Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data

Abstract

Numerical simulations on fluid dynamics problems primarily rely on spatially or/and temporally discretization of the governing equation into the finite-dimensional algebraic system solved by computers. Due to complicated nature of the physics and geometry, such process can be computational prohibitive for most real-time applications and many-query analyses. Therefore, developing a cost-effective surrogate model is of great practical significance. Deep learning (DL) has shown new promises for surrogate modeling due to its capability of handling strong nonlinearity and high dimensionality. However, the off-the-shelf DL architectures fail to operate when the data becomes sparse. Unfortunately, data is often insufficient in most parametric fluid dynamics problems since each data point in the parameter space requires an expensive numerical simulation based on the first principle, e.g., Naiver--Stokes equations. In this paper, we provide a physics-constrained DL approach for surrogate modeling of fluid flows without relying on any simulation data. Specifically, a structured deep neural network (DNN) architecture is devised to enforce the initial and boundary conditions, and the governing partial differential equations are incorporated into the loss of the DNN to drive the training. Numerical experiments are conducted on a number of internal flows relevant to hemodynamics applications, and the forward propagation of uncertainties in fluid properties and domain geometry is studied as well. The results show excellent agreement on the flow field and forward-propagated uncertainties between the DL surrogate approximations and the first-principle numerical simulations.

43 pages, 12 figures

References in corpus (6)

• Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Theano: new features and speed improvements
• Searching for Activation Functions
• Deep autoregressive neural networks for high-dimensional inverse problems in groundwater contaminant source identification
• Imposing Hard Constraints on Deep Networks: Promises and Limitations

Cited by in corpus (119)

