Journal of the Earthquake Engineering Society of Korea (한국지진공학회논문집)

Earthquake Engineering Society of Korea (한국지진공학회)
권호 표지
DOI QR코드

DOI QR Code

Proposal of a Practical Multi-Class Deep SVDD-Based Methodology for Real-Time Defect Detection During Earthquakes

지진 발생 시 실시간 결함 탐지를 위한 실용적인 다중 클래스 Deep SVDD 기반 방법론 제안

  • Lee, Yeong In (Interdisciplinary Program in Artificial Intelligence, Seoul National University) ;
  • Kang, Thomas H.-K. (Department of Architecture and Architectural Engineering and Interdisciplinary Program in Artificial Intelligence, Seoul National University)
  • 이영인 (서울대학교 협동과정 인공지능전공) ;
  • 강현구 (서울대학교 건축학과 및 협동과정 인공지능전공)
  • Received : 2026.02.13
  • Accepted : 2026.03.10
  • Published : 2026.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

Rapid, real-time detection of anomalies and locate structural defects during earthquakes is critical for ensuring safety and enabling timely decision-making. Although deep learning-based structural health monitoring (SHM) has shown considerable promise, conventional supervised models are often impractical because labeled damage data from real-world structures are extremely scarce. To address this challenge, this paper proposes a Multi-Class Deep Support Vector Data Description (SVDD) framework for structural defect detection. The proposed Multi-Class Deep SVDD approach learns the boundary of normal data using only normal seismic acceleration responses. When new data are recorded, the system infers both the occurrence and location of defects by evaluating whether the responses fall within or deviate from the learned normal boundary. The framework is validated using the Los Alamos National Laboratory 3-story bookshelf structure benchmark dataset. Experimental results show that the proposed model achieves a peak average accuracy of 87.12% in a 4-dimensional latent space, substantially outperforming traditional baseline methods, including Kernel Density Estimation (KDE), SVDD, and One-Class Deep SVDD. These findings indicate that the Multi-Class Deep SVDD framework provides a robust and objective metric for rapid post-earthquake safety assessment without requiring prior exposure to faulty datasets.

Keywords

Acknowledgement

이 논문은 2026년도 정부(과학기술정보통신부)의 재원으로 정보통신기획평가원의 지원을 받아 수행된 연구임 [NO.RS-2021-II211343, 인공지능대학원지원(서울대학교)].

References

  1. Eem SH, Yang B, Jeon H. Earthquake damage assessment of buildings using opendata in the Pohang and the Gyeongju earthquakes. EESK. 2018;22(3):121-128. https://doi.org/10.5000/EESK.
  2. Hsu TY, Yin RC, Wu YM. Evaluating post-earthquake building safety using economical MEMS seismometers. Sensors. 2018;18(5):1437. https://doi.org/10.3390/s18051437
  3. Giordano PF, Iacovino C, Quqa S, Limongelli MP. The value of seismic structural health monitoring for post-earthquake building evacuation. Bulletin of Earthquake Engineering. 2022;20(9):4367-4393. https://doi.org/10.1007/s10518-022-01375-2
  4. Iacovino C, Ditommaso R, Ponzo FC, Limongelli MP. The interpolation evolution method for damage localization in structures under seismic excitation. Earthquake Engineering & Structural Dynamics. 2018;47(10):2117-2136. https://doi.org/10.1002/eqe.v47.10
  5. Limongelli MP. Seismic health monitoring of an instrumented multistory building using the interpolation method. Earthquake Engineering & Structural Dynamics. 2014;43(11):1581-1602. https://doi.org/10.1002/eqe.v43.11
  6. Cha YJ, Ali R, Lewis J, Büyükoztürk O. Deep learning-based structural health monitoring. Automation in Construction. 2024;161:105328. https://doi.org/10.1016/j.autcon.2024.105328
  7. Avci O, Abdeljaber O, Kiranyaz S, Hussein M, Gabbouj M, Inman DJ. 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, 2021;147:107077. https://doi.org/10.1016/j.ymssp.2020.107077
  8. Teng S, Chen G, Yan Z, Cheng L, Bassir D. Vibration-based structural damage detection using 1-D convolutional neural network and transfer learning. Structural Health Monitoring. 2023;22(4):2888-2909. https://doi.org/10.1177/14759217221137931
  9. Abdeljaber O, Avci O, Kiranyaz S, Gabbouj M, Inman DJ. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. Journal of Sound and Vibration. 2017;388:154-170. https://doi.org/10.1016/j.jsv.2016.10.043
  10. Coraça EM, Ferreira JV, Nóbrega EG. An unsupervised structural health monitoring framework based on variational autoencoders and hidden Markov models. Reliability Engineering & System Safety. 2023;231:109025. https://doi.org/10.1016/j.ress.2022.109025
  11. Keshmiry A, Hassani S, Mousavi M, Dackermann U. Effects of environmental and operational conditions on structural health monitoring and non-destructive testing: a systematic review. Buildings. 2023;13(4):918. https://doi.org/10.3390/buildings13040918
  12. Kim EJ, Cho S, Sim SH. A recent research summary on smart sensors for structural health monitoring. Journal of the Korea Institute for Structural Maintenance and Inspection. 2015;19(3):10-21. https://doi.org/10.11112/JKSMI.2015.19.3.010
  13. Zhu YK, Wan HP, Ye YJ, Todd MD. A conditional probabilistic deep learning approach for anomaly detection in structures under varying environmental conditions. Mechanical Systems and Signal Processing. 2025;236:113005. https://doi.org/10.1016/j.ymssp.2025.113005
  14. Dy J, Krause A, editors. Proceedings of the 35th International Conference on Machine Learning; 2018 Jul 10-15; Stockholm. PMLR; c2018. p. 4393-4402.
  15. Pérez-Carrasco M, Cabrera-Vives G, Hernández-García L, Forster F, Sánchez-Sáez P, Muñoz Arancibia A, Astorga N, Bauer F, Bayo A, Cádiz-Leyton M, Catelan M. Multi-Class Deep SVDD: Anomaly Detection Approach in Astronomy with Distinct Inlier Categories. arXiv [Internet]. 2023 Aug 10 [cited 2026 Mar 9];arXiv:2308.05011. Available from: DOI:10.48550/arXiv.2308.05011.
  16. Los Alamos National Laboratory Engineering Institute. SHM datasets and software. Los Alamos (NM): Los Alamos National Laboratory; c2000.
  17. Rosenblatt M. Remarks on some nonparametric estimates of a density function. The Annals of Mathematical Statistics. 1956;27(3):832-837. https://doi.org/10.1214/aoms/1177728190
  18. Parzen E. On estimation of a probability density function and mode. The Annals of Mathematical Statistics. 1962;33(3):1065-1076. https://doi.org/10.1214/aoms/1177704472
  19. Tax DM, Duin RP. Support vector data description. Machine Learning. 2004;54(1):45-66. https://doi.org/10.1023/B:MACH.0000008084.60811.49