Data-driven reduced order model with temporal convolutional neural network

DOI10.1016/j.cma.2019.112766zbMath1441.76101OpenAlexW2996132844WikidataQ126535162 ScholiaQ126535162MaRDI QIDQ2175300

Pin Wu, Xuting Chang, Rossella Arcucci, Junwu Sun, Christopher C. Pain, Wen-Jie Zhang, Yi Ke Guo

Publication date: 29 April 2020

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cma.2019.112766

zbMATH Keywords

proper orthogonal decompositiondeep learningreduced order modeltemporal convolutional network

Mathematics Subject Classification ID

Computational methods for sparse matrices (65F50) Basic methods in fluid mechanics (76M99)

Related Items (11)

NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations ⋮ Model order reduction method based on (r)POD-ANNs for parameterized time-dependent partial differential equations ⋮ Retracted: Model order reduction method based on machine learning for parameterized time-dependent partial differential equations ⋮ An intelligent nonlinear meta element for elastoplastic continua: deep learning using a new time-distributed residual U-net architecture ⋮ CD-ROM: complemented deep -- reduced order model ⋮ Adaptive learning of effective dynamics for online modeling of complex systems ⋮ Parametric dynamic mode decomposition for reduced order modeling ⋮ Learning constitutive models from microstructural simulations via a non-intrusive reduced basis method ⋮ A DNN-based data-driven modeling employing coarse sample data for real-time flexible multibody dynamics simulations ⋮ Data-driven nonintrusive reduced order modeling for dynamical systems with moving boundaries using Gaussian process regression ⋮ Frame invariant neural network closures for Kraichnan turbulence

Uses Software

• Adam
• WaveNet

Cites Work

• Projection methods for reduced-order models of compressible flows.
• Non-intrusive reduced order modeling of nonlinear problems using neural networks
• A non-intrusive reduced-order model for compressible fluid and fractured solid coupling and its application to blasting
• Reduced order modeling for nonlinear structural analysis using Gaussian process regression
• Non-intrusive reduced order modeling of unsteady flows using artificial neural networks with application to a combustion problem
• Machine learning closures for model order reduction of thermal fluids
• Non-intrusive reduced order modelling of fluid-structure interactions
• Non-intrusive reduced order modelling of the Navier-Stokes equations
• A public turbulence database cluster and applications to study Lagrangian evolution of velocity increments in turbulence
• Nonintrusive reduced-order modeling of parametrized time-dependent partial differential equations
• Nonlinear Model Reduction via Discrete Empirical Interpolation
• Stabilization of projection‐based reduced‐order models
• Non‐intrusive reduced‐order modelling of the Navier–Stokes equations based on RBF interpolation
• Deep learning in fluid dynamics

This page was built for publication: Data-driven reduced order model with temporal convolutional neural network