Filter Banks and Hybrid Deep Learning Architectures for Performance-Based Seismic Assessments of Bridges
Publication: Journal of Structural Engineering
Volume 148, Issue 12
Abstract
The existing machine learning (ML) models for vibration-based damage assessments often use highly compressed features or are restricted to preprocessed signals with fixed durations and sampling rates. Additionally, the learning capacities of ML models and computational resources are limited, which restricts using raw signals as direct input. This paper studied Mel filter banks (MFBs) for seismic signal processing, inspired by speech recognition technology. It is argued that the same filter designs in audio engineering may not be appropriate for seismic records, and therefore, a customized filter bank formulation was developed. Hybrid deep learning models for rapid assessments (HyDRA) were introduced as multibranch neural network architectures that enable end-to-end training for different types of processed vibration data structures. Moreover, the performance-based earthquake engineering (PBEE) equation was adjusted to integrate ML model uncertainties for probabilistic assessments. The proposed concepts were validated in a case study based on a data set of 32,400 nonlinear time-history analyses of a highway bridge in California. Insights and guidelines are provided for optimum filter design based on 5,184 experiments. Several HyDRA architectures were compared with benchmark models. The optimized MFB feature type outperformed features obtained from continuous wavelet transform and a stacked vector of conventional earthquake engineering indexes. A Bayesian variant of HyDRA was investigated to showcase its integration in the modified PBEE equation. Adopting custom filter banks with the HyDRA architecture enables effective feature extraction from raw vibration records by diversifying feature space and preserving information in the time and frequency domains.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the study are available in a repository online in accordance with funder data retention policies (https://github.com/OmidSaj/HyDRA).
Acknowledgments
The research was supported by the CAIT Region 2 UTC Consortium and the Institute of Bridge Engineering at the University at Buffalo. The authors gratefully acknowledge their generous support. The authors also acknowledge NVIDIA for the donation of a Titan V GPU that was used in this research.
References
Abdeljaber, O., O. Avci, M. S. Kiranyaz, B. Boashash, H. Sodano, and D. J. Inman. 2018. “1-D CNNs for structural damage detection: Verification on a structural health monitoring benchmark data.” Neurocomputing 275 (Jan): 1308–1317. https://doi.org/10.1016/j.neucom.2017.09.069.
AES (Audio Engineering Society). 2018. AES recommended practice for professional digital audio—Preferred sampling frequencies for applications employing pulse-code modulation. New York: AES.
Akkar, S., and Ö. Özen. 2005. “Effect of peak ground velocity on deformation demands for SDOF systems.” Earthquake Eng. Struct. Dyn. 34 (13): 1551–1571. https://doi.org/10.1002/eqe.492.
Ancheta, T. D., et al. 2014. “NGA-West2 database.” Earthquake Spectra 30 (3): 989–1005. https://doi.org/10.1193/070913EQS197M.
ASCE. 2021. 2021 report card for America’s infrastructure. Reston, VA: ASCE.
ATC (Applied Technology Council). 2012. Seismic performance assessment of buildings. FEMA-P58. Washington, DC: ATC.
Avci, O., O. Abdeljaber, S. Kiranyaz, M. Hussein, M. Gabbouj, and D. J. Inman. 2021. “A review of vibration-based damage detection in civil structures: From traditional methods to Machine Learning and Deep Learning applications.” Mech. Syst. Sig. Process. 147 (Jan): 107077. https://doi.org/10.1016/j.ymssp.2020.107077.
Azimi, M., and G. Pekcan. 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.
Baker, J. W. 2015. “Efficient analytical fragility function fitting using dynamic structural analysis.” Earthquake Spectra 31 (1): 579–599. https://doi.org/10.1193/021113EQS025M.
Balsamo, L., R. Betti, and H. Beigi. 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.
Bogert, B. P., M. J. R. Healy, and J. W. Tukey. 1963. “The quefrency alanysis of time series for echoes; Cepstrum, pseudo-autocovariance, cross-cepstrum and saphe cracking.” Time Ser. Anal. 209–243.
Campbell, K. W., and Y. Bozorgnia. 2014. “NGA-West2 ground motion model for the average horizontal components of PGA, PGV, and 5% damped linear acceleration response spectra.” Earthquake Spectra 30 (3): 1087–1115. https://doi.org/10.1193/062913EQS175M.
CESMD (Center for Engineering Strong Motion Data). 2021. “Center for engineering strong motion data.” Accessed March 22, 2022. https://www.strongmotioncenter.org/.
Chan, W., N. Jaitly, Q. Le, and O. Vinyals. 2016. “Listen, attend and spell: A neural network for large vocabulary conversational speech recognition.” In Proc., 2016 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), 4960–4964. New York: IEEE.
