Metamodeling through Deep Learning of High-Dimensional Dynamic Nonlinear Systems Driven by General Stochastic Excitation
Publication: Journal of Structural Engineering
Volume 148, Issue 11
Abstract
Modern performance evaluation and design procedures for structural systems against severe natural hazards generally require the propagation of uncertainty through the repeated evaluation of high-dimensional nonlinear dynamic systems. This often leads to intractable computational problems. A potential remedy to this situation is to accelerate the evaluation of the dynamic system through leveraging metamodeling techniques. In this work, deep learning is combined with a data-driven model order reduction technique for defining a highly efficient and nonintrusive metamodeling approach for nonlinear dynamic systems subject to general stochastic excitation. Potentially high-dimensional building structures are reduced first through Galerkin projection by leveraging a set of proper orthogonal decomposition bases via singular value decomposition. A long-short term memory deep learning network is subsequently trained to mimic the mapping from the space of the excitation to the responses of the reduced model. In addition, to accelerate the efficiency of the network, wavelet approximations of the reduced excitation and responses are incorporated. The potential of the metamodeling framework is illustrated through the application to both a multi-degree-of-freedom Bouc–Wen system as well as a multi-degree-of-freedom fiber-discretized nonlinear steel moment resisting frame. The calibrated metamodels are shown to be over three orders of magnitude faster than state-of-the-art high-fidelity nonlinear dynamic solvers while preserving remarkable accuracy in reproducing both global and local dynamic response.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
All data, models, and code generated or used during the study appear in the published article.
Acknowledgments
This research effort was supported in part by the National Science Foundation (NSF) under Grant No. CMMI-1750339. This support is gratefully acknowledged.
References
ASCE. 2016. Minimum design loads and associated criteria for buildings and other structures. ASCE/SEI 7-16. Reston, VA: ASCE.
Bamer, F., A. K. Amiri, and C. Bucher. 2017. “A new model order reduction strategy adapted to nonlinear problems in earthquake engineering.” Earthquake Eng. Struct. Dyn. 46 (4): 537–559. https://doi.org/10.1002/eqe.2802.
Bengio, Y., P. Simard, and P. Frasconi. 1994. “Learning long-term dependencies with gradient descent is difficult.” IEEE Trans. Neural Networks 5 (2): 157–166. https://doi.org/10.1109/72.279181.
Bhattacharyya, B., E. Jacquelin, and D. Brizard. 2020. “A Kriging–NARX model for uncertainty quantification of nonlinear stochastic dynamical systems in time domain.” J. Eng. Mech. 146 (7): 04020070. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001792.
Billings, S. A. 2013. Nonlinear system identification: NARMAX methods in the time, frequency, and spatio-temporal domains. New York: Wiley.
Box, G. E., and K. B. Wilson. 1951. “On the experimental attainment of optimum conditions.” J. R. Stat. Soc. B 13 (1): 1–38. https://doi.org/10.1111/j.2517-6161.1951.tb00067.x.
Chatterjee, T., and R. Chowdhury. 2017. “An efficient sparse Bayesian learning framework for stochastic response analysis.” Struct. Saf. 68 (Sep): 1–14. https://doi.org/10.1016/j.strusafe.2017.05.003.
Chuang, W. C., and S. M. J. Spence. 2019. “Rapid uncertainty quantification for non-linear and stochastic wind excited structures: A metamodeling approach.” Meccanica 54 (9): 1327–1338. https://doi.org/10.1007/s11012-019-00958-9.
Cohen, A., I. Daubechies, and J.-C. Feauveau. 1992. “Biorthogonal bases of compactly supported wavelets.” Commun. Pure Appl. Math. 45 (5): 485–560. https://doi.org/10.1002/cpa.3160450502.
De Grandis, S., M. Domaneschi, and F. Perotti. 2009. “A numerical procedure for computing the fragility of NPP components under random seismic excitation.” Nucl. Eng. Des. 239 (11): 2491–2499. https://doi.org/10.1016/j.nucengdes.2009.06.027.
