Active Training of Physics-Informed Neural Networks to Aggregate and Interpolate Parametric Solutions to the Navier-Stokes Equations

Abstract

The goal of this work is to train a neural network which approximates solutions to the Navier-Stokes equations across a region of parameter space, in which the parameters define physical properties such as domain shape and boundary conditions. The contributions of this work are threefold: 1) To demonstrate that neural networks can be efficient aggregators of whole families of parameteric solutions to physical problems, trained using data created with traditional, trusted numerical methods such as finite elements. Advantages include extremely fast evaluation of pressure and velocity at any point in physical and parameter space (asymptotically, ~3 $\mu s$ / query), and data compression (the network requires 99\% less storage space compared to its own training data). 2) To demonstrate that the neural networks can accurately interpolate between finite element solutions in parameter space, allowing them to be instantly queried for pressure and velocity field solutions to problems for which traditional simulations have never been performed. 3) To introduce an active learning algorithm, so that during training, a finite element solver can automatically be queried to obtain additional training data in locations where the neural network's predictions are in most need of improvement, thus autonomously acquiring and efficiently distributing training data throughout parameter space. In addition to the obvious utility of Item 2, above, we demonstrate an application of the network in rapid parameter sweeping, very precisely predicting the degree of narrowing in a tube which would result in a 50\% increase in end-to-end pressure difference at a given flow rate. This capability could have applications in both medical diagnosis of arterial disease, and in computer-aided design.

arXiv comment16 pages, 9 figures; added missing details from author affiliations

References in corpus (14)

• SciPy 1.0--Fundamental Algorithms for Scientific Computing in Python
• Hidden Physics Models: Machine Learning of Nonlinear Partial Differential Equations
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations
• Less is more: sampling chemical space with active learning
• Physics-informed neural networks for inverse problems in nano-optics and metamaterials
• Machine Learning of Linear Differential Equations using Gaussian Processes
• Quantifying total uncertainty in physics-informed neural networks for solving forward and inverse stochastic problems
• Inferring solutions of differential equations using noisy multi-fidelity data
• Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• Physics-informed Neural Networks for Solving Nonlinear Diffusivity and Biot's equations
• Hidden Fluid Mechanics: A Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization Data
• Accelerating Physics-Informed Neural Network Training with Prior Dictionaries

Cited by in corpus (7)

• An AI-based Domain-Decomposition Non-Intrusive Reduced-Order Model for Extended Domains applied to Multiphase Flow in Pipes
• ViscoelasticNet: A physics informed neural network framework for stress discovery and model selection
• Investigation of Compressor Cascade Flow Using Physics- Informed Neural Networks with Adaptive Learning Strategy
• HyperPINN: Learning parameterized differential equations with physics-informed hypernetworks
• Active learning with physics-informed neural networks for optimal sensor placement in deep tunneling through transversely isotropic elastic rocks
• Surrogate models for Rock-Fluid Interaction: A Grid-Size-Invariant Approach
• Physics-Coupled Spatio-Temporal Active Learning for Dynamical Systems