• On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks
• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• Physics-informed learning of governing equations from scarce data
• Physics-Informed Multi-LSTM Networks for Metamodeling of Nonlinear Structures
• Self-adaptive loss balanced Physics-informed neural networks for the incompressible Navier-Stokes equations
• A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applications
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
• Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations
• Flow over an espresso cup: Inferring 3D velocity and pressure fields from tomographic background oriented schlieren videos via physics-informed neural networks
• Physics-informed deep learning for incompressible laminar flows
• Physics-Informed Neural Network for Modelling the Thermochemical Curing Process of Composite-Tool Systems During Manufacture
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• Uncovering near-wall blood flow from sparse data with physics-informed neural networks
• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• Physics informed neural networks for continuum micromechanics
• DeepM&Mnet: Inferring the electroconvection multiphysics fields based on operator approximation by neural networks
• Understanding and mitigating gradient pathologies in physics-informed neural networks
• Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
• Deep-learning-based surrogate flow modeling and geological parameterization for data assimilation in 3D subsurface flow
• Deep Learning in Deterministic Computational Mechanics
• Physics-Informed Neural Operator for Learning Partial Differential Equations
• Physics-Informed Neural Network Method for Forward and Backward Advection-Dispersion Equations
• Residual-based adaptivity for two-phase flow simulation in porous media using Physics-informed Neural Networks
• When and why PINNs fail to train: A neural tangent kernel perspective
• Distributed physics informed neural network for data-efficient solution to partial differential equations
• Deep learning of free boundary and Stefan problems
• Physics-informed neural networks of the Saint-Venant equations for downscaling a large-scale river model
• Geom-DeepONet: A Point-cloud-based Deep Operator Network for Field Predictions on 3D Parameterized Geometries
• Multilevel domain decomposition-based architectures for physics-informed neural networks
• Learning in Sinusoidal Spaces with Physics-Informed Neural Networks
• Deep Learning for One-dimensional Consolidation
• A practical PINN framework for multi-scale problems with multi-magnitude loss terms
• Efficient Uncertainty Quantification for Dynamic Subsurface Flow with Surrogate by Theory-guided Neural Network
• A novel meta-learning initialization method for physics-informed neural networks
• Solving Forward and Inverse Problems of Contact Mechanics using Physics-Informed Neural Networks
• Theory-guided Auto-Encoder for Surrogate Construction and Inverse Modeling
• Physics-Informed Neural Networks with Adaptive Localized Artificial Viscosity
• Multifidelity Deep Operator Networks For Data-Driven and Physics-Informed Problems
• Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics
• Surrogate and inverse modeling for two-phase flow in porous media via theory-guided convolutional neural network
• Active Training of Physics-Informed Neural Networks to Aggregate and Interpolate Parametric Solutions to the Navier-Stokes Equations
• Generative AI and Process Systems Engineering: The Next Frontier
• Data-driven soliton solutions and model parameters of nonlinear wave models via the conservation-law constrained neural network method
• Adaptive weighting of Bayesian physics informed neural networks for multitask and multiscale forward and inverse problems
• Mosaic Flows: A Transferable Deep Learning Framework for Solving PDEs on Unseen Domains
• A solver for subsonic flow around airfoils based on physics-informed neural networks and mesh transformation
• Global Sensitivity Analysis of Four Chamber Heart Hemodynamics Using Surrogate Models
• Adaptive Training of Grid-Dependent Physics-Informed Kolmogorov-Arnold Networks
• Learning nonlocal constitutive models with neural networks
• DropTrack -- automatic droplet tracking using deep learning for microfluidic applications
• A complete state-space solution model for inviscid flow around airfoils based on physics-informed neural networks
• Deep-learning assisted reduced order model for high-dimensional flow prediction from sparse data
• A robust single-pixel particle image velocimetry based on fully convolutional networks with cross-correlation embedded
• Finite volume method network for acceleration of unsteady computational fluid dynamics: non-reacting and reacting flows
• Using neural networks to accelerate the solution of the Boltzmann equation
• GINNs: Graph-Informed Neural Networks for Multiscale Physics
• Physics-Informed Neural Networks for Parametric Compressible Euler Equations
• Physics-driven Learning of the Steady Navier-Stokes Equations using Deep Convolutional Neural Networks
• Predicting Opinion Dynamics via Sociologically-Informed Neural Networks
• Physics-aware deep neural networks for surrogate modeling of turbulent natural convection
• A Bi-fidelity Surrogate Modeling Approach for Uncertainty Propagation in Three-Dimensional Hemodynamic Simulations
• Adaptive physics-informed neural operator for coarse-grained non-equilibrium flows
• Physics-integrated hybrid framework for model form error identification in nonlinear dynamical systems
• A Deep Learning Approach for the solution of Probability Density Evolution of Stochastic Systems
• Physics-Informed Deep Learning of Rate-and-State Fault Friction
• Kalibre: Knowledge-based Neural Surrogate Model Calibration for Data Center Digital Twins
• A Combined Data-driven and Physics-driven Method for Steady Heat Conduction Prediction using Deep Convolutional Neural Networks
• Variational operator learning: A unified paradigm marrying training neural operators and solving partial differential equations
• Joint Deep Reversible Regression Model and Physics-Informed Unsupervised Learning for Temperature Field Reconstruction
• Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes
• Making Invisible Visible: Data-Driven Seismic Inversion with Spatio-temporally Constrained Data Augmentation
• Machine learning for metal additive manufacturing: Predicting temperature and melt pool fluid dynamics using physics-informed neural networks
• Deep learning for solution and inversion of structural mechanics and vibrations
• Bayesian neural networks for weak solution of PDEs with uncertainty quantification
• Physics-informed deep learning for flow and deformation in poroelastic media
• Multi-scale Time-stepping of Partial Differential Equations with Transformers
• PhyAug: Physics-Directed Data Augmentation for Deep Sensing Model Transfer in Cyber-Physical Systems
• Mutual Information for Explainable Deep Learning of Multiscale Systems
• Physics-Constrained Bayesian Neural Network for Fluid Flow Reconstruction with Sparse and Noisy Data
• Improved Surrogate Modeling of Fluid Dynamics with Physics-Informed Neural Networks
• Rapid Estimation of Left Ventricular Contractility with a Physics-Informed Neural Network Inverse Modeling Approach
• Solution of FPK Equation for Stochastic Dynamics Subjected to Additive Gaussian Noise via Deep Learning Approach
• Modelling parametric uncertainty in PDEs models via Physics-Informed Neural Networks
• Physics Informed Neural Networks for Modeling of 3D Flow-Thermal Problems with Sparse Domain Data
• Physics-informed Convolutional Neural Networks for Temperature Field Prediction of Heat Source Layout without Labeled Data
• A Physics-Informed Deep Learning Description of Knudsen Layer Reactivity Reduction
• Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids
• CGKN: A Deep Learning Framework for Modeling Complex Dynamical Systems and Efficient Data Assimilation
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• Approximately well-balanced Discontinuous Galerkin methods using bases enriched with Physics-Informed Neural Networks
• Generative Adversarial Networks with Physical Evaluators for Spray Simulation of Pintle Injector
• Multi-Fidelity Machine Learning Applied to Steady Fluid Flows
• Approximating Families of Sharp Solutions to Fisher's Equation with Physics-Informed Neural Networks
• Predicting continuum breakdown with deep neural networks
• Augmenting a Physics-Informed Neural Network for the 2D Burgers Equation by Addition of Solution Data Points
• Connect the Dots: In Situ 4D Seismic Monitoring of CO2 Storage with Spatio-temporal CNNs
• Conditionally Parameterized, Discretization-Aware Neural Networks for Mesh-Based Modeling of Physical Systems
• Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
• Point-DeepONet: Predicting Nonlinear Fields on Non-Parametric Geometries under Variable Load Conditions
• FlexPINN: Modeling Fluid Dynamics and Mass Transfer in 3D Micromixer Geometries Using a Flexible Physics-Informed Neural Network
• Leveraging Interpolation Models and Error Bounds for Verifiable Scientific Machine Learning
• Physics-Informed Neural Networks for Solving Multiscale Mode-Resolved Phonon Boltzmann Transport Equation
• A Bayesian Neural Network Approach for Tropospheric Temperature Retrievals from a Lidar Instrument
• Label-free timing analysis of SiPM-based modularized detectors with physics-constrained deep learning
• Optimal Transport Based Refinement of Physics-Informed Neural Networks
• Resistance-Time Co-Modulated PointNet for Temporal Super-Resolution Simulation of Blood Vessel Flows
• Machine Learning for Naval Architecture, Ocean and Marine Engineering
• Approximation of sea surface velocity field by fitting surrogate two-dimensional flow to scattered measurements
• A discrete physics-informed training for projection-based reduced order models with neural networks
• Physics-informed neural networks for non-Newtonian fluid thermo-mechanical problems: an application to rubber calendering process
• Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control
• Accelerating Dimensionality Reduction in Wave-Resistance Problems through Geometric Operators
• Variational inference formulation for a model-free simulation of a dynamical system with unknown parameters by a recurrent neural network
• Recurrent convolutional neural network for the surrogate modeling of subsurface flow simulation
• Hard-constraint physics-residual networks for hydrogen crossover prediction and high-pressure extrapolation in PEM water electrolysis
• Efficient data-driven flow modeling for accurate passive scalar advection in submesoscale domains