Chen, T., and C. Guestrin. 2016. “Xgboost: A scalable tree boosting system.” In Proc., 22nd ACM SIGKDD Int. Conf. on Knowledge Discovery and Data Mining, 785–794. San Francisco: Association for Computing Machinery.
Cho, K., B. van Merriënboer, C. Gulcehre, D. Bahdanau, F. Bougares, H. Schwenk, and Y. Bengio. 2014. “Learning phrase representations using RNN encoder-decoder for statistical machine translation.” Preprint, submitted June 3, 2014. https://arxiv.org/abs/1406.1078.
Chollet, F., et al. 2015. “Keras.” Accessed March 22, 2022. https://github.com/keras-team/keras.
Civera, M., M. Ferraris, R. Ceravolo, C. Surace, and R. Betti. 2019. “The Teager-Kaiser energy cepstral coefficients as an effective structural health monitoring tool.” Appl. Sci. 9 (23): 5064. https://doi.org/10.3390/app9235064.
Cornell, C., and H. Krawinkler. 2000. “Progress and challenges in seismic performance assessment.” PEER Center News 3 (2): 1–3.
Dackermann, U., W. A. Smith, and R. B. Randall. 2014. “Damage identification based on response-only measurements using cepstrum analysis and artificial neural networks.” Struct. Health Monit. 13 (4): 430–444. https://doi.org/10.1177/1475921714542890.
Davis, S., and P. Mermelstein. 1980. “Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences.” IEEE Trans. Acoust. Speech Signal Process. 28 (4): 357–366. https://doi.org/10.1109/TASSP.1980.1163420.
Dutta, A. 1999. On energy-based seismic analysis and design of highway bridges. Buffalo, NY: State Univ. of New York at Buffalo.
Eltouny, K. A., and X. Liang. 2021. “Bayesian-optimized unsupervised learning approach for structural damage detection.” Comput.-Aided Civ. Infrastruct. Eng. 36 (10): 1249–1269. https://doi.org/10.1111/mice.12680.
Eltouny, K. A., and X. Liang. 2022. “Large-scale structural health monitoring using composite recurrent neural networks and grid environments.” Comput.-Aided Civ. Infrastruct. Eng. (Apr): 1–17. https://doi.org/10.1111/mice.12845.
Ferraris, M., M. Civera, R. Ceravolo, C. Surace, and R. Betti. 2020. “Using enhanced cepstral analysis for structural health monitoring.” In Proc., 13th Int. Conf. on Damage Assessment of Structures, 150–165. Singapore: Springer.
Gal, Y., and Z. Ghahramani. 2016. “Dropout as a Bayesian approximation: Representing model uncertainty in deep learning.” In Proc., Int. Conf. on Machine Learning, 1050–1059. New York: arXiv.
Guan, X., H. Burton, M. Shokrabadi, and Z. Yi. 2021. “Seismic drift demand estimation for steel moment frame buildings: From mechanics-based to data-driven models.” J. Struct. Eng. 147 (6): 04021058. https://doi.org/10.1061/(ASCE)ST.1943-541X.0003004.
Haddadi, H., A. Shakal, M. Huang, J. Parrish, C. Stephens, W. Savage, and W. Leith. 2012. “Report on progress at the center for engineering strong motion data (CESMD).” In Proc., World Conf. on Earthquake Engineering, 1–7. Lisbon, Portugal: Earthquake Science Center.
Hamburger, R., C. Rojahn, J. Heintz, and M. Mahoney. 2012. “FEMA P58: Next-generation building seismic performance assessment methodology.” In Proc., 15th World Conf. on Earthquake Engineering. Lisbon, Portugal: Earthquake Science Center.
Kaviani, P., F. Zareian, and E. Taciroglu. 2014. Performance-based seismic assessment of skewed bridges. Pacific Earthquake Engineering Research Center, Univ. of California Irvine. Berkeley, CA: Univ. of California.
Khodabandehlou, H., G. Pekcan, and M. S. Fadali. 2019. “Vibration-based structural condition assessment using convolution neural networks.” Struct. Control Health Monit. 26 (2): e2308. https://doi.org/10.1002/stc.2308.
Küçükdogan, B. 2007. “Investigation of the effect of ground-motion intensity measures on seismic demand parameters using probabilistic methods.” M.Sc. thesis, Dept. of Civil Engineering, Middle East Technical Univ.
Liang, X. 2019. “Image-based post-disaster inspection of reinforced concrete bridge systems using deep learning with Bayesian optimization.” Comput.-Aided Civ. Infrastruct. Eng. 34 (5): 415–430. https://doi.org/10.1111/mice.12425.
Liang, X., and K. M. Mosalam. 2020. “Ground motion selection and modification evaluation for highway bridges subjected to Bi-directional horizontal excitation.” Soil Dyn. Earthquake Eng. 130 (Mar): 105994. https://doi.org/10.1016/j.soildyn.2019.105994.
