Physics-Informed Neural Networks for System Identification of Structural Systems with a Multiphysics Damping Model
Publication: Journal of Engineering Mechanics
Volume 149, Issue 10
Abstract
Structural system identification is critical in resilience assessments and structural health monitoring, especially following natural hazards. Among the nonlinear structural behaviors, structural damping is a complex behavior that can be modeled as a multiphysics system wherein the structure interacts with an external thermal bath and undergoes thermalization. In this paper, we propose a novel physics-informed neural network approach for nonlinear structural system identification and demonstrate its application in multiphysics cases where the damping term is governed by a separated dynamics equation. The proposed approach, called PIDynNet, improves the estimation of the parameters of nonlinear structural systems by integrating auxiliary physics-based loss terms, one for the structural dynamics and one for the thermal transfer. These physics-based loss terms form the overall loss function in addition to a supervised data-based loss term. To ensure effective learning during the identification process, subsampling and early stopping strategies are developed. The proposed framework also has the generalization capability to predict nonlinear responses for unseen ground excitations. Two numerical experiments of nonlinear systems are conducted to demonstrate the comparative performance of PIDynNet.
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 that support the findings of this study are available from the corresponding author upon reasonable request, including training dataset and code.
Acknowledgments
This material is based in part upon work supported by the National Science Foundation under Grant No. CMMI-1752302 and USDOT under Grant No. 69A3551747105.
References
Abazarsa, F., S. Ghahari, F. Nateghi, and E. Taciroglu. 2013. “Response-only modal identification of structures using limited sensors.” Struct. Control Health Monit. 20 (6): 987–1006. https://doi.org/10.1002/stc.1513.
Adhikari, S. 2013. Structural dynamic analysis with generalized damping models: Analysis. New York: Wiley.
Alonso-Rodriguez, A., N. Nikitas, J. Knappett, G. Kampas, I. Anastasopoulos, and R. Fuentes. 2018. “System identification of tunnel response to ground motion considering a simplified model.” Front. Built Environ. 4 (Jul): 39. https://doi.org/10.3389/fbuil.2018.00039.
Baker, J. W., and C. Lee. 2018. “An improved algorithm for selecting ground motions to match a conditional spectrum.” J. Earthquake Eng. 22 (4): 708–723. https://doi.org/10.1080/13632469.2016.1264334.
Bouc, R. 1967. “Forced vibrations of mechanical systems with hysteresis.” In Proc., 14th Conf. on Nonlinear Oscillations. Prague, Czech Republic: Czechoslovak Academy of Sciences.
Ceravolo, R., S. Erlicher, and L. Z. Fragonara. 2013. “Comparison of restoring force models for the identification of structures with hysteresis and degradation.” J. Sound Vib. 332 (26): 6982–6999. https://doi.org/10.1016/j.jsv.2013.08.019.
Dissanayake, M., and N. Phan-Thien. 1994. “Neural-network-based approximations for solving partial differential equations.” Commun. Numer. Methods Eng. 10 (3): 195–201. https://doi.org/10.1002/cnm.1640100303.
Eshkevari, S. S., T. J. Matarazzo, and S. N. Pakzad. 2020. “Bridge modal identification using acceleration measurements within moving vehicles.” Mech. Syst. Signal Process. 141 (Jul): 106733. https://doi.org/10.1016/j.ymssp.2020.106733.
Eshkevari, S. S., M. Takáč, S. N. Pakzad, and M. Jahani. 2021. “Dynnet: Physics-based neural architecture design for nonlinear structural response modeling and prediction.” Eng. Struct. 229 (Feb): 111582. https://doi.org/10.1016/j.engstruct.2020.111582.
Gladstone, R. J., M. A. Nabian, and H. Meidani. 2022. “FO-Pinns: A first-order formulation for physics informed neural networks.” Preprint, submitted April 20, 2023. http://arxiv.org/abs/2210.14320.
Goncalves Salsa, R., D. T. Kawano, F. Ma, and G. Leitmann. 2018. “The inverse problem of linear Lagrangian dynamics.” J. Appl. Mech. 85 (3): 031002. https://doi.org/10.1115/1.4038749.
