Disaster Building Database Updating Using Automated Deep Learning: An Integration of Pre-Disaster OpenStreetMap and Multi-Temporal Satellite Data, Remote Sensing. 11 (2019) 2427. https://doi.org/10.3390/rs11202427.
[8]           G. Gui, H. Pan, Z. Lin, Y. Li, Z. Yuan, Data-driven support vector machine with optimization techniques for structural health monitoring and damage detection, KSCE J Civ Eng. 21 (2017) 523–534. https://doi.org/10.1007/s12205-017-1518-5.
[9]        Naderpour H, Abbasi M, Kontoni D-PN, Mirrashid M, Ezami N, Savvides A-A. Integrating Image Processing and Machine Learning for the Non-Destructive Assessment of RC Beams Damage. Buildings. 2024; 14(1):214. https://doi.org/10.3390/buildings14010214
[10]      Vahid Ahmadian, S. Bahram Beheshti Aval, Mohammad Noori, Tianyu Wang, Wael A. Altabey, Comparative study of a newly proposed machine learning classification to detect damage occurrence in structures, Engineering Applications of Artificial Intelligence, 127 (2024), 107226, https://doi.org/10.1016/j.engappai.2023.107226.
[11]         F. Nex, D. Duarte, F.G. Tonolo, N. Kerle, Structural Building Damage Detection with Deep Learning: Assessment of a State-of-the-Art CNN in Operational Conditions, Remote Sensing. 11 (2019) 2765. https://doi.org/10.3390/rs11232765.
[12]         Y. Bai, B. Zha, H. Sezen, A. Yilmaz, Engineering deep learning methods on automatic detection of damage in infrastructure due to extreme events, Structural Health Monitoring. 22 (2023) 338–352. https://doi.org/10.1177/14759217221083649.
[13]         P. Chun, S. Izumi, T. Yamane, Automatic detection method of cracks from concrete surface imagery using two‐step light gradient boosting machine, Computer‐Aided Civil and Infrastructure Engineering. 36 (2021) 61–72. https://doi.org/10.1111/mice.12564.
[14]         S. Naito, H. Tomozawa, Y. Mori, T. Nagata, N. Monma, H. Nakamura, H. Fujiwara, G. Shoji, Building-damage detection method based on machine learning utilizing aerial photographs of the Kumamoto earthquake, Earthquake Spectra. 36 (2020) 1166–1187. https://doi.org/10.1177/8755293019901309.
[15]         B.A. Mir, T. Sasaki, K. Nakao, K. Nagae, K. Nakada, M. Mitani, T. Tsukada, N. Osada, K. Terabayashi, M. Jindai, Machine learning-based evaluation of the damage caused by cracks on concrete structures, Precision Engineering. 76 (2022) 314–327. https://doi.org/10.1016/j.precisioneng.2022.03.016.
[16]         E. Harirchian, V. Kumari, K. Jadhav, R. Raj Das, S. Rasulzade, T. Lahmer, A Machine Learning Framework for Assessing Seismic Hazard Safety of Reinforced Concrete Buildings, Applied Sciences. 10 (2020) 7153. https://doi.org/10.3390/app10207153.
[17]         C. Zhu, Y. Xu, Y. Wu, M. He, C. Zhu, Q. Meng, Y. Lin, A hybrid artificial bee colony algorithm and support vector machine for predicting blast-induced ground vibration, Earthq. Eng. Eng. Vib. 21 (2022) 861–876. https://doi.org/10.1007/s11803-022-2125-0.
[18]         H. Fattahi, M.A. Ebrahimi Farsangi, S. Shojaee, K. Nekooei, H. Mansouri, Application Of The Hybrid Harmony Search With Support Vector Machine For Identification And Calssification Of Damaged Zone Around Underground Spaces, IUST. 3 (2013) 345–358.
[19]         A.C. Catlin, C. HewaNadungodage, S. Pujol, L. Laughery, C. Sim, A. Puranam, A. Bejarano, A Cyberplatform for Sharing Scientific Research Data at DataCenterHub, Comput. Sci. Eng. 20 (2018) 49–70. https://doi.org/10.1109/MCSE.2017.3301213.
[20]         P. Shah, S. Pujol, A. Puranam, L. Laughery, 2015 Nepal Earthquake Building Performance Database, (2016). https://doi.org/10.7277/Z82F-0728.
[21]         S. Tallett-Williams, B. Gosh, S. Wilkinson, C. Fenton, P. Burton, M. Whitworth, S. Datla, G. Franco, A. Trieu, M. Dejong, V. Novellis, T. White, T. Lloyd, Site Amplification In The Kathmandu Valley During The 2015 M7.6 Gorkha, Nepal Earthquake, Bull Earthquake Eng. 14 (2016) 3301–3315. https://doi.org/10.1007/s10518-016-0003-8.
[22]         C. Sim, E. Villalobos, J. Smith, P. Rojas, S. Pujol, A. Puranam, L. Laughery, Performance of Low-rise Reinforced Concrete Buildings in the 2016 Ecuador Earthquake, (2017). https://doi.org/10.4231/R7ZC8111.
[23]         X. Vera-Grunauer, GEER-ATC Mw7.8 Ecuador 4/16/16 Earthquake Reconnaissance Part Ii: Selected Geotechnical Observations, in: 2017.