Gharehbaghi, S., H. Yazdani, and M. Khatibinia. 2019. “Estimating inelastic seismic response of reinforced concrete frame structures using a wavelet support vector machine and an artificial neural network.” Neural Comput. Appl. 32 (8): 2975–2988. https://doi.org/10.1007/s00521-019-04075-2.
Ghosh, S., A. Roy, and S. Chakraborty. 2019. “Kriging metamodeling-based Monte Carlo simulation for improved seismic fragility analysis of structures.” J. Earthquake Eng. 25 (7): 1316–1336. https://doi.org/10.1080/13632469.2019.1570395.
Gidaris, I., and A. A. Taflanidis. 2013. “Parsimonious modeling of hysteretic structural response in earthquake engineering: Calibration/validation and implementation in probabilistic risk assessment.” Eng. Struct. 49 (Apr): 1017–1033. https://doi.org/10.1016/j.engstruct.2012.12.030.
Gidaris, I., A. A. Taflanidis, and G. P. Mavroeidis. 2015. “Kriging metamodeling in seismic risk assessment based on stochastic ground motion models.” Earthquake Eng. Struct. Dyn. 44 (14): 2377–2399. https://doi.org/10.1002/eqe.2586.
Grigoriu, M. 2009. “Reduced order models for random functions. Application to stochastic problems.” Appl. Math. Modell. 33 (1): 161–175. https://doi.org/10.1016/j.apm.2007.10.023.
Grigoriu, M. 2012. “A method for solving stochastic equations by reduced order models and local approximations.” J. Comput. Phys. 231 (19): 6495–6513. https://doi.org/10.1016/j.jcp.2012.06.013.
Hardy, R. L. 1971. “Multiquadric equations of topography and other irregular surfaces.” J. Geophys. Res. 76 (8): 1905–1915. https://doi.org/10.1029/JB076i008p01905.
Hochreiter, S., and J. Schmidhuber. 1997. “Long short-term memory.” Neural Comput. 9 (8): 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735.
Jensen, H., A. Muñoz, C. Papadimitriou, and E. Millas. 2016. “Model reduction techniques for reliability-based design problems of complex structural systems.” Reliab. Eng. Syst. Saf. 149 (May): 204–217. https://doi.org/10.1016/j.ress.2016.01.003.
Kerschen, G., and J. C. Golinval. 2002. “Physical interpretation of the proper orthogonal modes using the singular value decomposition.” J. Sound Vib. 249 (5): 849–865. https://doi.org/10.1006/jsvi.2001.3930.
Kim, T., O.-S. Kwon, and J. Song. 2019. “Response prediction of nonlinear hysteretic systems by deep neural networks.” Neural Networks 111 (Mar): 1–10. https://doi.org/10.1016/j.neunet.2018.12.005.
Kim, T., J. Song, and O.-S. Kwon. 2020. “Probabilistic evaluation of seismic responses using deep learning method.” Struct. Saf. 84 (May): 101913. https://doi.org/10.1016/j.strusafe.2019.101913.
Kingma, D. P., and J. Ba. 2014. “Adam: A method for stochastic optimization.” Preprint, submitted July 5, 2022. http://arxiv.org/abs/1412.6980.
Krige, D. G. 1951. “A statistical approach to some basic mine valuation problems on the Witwatersrand.” J. South Afr. Inst. Min. Metall. 52 (6): 119–139.
Krishnamurthy, T. 2003. “Response surface approximation with augmented and compactly supported radial basis functions.” In Proc., 44th AIAA/ASME/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conf., 1748. Reston, VA: American Institute of Aeronautics and Astronautics. https://doi.org/10.2514/6.2003-1748.
Kundu, A., and S. Chakraborty. 2020. “Deep learning-based metamodeling technique for nonlinear seismic response quantification.” IOP Conf. Ser.: Mater. Sci. Eng. 936 (1): 012042. https://doi.org/10.1088/1757-899X/936/1/012042.
