Abstract
Although many data-driven-based damage detection methods in supervised learning mode have been proposed in recent decades, these methods require training data from not only undamaged structural scenarios but also various damaged scenarios (DSs) of the monitored structures. However, acquiring sufficient training data from various DSs for the infrastructures in service is impractical, and labeling huge amounts of training data with specific structural scenarios is time-consuming and costly. In this study, the unsupervised damage detection method with a deep auto-encoder (DAE) and a one-class support vector machine (OC-SVM) is investigated extensively (Wang Z, Cha YJ, Structural Health Monitoring, 2020). The unsupervised deep learning-based method only uses the acceleration responses recorded from undamaged scenarios as training data, and the recorded acceleration responses from various unknown structural scenarios are taken as testing data. Overall, the proposed method provides high performance in damage detection with reduced tuning parameters. The numerical and experimental studies show the high damage detection performance of the proposed method: a 93.2% average detection accuracy for a numerical multi-storey building frame with light damage in the form of stiffness reduction.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wang, Z., Cha, Y.J.: Unsupervised deep learning approach using a deep auto-encoder with an one-class support vector machine to detect structural damage. Struct. Health Monit. (2020). https://doi.org/10.1177/1475921720934051
Farrar, C.R., Worden, K.: Structural Health Monitoring: A Machine Learning Perspective. Wiley, Hoboken (2012)
Cha, Y.J., Choi, W., Büyüköztürk, O.: Deep learning-based crack damage detection using convolutional neural networks. Comput. Aided Civ. Inf. Eng. 32(5), 361–378 (2017)
Cha, Y.J., Choi, W., Suh, G., Mahmoudkhani, S., Büyüköztürk, O.: Autonomous structural visual inspection using region-based deep learning for detecting multiple damage types. Comput. Aided Civ. Inf. Eng. 33(9), 731–747 (2018)
Kang, D., Cha, Y.J.: Autonomous UAVs for structural health monitoring using deep learning and an ultrasonic Beacon system with geo-tagging. Comput. Aided Civ. Inf. Eng. 33(10), 885–902 (2018)
Beckman, G.H., Polyzois, D., Cha, Y.J.: Deep learning-based automatic volumetric damage quantification using depth camera. Autom. Constr. 99, 114–124 (2019)
Ali, R., Cha, Y.J.: Subsurface damage detection of a steel bridge using deep learning and uncooled micro-bolometer. Constr. Build. Mater. 226, 376–387 (2019)
Choi, W., Cha, Y.J.: SDDNet: real-time crack segmentation. IEEE Trans. Ind. Electron. 67(9), 8016–8025 (2019)
Kang, D., Benipal, S.S., Gopal, D.L., Cha, Y.J.: Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning. Autom. Constr. 118, 103291 (2020)
Abdeljaber, O., Avci, O., Kiranyaz, S., Gabbouj, M., Inman, D.J.: Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J. Sound Vib. 388, 154–170 (2017)
Cha, Y.J., Wang, Z.: Unsupervised novelty detection–based structural damage localization using a density peaks-based fast clustering algorithm. Struct. Health Monit. 17(2), 313–324 (2018)
Wang, Z., Cha, Y.J.: Unsupervised novelty detection techniques for structural damage localization: A comparative study. In: Model Validation and Uncertainty Quantification, vol. 3, pp. 125–132. Springer, Cham (2017)
Wang, Z., Cha, Y.J.: Automated damage-sensitive feature extraction using unsupervised convolutional neural networks. In: Sensors and Smart Structures Technologies for Civil, Mechanical, and Aerospace Systems 2018, vol. 10598, p. 105981J. International Society for Optics and Photonics (2018)
Rafiei, M.H., Adeli, H.: A novel unsupervised deep learning model for global and local health condition assessment of structures. Eng. Struct. 156, 598–607 (2018)
Figueiredo, E., Park, G., Farrar, C.R., Worden, K., Figueiras, J.: Machine learning algorithms for damage detection under operational and environmental variability. Struct. Health Monit. 10(6), 559–572 (2011)
Hinton, G.E.: Connectionist learning procedures. Machine learning. 555–610 (1990)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science. 313(5786), 504–507 (2006)
Acknowledgments
The research presented in this paper was supported by the Natural Sciences and Engineering Research Council of Canada Discovery Grant (Common Personal Identifier: 1262624).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Society for Experimental Mechanics, Inc.
About this paper
Cite this paper
Wang, Z., Cha, YJ. (2022). An Unsupervised Deep Auto-encoder with One-Class Support Vector Machine for Damage Detection. In: Madarshahian, R., Hemez, F. (eds) Data Science in Engineering, Volume 9. Conference Proceedings of the Society for Experimental Mechanics Series. Springer, Cham. https://doi.org/10.1007/978-3-030-76004-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-76004-5_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-76003-8
Online ISBN: 978-3-030-76004-5
eBook Packages: EngineeringEngineering (R0)