[24]         P. O’Brien, M. Eberhard, O. Haraldsson, A. Irfanoglu, D. Lattanzi, S. Lauer, S. Pujol, Measures of the Seismic Vulnerability of Reinforced Concrete Buildings in Haiti, Earthquake Spectra. 27 (2011) 373–386. https://doi.org/10.1193/1.3637034.
[25]         N. Sedra, M. Eberhard, A. Irfanoglu, A.B. Matamoros, S. Pujol, Olafur Sveinn Haraldsson, D.A. Lattanzi, S.L. Lauer, B. Lyon, J. Messmer, K. Nasi, J. Rautenberg, S. Symithe, R. Douilly, The Haiti Earthquake Database, (2010). https://doi.org/10.4231/D3P843W0H.
[26]         R.O. de León, Flexible Soils Amplified The Damage In The 2010 Haiti Earthquake, in: A Coruña, Spain, 2013: pp. 433–444. https://doi.org/10.2495/ERES130351.
[27]         B. Warf, Encyclopedia of Geography, SAGE Publications, Inc., 2455 Teller Road, Thousand Oaks California 91320 United States, 2010. https://doi.org/10.4135/9781412939591.
[28]         C. Sim, L. Laughery, T. Chiou, P.-W. Weng, 2017 Pohang Earthquake, (2018). https://doi.org/10.7277/04XV-FA16.
[29]         H.-S. Kim, C.-G. Sun, H.-I. Cho, Geospatial Assessment of the Post-Earthquake Hazard of the 2017 Pohang Earthquake Considering Seismic Site Effects, IJGI. 7 (2018) 375. https://doi.org/10.3390/ijgi7090375.
[30]         E. Harirchian, T. Lahmer, V. Kumari, K. Jadhav, Application of Support Vector Machine Modeling for the Rapid Seismic Hazard Safety Evaluation of Existing Buildings, Energies. 13 (2020) 3340. https://doi.org/10.3390/en13133340.
[31]         H. Stone, Exposure and vulnerability for seismic risk evaluations, Ph.D. Thesis, UCL (University College London), 2018. https://discovery.ucl.ac.uk/id/eprint/10051591.
[32]         B. Lizundia, S. Durphy, M. Griffin, W. Holmes, A. Hortacsu, B. Kehoe, K. Porter, B. Welliver, Third Edition Update of FEMA P-154: Rapid Visual Screening for Potential Seismic Hazards, in: Improving the Seismic Performance of Existing Buildings and Other Structures 2015, American Society of Civil Engineers, San Francisco, California, 2015: pp. 775–786. https://doi.org/10.1061/9780784479728.064.
[33]         A. Yakut, V. Aydogan, G. Ozcebe, M.S. Yucemen, Preliminary Seismic Vulnerability Assessment of Existing Reinforced Concrete Buildings in Turkey, in: S.T. Wasti, G. Ozcebe (Eds.), Seismic Assessment and Rehabilitation of Existing Buildings, Springer Netherlands, Dordrecht, 2003: pp. 43–58. https://doi.org/10.1007/978-94-010-0021-5_4.
[34]         Ahmed F. Hassan and Mete A. Sozen, Seismic Vulnerability Assessment of Low-Rise Buildings in Regions with Infrequent Earthquakes, ACI Structural Journal. 94 (1997). https://doi.org/10.14359/458.
[35]         E. Harirchian, T. Lahmer, Earthquake Hazard Safety Assessment of Buildings via Smartphone App: A Comparative Study, IOP Conf. Ser.: Mater. Sci. Eng. 652 (2019) 012069. https://doi.org/10.1088/1757-899X/652/1/012069.
[36]         M.S. Yücemen, G. Özcebe, A.C. Pay, Prediction of potential damage due to severe earthquakes, Structural Safety. 26 (2004) 349–366. https://doi.org/10.1016/j.strusafe.2003.09.002.
[37]         C. Albon, Machine learning with Python cookbook: practical solutions from preprocessing to deep learning, First edition, O’Reilly Media, Sebastopol, CA, 2018.
[38]         A. Géron, Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: concepts, tools, and techniques to build intelligent systems, Second edition, O’Reilly Media, Inc, Beijing [China] ; Sebastopol, CA, 2019.
[3۹]         Tyralis, H., Papacharalampous, G. A review of predictive uncertainty estimation with machine learning. Artif Intell Rev 57, 94 (2024). https://doi.org/10.1007/s10462-023-10698-8.
[40]         Gawlikowski, J., Tassi, C.R.N., Ali, M. et al. A survey of uncertainty in deep neural networks. Artif Intell Rev 56 (Suppl 1), 1513–1589 (2023). https://doi.org/10.1007/s10462-023-10562-9
[4۱]         Seoni, Silvia & Vicnesh, Jahmunah & Salvi, Massimo & Barua, Prabal Datta & Molinari, Filippo & Acharya, U Rajendra. (2023). Application of uncertainty quantification to artificial intelligence in healthcare: A review of last decade (2013–2023). Computers in Biology and Medicine. 165. 107441. 10.1016/j.compbiomed.2023.107441.
Journal of Concrete Structures and Materials
Volume 8, Issue 2 - Serial Number 16
November 2023
Pages 203-224

  • Receive Date 29 February 2024
  • Revise Date 23 April 2024
  • Accept Date 25 May 2024