Abstract
With the explosive growth of available data collected from various sensors and increasingly powerful computing resources, recent advanced in machine learning (ML) and other data-driven techniques have yielded transformative results in structural health monitoring (SHM). A common challenge in applying ML algorithms to SHM problems in a supervised learning manner is that the ML models need a comprehensive and systematic training process, typically requiring large datasets representing structures under different damage conditions, a requirement that is usually not met when dealing with real-life civil structures. In this study, we propose a novel data augmentation strategy within a vibration-based SHM framework, based on a conditional variational autoencoder (CVAE) to generate additional data samples of the power cepstral coefficients of the structural acceleration response in various damage conditions. The developed CVAE architecture can be trained to model various statistical distributions of the power cepstral coefficients simultaneously by incorporating newly defined conditional variables, where the decoder of the trained CVAE is subsequently separated and used to generate new samples for the data augmentation. A new type of the power cepstral coefficients is used to boost the performance and robustness of the data augmentation and consequently of the subsequent damage classification task. The augmented training datasets can be used to better train a probabilistic linear discriminant analysis (PLDA) model that can be employed for structural damage identification and classification in both supervised and unsupervised learning strategies. The proposed method has been validated by numerical simulations and experimental data.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13349-023-00705-5/MediaObjects/13349_2023_705_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13349-023-00705-5/MediaObjects/13349_2023_705_Fig2_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13349-023-00705-5/MediaObjects/13349_2023_705_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13349-023-00705-5/MediaObjects/13349_2023_705_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13349-023-00705-5/MediaObjects/13349_2023_705_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13349-023-00705-5/MediaObjects/13349_2023_705_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs13349-023-00705-5/MediaObjects/13349_2023_705_Fig7_HTML.png)
Similar content being viewed by others
Data Availability
The data that support the findings of this study are not openly available due to reasons of sensitivity. The data are, however, available from the authors upon reasonable request and with permission from the Department of Civil Engineering and Engineering Mechanics of Columbia University and the Structural Mechanics Section of KU Leuven.
References
Azimi M, Eslamlou AD, Pekcan G (2020) Data-driven structural health monitoring and damage detection through deep learning: state-of-the-art review. Sensors 20(10):2778
Fritzen CP (2005) Vibration-based structural health monitoring–concepts and applications. Key Eng Mater 293:3–20
Avci O, Abdeljaber O, Kiranyaz S, Hussein M, Gabbouj M, Inman DJ (2021) A review of vibration-based damage detection in civil structures: from traditional methods to machine learning and deep learning applications. Mech Syst Signal Process 147:107077. https://doi.org/10.1016/j.ymssp.2020.107077
Farrar CR, Worden K (2012) Structural health monitoring: a machine learning perspective. Wiley
O'Shea K, Nash R (2015) An introduction to convolutional neural networks. ar**v preprint ar**v:1511.08458. https://doi.org/10.48550/ar**v.1511.08458
Ni F, Zhang J, Noori MN (2020) Deep learning for data anomaly detection and data compression of a long-span suspension bridge. Comput-Aided Civ Infrastruct Eng 35(7):685–700. https://doi.org/10.1111/mice.12528
Azimi M, Pekcan G (2020) Structural health monitoring using extremely compressed data through deep learning. Comput-Aided Civ Infrastruct Eng 35(6):597–614. https://doi.org/10.1111/mice.12517
Abdeljaber O, Avci O, Kiranyaz S, Gabbouj M, Inman DJ (2017) Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J Sound Vib 388:154–170. https://doi.org/10.1016/j.jsv.2016.10.043
Cha YJ, Choi W, Büyüköztürk O (2017) Deep learning-based crack damage detection using convolutional neural networks. Comput-Aided Civ Infrastruct Eng 32(5):361–378. https://doi.org/10.1111/mice.12263
Wang Z, Cha YJ (2021) Unsupervised deep learning approach using a deep auto-encoder with a one-class support vector machine to detect damage. Struct Health Monit 20(1):406–425. https://doi.org/10.1177/1475921720934051