Le, T.-H., and L. Caracoglia. 2015. “Reduced-order wavelet-Galerkin solution for the coupled, nonlinear stochastic response of slender buildings in transient winds.” J. Sound Vib. 344 (May): 179–208. https://doi.org/10.1016/j.jsv.2015.01.007.
LeCun, Y., Y. Bengio, and G. Hinton. 2015. “Deep learning.” Nature 521 (7553): 436–444. https://doi.org/10.1038/nature14539.
Leontaritis, I. J., and S. A. Billings. 1985. “Input-output parametric models for non-linear systems. I: Deterministic non-linear systems.” Int. J. Control 41 (2): 303–328. https://doi.org/10.1080/0020718508961129.
Li, B., W. C. Chuang, and S. M. J. Spence. 2021. “Response estimation of multi-degree-of-freedom nonlinear stochastic structural systems through metamodeling.” J. Eng. Mech. 147 (11): 04021082. https://doi.org/10.1061/(ASCE)EM.1943-7889.0001963.
Mai, C. V. 2016. “Polynomial chaos expansions for uncertain dynamical systems—Applications in earthquake engineering.” Ph.D. thesis, Department of Construction, Environment and Geomatics, ETH Zurich.
Mai, C. V., M. D. Spiridonakos, E. N. Chatzi, and B. Sudret. 2016. “Surrogate modeling for stochastic dynamical systems by combining nonlinear autoregressive with exogenous input models and polynomial chaos expansions.” Int. J. Uncertainty Quantif. 6 (4): 313–339. https://doi.org/10.1615/Int.J.UncertaintyQuantification.2016016603.
Molina Hutt, C., I. Almufti, M. Willford, and G. Deierlein. 2016. “Seismic loss and downtime assessment of existing tall steel-framed buildings and strategies for increased resilience.” J. Struct. Eng. 142 (8): C4015005. https://doi.org/10.1061/(ASCE)ST.1943-541X.0001314.
Pascanu, R., T. Mikolov, and Y. Bengio. 2013. “On the difficulty of training recurrent neural networks.” In Proc., Int. Conf. on Machine Learning, PMLR, 1310–1318. Cambridge, UK: PMLR.
Patsialis, D., and A. A. Taflanidis. 2020. “Reduced order modeling of hysteretic structural response and applications to seismic risk assessment.” Eng. Struct. 209 (Apr): 110135. https://doi.org/10.1016/j.engstruct.2019.110135.
Perotti, F., M. Domaneschi, and S. De Grandis. 2013. “The numerical computation of seismic fragility of base-isolated nuclear power plants buildings.” Nucl. Eng. Des. 262 (Sep): 189–200. https://doi.org/10.1016/j.nucengdes.2013.04.029.
Rezaeian, S., and A. Der Kiureghian. 2010. “Simulation of synthetic ground motions for specified earthquake and site characteristics.” Earthquake Eng. Struct. Dyn. 39 (10): 1155–1180. https://doi.org/10.1002/eqe.997.
Rumelhart, D. E., G. E. Hinton, and R. J. Williams. 1986. Parallel distributed processing: Explorations in the microstructure of cognition, Vol. 1: Foundations learning internal representations by error propagation, 318–362. Cambridge, MA: MIT Press.
Saha, S. K., V. Matsagar, and S. Chakraborty. 2016. “Uncertainty quantification and seismic fragility of base-isolated liquid storage tanks using response surface models.” Probab. Eng. Mech. 43 (Jan): 20–35. https://doi.org/10.1016/j.probengmech.2015.10.008.
Segura, R., J. E. Padgett, and P. Paultre. 2020. “Metamodel-based seismic fragility analysis of concrete gravity dams.” J. Struct. Eng. 146 (7): 04020121. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002629.
Seo, J., L. Dueñas-Osorio, J. I. Craig, and B. J. Goodno. 2012. “Metamodel-based regional vulnerability estimate of irregular steel moment-frame structures subjected to earthquake events.” Eng. Struct. 45 (Dec): 585–597. https://doi.org/10.1016/j.engstruct.2012.07.003.