Mangalathu, S., and J.-S. Jeon. 2020. “Ground motion-dependent rapid damage assessment of structures based on wavelet transform and image analysis techniques.” J. Struct. Eng. 146 (11): 04020230. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002793.
McKenna, F., M. H. Scott, and G. L. Fenves. 2010. “Nonlinear finite-element analysis software architecture using object composition.” J. Comput. Civ. Eng. 24 (1): 95–107. https://doi.org/10.1061/(ASCE)CP.1943-5487.0000002.
Mei, Q., M. Gül, and M. Boay. 2019. “Indirect health monitoring of bridges using Mel-frequency cepstral coefficients and principal component analysis.” Mech. Syst. Sig. Process. 119 (Mar): 523–546. https://doi.org/10.1016/j.ymssp.2018.10.006.
Muin, S., C. Chern, and K. Mosalam. 2020. “Human-machine collaboration framework for bridge health monitoring.” In Proc., SMIP20 Seminar on Utilization of Strong-Motion Data, 100–127. Sacramento, CA: California Geological Survey and California Dept. of Conservation.
Oppenheim, A. V., and R. W. Schafer. 2004. “From frequency to quefrency: A history of the cepstrum.” IEEE Signal Process Mag. 21 (5): 95–106. https://doi.org/10.1109/MSP.2004.1328092.
Riddell, R. 2007. “On ground motion intensity indices.” Earthquake Spectra 23 (1): 147–173. https://doi.org/10.1193/1.2424748.
Sajedi, S., and X. Liang. 2021a. “Dual Bayesian inference for risk-informed vibration-based damage diagnosis.” Comput.-Aided Civ. Infrastruct. Eng. 36 (9): 1168–1184. https://doi.org/10.1111/mice.12642.
Sajedi, S., W. Liu, K. Eltouny, S. Behdad, M. Zheng, and X. Liang. 2022. “Uncertainty-assisted image-processing for human-robot close collaboration.” IEEE Rob. Autom. Lett. 7 (2): 4236–4243. https://doi.org/10.1109/LRA.2022.3150487.
Sajedi, S. O., and X. Liang. 2020a. “A data-driven framework for near real-time and robust damage diagnosis of building structures.” Struct. Control Health Monit. 27 (3): e2488. https://doi.org/10.1002/stc.2488.
Sajedi, S. O., and X. Liang. 2020b. “Vibration-based semantic damage segmentation for large-scale structural health monitoring.” Comput.-Aided Civ. Infrastruct. Eng. 35 (6): 579–596. https://doi.org/10.1111/mice.12523.
Sajedi, S. O., and X. Liang. 2021b. “Uncertainty-assisted deep vision structural health monitoring.” Comput.-Aided Civ. Infrastruct. Eng. 36 (2): 126–142. https://doi.org/10.1111/mice.12580.
Tamhidi, A., N. Kuehn, S. F. Ghahari, A. J. Rodgers, M. D. Kohler, E. Taciroglu, and Y. Bozorgnia. 2022. “Conditioned simulation of ground-motion time series at uninstrumented sites using Gaussian process regression.” Bull. Seismol. Soc. Am. 112 (1): 331–347. https://doi.org/10.1785/0120210054.
Virtanen, P., et al. 2020. “SciPy 1.0: Fundamental algorithms for scientific computing in Python.” Nat. Methods 17 (3): 261–272. https://doi.org/10.1038/s41592-019-0686-2.
Xu, Y., X. Lu, B. Cetiner, and E. Taciroglu. 2021. “Real-time regional seismic damage assessment framework based on long short-term memory neural network.” Comput.-Aided Civ. Infrastruct. Eng. 36 (4): 504–521. https://doi.org/10.1111/mice.12628.
Information & Authors
Information
Published In
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Oct 18, 2021
Accepted: Jul 14, 2022
Published online: Sep 23, 2022
Published in print: Dec 1, 2022
Discussion open until: Feb 23, 2023
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- De-Cheng Feng, Yue Li, Abdollah Shafieezadeh, Ertugrul Taciroglu, Advances in Data-Driven Risk-Based Performance Assessment of Structures and Infrastructure Systems, Journal of Structural Engineering, 10.1061/JSENDH.STENG-12434, 149, 5, (2023).
- Yitian Feng, Yifan Fei, Yuanqing Lin, Wenjie Liao, Xinzheng Lu, Intelligent Generative Design for Shear Wall Cross-Sectional Size Using Rule-Embedded Generative Adversarial Network, Journal of Structural Engineering, 10.1061/JSENDH.STENG-12206, 149, 11, (2023).
- Seyedomid Sajedi, Xiao Liang, Trident: A Deep Learning Framework for High-Resolution Bridge Vibration Monitoring, Applied Sciences, 10.3390/app122110999, 12, 21, (10999), (2022).