Pathirage CS, Li J, Li L, Hao H, Liu W, Ni P (2018) Structural damage identification based on autoencoder neural networks and deep learning. Eng Struct 172:13–28. https://doi.org/10.1016/j.engstruct.2018.05.109
Li L, Morgantini M, Betti R (2023) Structural damage assessment through a new generalized autoencoder with features in the quefrency domain. Mech Syst Signal Process 184:109713. https://doi.org/10.1016/j.ymssp.2022.109713
Morgantini M, Betti R, Balsamo L (2021) Structural damage assessment through features in quefrency domain. Mech Syst Signal Process 147:107017. https://doi.org/10.1016/j.ymssp.2020.107017
Dike HU, Zhou Y, Deveerasetty KK, Wu Q (2018) Unsupervised learning based on artificial neural network: a review. In 2018 IEEE International Conference on Cyborg and Bionic Systems (CBS), 322–327. https://doi.org/10.1109/CBS.2018.8612259
Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big data 3(1):1–40. https://doi.org/10.1186/s40537-016-0043-6
Lu J, Behbood V, Hao P, Zuo H, Xue S, Zhang G (2015) Transfer learning using computational intelligence: a survey. Knowl-Based Syst 80:14–23. https://doi.org/10.1016/j.knosys.2015.01.010
Gao Y, Mosalam KM (2018) Deep transfer learning for image-based structural damage recognition. Comput-Aided Civ Infrastruct Eng 33(9):748–768. https://doi.org/10.1111/mice.12363
Tronci EM, Beigi H, Feng MQ, Betti R (2022) Transfer learning from audio domains a valuable tool for structural health monitoring. Dynamics of civil structures, vol 2. Springer, Cham, pp 99–107. https://doi.org/10.1007/978-3-030-77143-0_11
Shorten C, Khoshgoftaar TM (2019) A survey on image data augmentation for deep learning. J Big Data 6(1):1–48. https://doi.org/10.1186/s40537-019-0197-0
Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. ar**v preprint ar**v:1712.04621. https://doi.org/10.48550/ar**v.1712.04621
Feng SY, Gangal V, Wei J, Chandar S, Vosoughi S, Mitamura T, Hovy E (2021) A survey of data augmentation approaches for NLP. ar**v preprint ar**v:2105.03075. https://doi.org/10.48550/ar**v.2105.03075
Creswell A, White T, Dumoulin V, Arulkumaran K, Sengupta B, Bharath AA (2018) Generative adversarial networks: an overview. IEEE Signal Process Mag 35(1):53–65. https://doi.org/10.1109/MSP.2017.2765202
Luleci F, Catbas FN, Avci O (2022) A literature review: generative adversarial networks for civil structural health monitoring. Front Built Environ Struct Sens Control Asset Manag 8:1027379. https://doi.org/10.3389/fbuil.2022.1027379/full
Wan P, He H, Guo L, Yang J, Li J (2021) InfoGAN-MSF: a data augmentation approach for correlative bridge monitoring factors. Meas Sci Technol 32(11):114008. https://doi.org/10.1088/1361-6501/ac0744/meta
Luleci F, Catbas FN, Avci O (2023) Generative adversarial networks for labeled acceleration data augmentation for structural damage detection. J Civil Struct Health Monit 13(1):181–98. https://doi.org/10.1007/s13349-022-00627-8
Kingma DP, Welling M (2013) Auto-encoding variational bayes, ar**v preprint ar**v:1312.6114. https://doi.org/10.48550/ar**v.1312.6114
Ma X, Lin Y, Nie Z, Ma H (2020) Structural damage identification based on unsupervised feature-extraction via variational Auto-encoder. Measurement 160:107811. https://doi.org/10.1016/j.measurement.2020.107811
Zhang Y, **e X, Li H, Zhou B (2022) An unsupervised tunnel damage identification method based on convolutional variational auto-encoder and wavelet packet analysis. Sensors 22(6):2412. https://doi.org/10.3390/s22062412
Sajedi S, Liang X (2022) Deep generative Bayesian optimization for sensor placement in structural health monitoring. Comput-Aided Civil Infrastruct Eng 37(9):1109–1127. https://doi.org/10.1111/mice.12799
F. Luleci, F.N. Catbas (2022) A Brief Introduction to Deep Generative Models for Civil Structural Health Monitoring, Civil Infrastructure Technologies for Resilience and Safety (CITRS). https://www.researchgate.net/publication/366422643_A_Brief_Introductory_Review_to_Deep_Generative_Models_for_Civil_Structural_Health_Monitoring . Retrieved 19 Dec 2022
Bogert BP (1963) The quefrency alanysis of time series for echoes: Cepstrum, pseudo-autocovariance, cross-cepstrum and saphe cracking. In Proc. Symposium Time Series Analysis. pp. 209–243. https://cir.nii.ac.jp/crid/1570854175999207936
Balsamo L, Betti R, Beigi H (2014) A structural health monitoring strategy using cepstral features. J Sound Vib 333(19):4526–4542. https://doi.org/10.1016/j.jsv.2014.04.062
Ioffe S (2006) Probabilistic linear discriminant analysis. In European Conference on Computer Vision, Springer, Berlin, Heidelberg. 531–542. https://doi.org/10.1007/11744085_41
Theis L, Oord AV, Bethge M (2015) A note on the evaluation of generative models. ar**v preprint ar**v:1511.01844. https://doi.org/10.48550/ar**v.1511.01844