Gonzalez, J., and W. Yu. 2018. “Non-linear system modeling using LSTM neural networks.” IFAC-PapersOnLine 51 (13): 485–489. https://doi.org/10.1016/j.ifacol.2018.07.326.
Hoover, W. G. 1985. “Canonical dynamics: Equilibrium phase-space distributions.” Phys. Rev. A 31 (3): 1695. https://doi.org/10.1103/PhysRevA.31.1695.
Huang, P., and Z. Chen. 2021. “Deep learning for nonlinear seismic responses prediction of subway station.” Eng. Struct. 244 (Oct): 112735. https://doi.org/10.1016/j.engstruct.2021.112735.
Karimi, P., M. Butala, and F. Kamalabadi. 2020. “Efficient model selection in switching linear dynamic systems.” Preprint, submitted December 20, 2020. http://arxiv.org/abs/2012.04543.
Kingma, D. P., and J. Ba. 2014. “Adam: A method for stochastic optimization.” Preprint, submitted March 23, 2023. http://arxiv.org/abs/1412.6980.
Kiranyaz, S., O. Avci, O. Abdeljaber, T. Ince, M. Gabbouj, and D. J. Inman. 2021. “1D convolutional neural networks and applications: A survey.” Mech. Syst. Signal Process. 151 (Apr): 107398. https://doi.org/10.1016/j.ymssp.2020.107398.
Kraska, T. 2006. “Molecular-dynamics simulation of argon nucleation from supersaturated vapor in the NVE ensemble.” J. Chem. Phys. 124 (5): 054507. https://doi.org/10.1063/1.2162882.
Labík, S., and W. Smith. 1994. “Scaled particle theory and the efficient calculation of the chemical potential of hard spheres in the NVT ensemble.” Mol. Simul. 12 (1): 23–31. https://doi.org/10.1080/08927029408022533.
Lagaris, I. E., A. Likas, and D. I. Fotiadis. 1998. “Artificial neural networks for solving ordinary and partial differential equations.” IEEE Trans. Neural Networks 9 (5): 987–1000. https://doi.org/10.1109/72.712178.
Lai, Z., and S. Nagarajaiah. 2019a. “Semi-supervised structural linear/nonlinear damage detection and characterization using sparse identification.” Struct. Control Health Monit. 26 (3): e2306. https://doi.org/10.1002/stc.2306.
Lai, Z., and S. Nagarajaiah. 2019b. “Sparse structural system identification method for nonlinear dynamic systems with hysteresis/inelastic behavior.” Mech. Syst. Signal Process. 117 (Feb): 813–842. https://doi.org/10.1016/j.ymssp.2018.08.033.
Lee, H., and H. Park. 2011. “Gage-free stress estimation of a beam-like structure based on terrestrial laser scanning.” Comput.-Aided Civ. Infrastruct. Eng. 26 (8): 647–658. https://doi.org/10.1111/j.1467-8667.2011.00723.x.
Leylaz, G., S. F. Ma, and J.-Q. Sun. 2021. “An optimal model identification algorithm of nonlinear dynamical systems with the algebraic method.” J. Vib. Acoust. 143 (2): 021002. https://doi.org/10.1115/1.4048169.
Li, D., and Y. Wang. 2020. “Parameter identification of a differentiable Bouc-Wen model using constrained extended Kalman filter.” Struct. Health Monit. 20 (1): 360–378. https://doi.org/10.1177/1475921720929434.
Liu, T., and H. Meidani. 2022. “Graph neural network surrogate for seismic reliability analysis of highway bridge system.” Preprint, submitted October 13, 2022. http://arxiv.org/abs/2210.06404.
Louhghalam, A., R. J.-M. Pellenq, and F.-J. Ulm. 2018. “Thermalizing and damping in structural dynamics.” J. Appl. Mech. 85 (8): 081001. https://doi.org/10.1115/1.4040080.
Nabian, M. A., and H. Meidani. 2018. “A deep neural network surrogate for high-dimensional random partial differential equations.” Preprint, submitted June 8, 2018. http://arxiv.org/abs/1806.02957.
Nguyen, L. H., and J.-A. Goulet. 2018. “Anomaly detection with the switching Kalman filter for structural health monitoring.” Struct. Control Health Monit. 25 (4): e2136. https://doi.org/10.1002/stc.2136.