Shekhar, S., and J. Ghosh. 2020. “A metamodeling based seismic life-cycle cost assessment framework for highway bridge structures.” Reliab. Eng. Syst. Saf. 195 (Mar): 106724. https://doi.org/10.1016/j.ress.2019.106724.
Shi, Y., Z. Lu, L. Xu, and S. Chen. 2019. “An adaptive multiple-kriging-surrogate method for time-dependent reliability analysis.” Appl. Math. Modell. 70 (Jun): 545–571. https://doi.org/10.1016/j.apm.2019.01.040.
Spiridonakos, M. D., and E. N. Chatzi. 2015. “Metamodeling of nonlinear structural systems with parametric uncertainty subject to stochastic dynamic excitation.” Earthquakes Struct. 8 (4): 915–934. https://doi.org/10.12989/eas.2015.8.4.915.
Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. “Dropout: A simple way to prevent neural networks from overfitting.” J. Mach. Learn. Res. 15 (1): 1929–1958.
Towashiraporn, P. 2004. “Building seismic fragilities using response surface metamodels.” Ph.D. thesis, Dept. of Civil and Environmental Engineering, Georgia Institute of Technology.
Vaidyanathan, C., P. Kamatchi, and R. Ravichandran. 2005. “Artificial neural networks for predicting the response of structural systems with viscoelastic dampers.” Comput.-Aided Civ. Infrastruct. Eng. 20 (4): 294–302. https://doi.org/10.1111/j.1467-8667.2005.00395.
Volkwein, S. 2013. “Proper orthogonal decomposition: Theory and reduced-order modeling.” Lect. Notes Univ. Konstanz 4 (4): 1–29.
Wang, H., and T. Wu. 2020. “Knowledge-enhanced deep learning for wind-induced nonlinear structural dynamic analysis.” J. Struct. Eng. 146 (11): 04020235. https://doi.org/10.1061/(ASCE)ST.1943-541X.0002802.
Zhang, R., Y. Liu, and H. Sun. 2020a. “Physics-guided convolutional neural network (PhyCNN) for data-driven seismic response modeling.” Eng. Struct. 215 (Jul): 110704. https://doi.org/10.1016/j.engstruct.2020.110704.
Zhang, R., Y. Liu, and H. Sun. 2020b. “Physics-informed multi-LSTM networks for metamodeling of nonlinear structures.” Preprint, submitted July 5, 2022. http://arxiv.org/abs/2002.10253.
Information & Authors
Information
Published In
Journal of Structural Engineering
Volume 148 • Issue 11 • November 2022
Copyright
© 2022 American Society of Civil Engineers.
History
Received: Jan 5, 2022
Accepted: Jul 5, 2022
Published online: Sep 10, 2022
Published in print: Nov 1, 2022
Discussion open until: Feb 10, 2023
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Computer programming
- Computing in civil engineering
- Continuum mechanics
- Dynamic models
- Dynamics (solid mechanics)
- Engineering fundamentals
- Engineering mechanics
- Excitation (physics)
- Mathematics
- Models (by type)
- Motion (dynamics)
- Neural networks
- Nonlinear response
- Probability
- Solid mechanics
- Stochastic processes
- Structural behavior
- Structural dynamics
- Structural engineering
- Structural models
- Structural systems
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
- Lei Zhang, Luca Caracoglia, Wind-induced fragility of a monopole structure via Artificial Neural Network based surrogate analysis, Engineering Structures, 10.1016/j.engstruct.2022.115515, 278, (115515), (2023).
- Marcos Souza Lenzi, Leandro Fleck Fadel Miguel, Rafael Holdorf Lopez, Humberto Brambila de Salles, Second-order Krylov subspaces for model order reduction of buildings subjected to seismic excitation, Journal of the Brazilian Society of Mechanical Sciences and Engineering, 10.1007/s40430-023-04043-x, 45, 2, (2023).