Kingma DP, Welling M (2019) An introduction to variational autoencoders. Found Trends Mach Learn 12(4):307–92. https://doi.org/10.1561/2200000056
Gulrajani I, Kumar K, Ahmed F, Taiga AA, Visin F, Vazquez D, et al. (2016) Pixelvae: a latent variable model for natural images. ar**v preprint ar**v:1611.05013. https://doi.org/10.48550/ar**v.1611.05013
Villalba J, Brümmer N, Dehak N (2017) Tied Variational Autoencoder Backends for i-Vector Speaker Recognition. InInterspeech. 1004–1008. https://www.isca-speech.org/archive_v0/Interspeech_2017/pdfs/1018.PDF. Retrieved 20 Dec 2022
Jordan MI (2004) Graphical models. Stat Sci 19(1):140–155. https://doi.org/10.1214/088342304000000026
Wu Z, Wang S, Qian Y, Yu K. Data Augmentation Using Variational Autoencoder for Embedding Based Speaker Verification. In INTERSPEECH. 1163–1167. https://www.isca-speech.org/archive_v0/Interspeech_2019/pdfs/2248.pdf. Retrieved 20 Dec 2022
Sohn K, Lee H, Yan X (2015) Learning structured output representation using deep conditional generative models. Advances in neural information processing systems. 28. https://openreview.net/forum?id=rJWXGDWd-H. Retrieved 21 Dec 2022
Kullback S (1997) Information theory and statistics. Courier Corporation
Doersch C (2016) Tutorial on variational autoencoders. ar**v preprint ar**v:1606.05908. https://doi.org/10.48550/ar**v.1606.05908
Kingma DP, Mohamed S, Jimenez Rezende D, Welling M (2014) Semi-supervised learning with deep generative models. Advances in neural information processing systems. 27. https://ui.adsabs.harvard.edu/link_gateway/2014ar**v1406.5298K/arxiv:1406.5298
An J, Cho S (2015) Variational autoencoder based anomaly detection using reconstruction probability. Special Lecture on IE. 2(1):1–8. http://dm.snu.ac.kr/static/docs/TR/SNUDM-TR-2015-03.pdf
Taud H, Mas JF (2018) Multilayer perceptron (MLP). Geomatic approaches for modeling land change scenarios. Springer, pp 451–455. https://doi.org/10.1007/978-3-319-60801-3_27.pdf
Izenman AJ (2013) Linear discriminant analysis. Modern multivariate statistical techniques. New York, Springer, pp 237–280. https://doi.org/10.1007/978-0-387-78189-1_8.pdf
Sizov A, Lee KA, Kinnunen T (2014) Unifying probabilistic linear discriminant analysis variants in biometric authentication. In Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR), Springer, Berlin, Heidelberg. 464–475. https://doi.org/10.1007/978-3-662-44415-3_47
Rossi RJ (2018) Mathematical statistics: an introduction to likelihood based inference. Wiley, Cham
Nandakumar K, Chen Y, Dass SC, Jain A (2007) Likelihood ratio-based biometric score fusion. IEEE Trans Pattern Anal Mach Intell 30(2):342–347. https://doi.org/10.1109/TPAMI.2007.70796
Boger Z, Guterman H (1997) Knowledge extraction from artificial neural network models. In1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation, IEEE. 4:3030–3035. https://doi.org/10.1109/ICSMC.1997.633051
Zhai G, Narazaki Y, Wang S, Shajihan SA, Spencer BF Jr (2022) Synthetic data augmentation for pixel-wise steel fatigue crack identification using fully convolutional networks. Smart Struct Syst 29(1):237–50. https://doi.org/10.12989/sss.2022.29.1.237
Jurafsky D (2000) Speech and language processing. Pearson Education India
Krämer C, De Smet CA, De Roeck G (1999) Z24 bridge damage detection tests. In IMAC 17, the International Modal Analysis Conference, Society of Photo-optical Instrumentation Engineers 3727:1023–1029. https://lirias.kuleuven.be/1123428?limo=0
Reynders E, De Roeck G Vibration-based damage identification: the Z24 benchmark. https://lirias.kuleuven.be/1725994?limo=0
Giglioni V, Venanzi I, Baia AE, Poggioni V, Milani A, Ubertini F (2023) Deep autoencoders for unsupervised damage detection with application to the Z24 benchmark bridge. In: Yen T (ed) European workshop on structural health monitoring. Springer, Cham, pp 1048–1057. https://doi.org/10.1007/978-3-031-07258-1_105
Acknowledgements
The authors gratefully acknowledge the Brite EuRam Programme BE-3157 SIMCES, the European Commission and the Structural Mechanics Section of KU Leuven for gathering and sharing the data of the Z24 bridge. We also would like to thank Ms. Sanaa Mouzahir for critically reading the final manuscript.
Author information
Authors and Affiliations
Corresponding author
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
Li, L., Betti, R. A machine learning-based data augmentation strategy for structural damage classification in civil infrastructure system. J Civil Struct Health Monit 13, 1265–1285 (2023). https://doi.org/10.1007/s13349-023-00705-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13349-023-00705-5