Nosé, S. 1984. “A unified formulation of the constant temperature molecular dynamics methods.” J. Chem. Phys. 81 (1): 511–519. https://doi.org/10.1063/1.447334.
Paszke, A., et al. 2019. “Pytorch: An imperative style, high-performance deep learning library.” In Advances in neural information processing systems, 32. La Jolla, CA: Neural Information Processing Systems Foundation.
Quade, M., M. Abel, J. Nathan Kutz, and S. L. Brunton. 2018. “Sparse identification of nonlinear dynamics for rapid model recovery.” Chaos: Interdiscip. J. Nonlinear Sci. 28 (6): 063116. https://doi.org/10.1063/1.5027470.
Raissi, M., P. Perdikaris, and G. E. Karniadakis. 2017. “Physics informed deep learning (Part I): Data-driven solutions of nonlinear partial differential equations.” Preprint, submitted November 28, 2015. http://arxiv.org/abs/1711.10561.
Sirca, G., Jr., and H. Adeli. 2012. “System identification in structural engineering.” Sci. Iran. 19 (6): 1355–1364. https://doi.org/10.1016/j.scient.2012.09.002.
Song, M., R. Astroza, H. Ebrahimian, B. Moaveni, and C. Papadimitriou. 2020. “Adaptive Kalman filters for nonlinear finite element model updating.” Mech. Syst. Signal Process. 143 (Sep): 106837. https://doi.org/10.1016/j.ymssp.2020.106837.
Villani, L. G., S. Da Silva, and A. Cunha. 2020. “Application of a stochastic version of the restoring force surface method to identify a Duffing oscillator.” In Nonlinear dynamics of structures, systems and devices, 299–307. New York: Springer.
Wang, Y. 2017. “A new concept using LSTM neural networks for dynamic system identification.” In Proc., American Control Conf. (ACC), 5324–5329. New York: IEEE.
Wen, Y.-K. 1976. “Method for random vibration of hysteretic systems.” J. Eng. Mech. Div. 102 (2): 249–263. https://doi.org/10.1061/JMCEA3.0002106.
Yang, Y., and J. P. Yang. 2018. “State-of-the-art review on modal identification and damage detection of bridges by moving test vehicles.” Int. J. Struct. Stab. Dyn. 18 (02): 1850025. https://doi.org/10.1142/S0219455418500256.
Zhang, D., L. Lu, L. Guo, and G. E. Karniadakis. 2019a. “Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems.” J. Comput. Phys. 397 (Nov): 108850. https://doi.org/10.1016/j.jcp.2019.07.048.
Zhang, R., Z. Chen, S. Chen, J. Zheng, O. Büyüköztürk, and H. Sun. 2019b. “Deep long short-term memory networks for nonlinear structural seismic response prediction.” Comput. Struct. 220 (Aug): 55–68. https://doi.org/10.1016/j.compstruc.2019.05.006.
Zhang, R., Y. Liu, and H. Sun. 2020. “Physics-informed multi-LSTM networks for metamodeling of nonlinear structures.” Comput. Methods Appl. Mech. Eng. 369 (Sep): 113226. https://doi.org/10.1016/j.cma.2020.113226.
Zhong, W., and H. Meidani. 2023. “PI-VAE: Physics-informed vibrational auto-encoder for stochastic differential equations.” Comput. Methods Appl. Mech. Eng. 403 (Mar): 115664. https://doi.org/10.1016/j.cma.2022.115664.
Information & Authors
Information
Published In
Journal of Engineering Mechanics
Volume 149 • Issue 10 • October 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Nov 14, 2022
Accepted: May 16, 2023
Published online: Aug 2, 2023
Published in print: Oct 1, 2023
Discussion open until: Jan 2, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Computer programming
- Computing in civil engineering
- Continuum mechanics
- Damping
- Dynamics (solid mechanics)
- Engineering mechanics
- Neural networks
- Nonlinear response
- Solid mechanics
- Structural behavior
- Structural dynamics
- Structural engineering
- Structural system identification
- Structural systems
- Thermal analysis
- Thermal properties
- Thermodynamics
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.