Fluid Flow Modelling Using Physics-Informed Convolutional Neural Network in Parametrised Domains

DOI10.1080/10618562.2023.2260763MaRDI QIDQ6092912zbMATH OpenOpenAlexFDO

Authors Ondřej Bublík, Václav Heidler, Aleš Pecka, Jan Vimmr

Publication date 23 November 2023

Published in International Journal of Computational Fluid Dynamics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/10618562.2023.2260763

zbMATH Keywords

convergent-divergent channel flowfinite difference methodincompressible Navier-Stokes equationsLagrange interpolationU-Net architecture

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Navier-Stokes equations for incompressible viscous fluids (76D05) Finite difference methods applied to problems in fluid mechanics (76M20) Basic methods in fluid mechanics (76M99)

Recommendations

• Data-driven, physics-based feature extraction from fluid flow fields using convolutional neural networks
• Physics-informed neural networks for high-speed flows
• Construction of reduced-order models for fluid flows using deep feedforward neural networks
• A physics-informed convolutional neural network for the simulation and prediction of two-phase Darcy flows in heterogeneous porous media
• Fluids-structures in Eulerian formulation and parameter identification by deep neural network
• Deep learning in fluid dynamics
• Deep-learning accelerated calculation of real-fluid properties in numerical simulation of complex flowfields
• Surrogate convolutional neural network models for steady computational fluid dynamics simulations

Cited in

(14)

• A minimalistic approach to physics-informed machine learning using neighbour lists as physics-optimized convolutions for inverse problems involving particle systems
• NSFnets (Navier-Stokes flow nets): physics-informed neural networks for the incompressible Navier-Stokes equations
• Weak form theory-guided neural network (TgNN-wf) for deep learning of subsurface single- and two-phase flow
• Deep-learning accelerated calculation of real-fluid properties in numerical simulation of complex flowfields
• Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network
• Physics-informed neural networks for high-speed flows
• Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data
• Variable separated physics-informed neural networks based on adaptive weighted loss functions for blood flow model
• Investigation of Low and High-Speed Fluid Dynamics Problems Using Physics-Informed Neural Network
• Neural-physics multi-fidelity model with active learning and uncertainty quantification for GPU-enabled microfluidic concentration gradient generator design
• Solving high-dimensional parametric engineering problems for inviscid flow around airfoils based on physics-informed neural networks
• Junction conditions for one-dimensional network hemodynamic model for total cavopulmonary connection using physically informed deep learning technique
• Identification of settling velocity with physics informed neural networks for sediment laden flows
• A spatio-temporal radial basis function collocation method based on Hausdorff fractal distance for Hausdorff derivative heat conduction equations in three-dimensional anisotropic materials

This page was built for publication: Fluid Flow Modelling Using Physics-Informed Convolutional Neural Network in Parametrised Domains

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6092912)