Metamodeling through Deep Learning of High-Dimensional Dynamic Nonlinear Systems Driven by General Stochastic Excitation
Authors:
- 1 November 2022
- journal article
- research article
- Published by American Society of Civil Engineers (ASCE) in Journal of Structural Engineering
- Vol. 148 (11) , 04022186
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.Keywords
This publication has 41 references indexed in Scilit:
- Metamodel-based regional vulnerability estimate of irregular steel moment-frame structures subjected to earthquake eventsEngineering Structures, 2012
- A method for solving stochastic equations by reduced order models and local approximationsJournal of Computational Physics, 2012
- Simulation of synthetic ground motions for specified earthquake and site characteristicsEarthquake Engineering & Structural Dynamics, 2010
- A numerical procedure for computing the fragility of NPP components under random seismic excitationNuclear Engineering and Design, 2009
- Reduced order models for random functions. Application to stochastic problemsApplied Mathematical Modelling, 2009
- Artificial Neural Networks for Predicting the Response of Structural Systems with Viscoelastic DampersComputer-Aided Civil and Infrastructure Engineering, 2005
- PHYSICAL INTERPRETATION OF THE PROPER ORTHOGONAL MODES USING THE SINGULAR VALUE DECOMPOSITIONJournal of Sound and Vibration, 2002
- Long Short-Term MemoryNeural Computation, 1997
- Input-output parametric models for non-linear systems Part I: deterministic non-linear systemsInternational Journal of Control, 1985
- Multiquadric equations of topography and other irregular surfacesJournal of Geophysical Research, 1971