Physics-informed PointNet: A deep learning solver for steady-state incompressible flows and thermal fields on multiple sets of irregular geometries

Abstract

We present a novel physics-informed deep learning framework for solving steady-state incompressible flow on multiple sets of irregular geometries by incorporating two main elements: using a point-cloud based neural network to capture geometric features of computational domains, and using the mean squared residuals of the governing partial differential equations, boundary conditions, and sparse observations as the loss function of the network to capture the physics. While the solution of the continuity and Navier-Stokes equations is a function of the geometry of the computational domain, current versions of physics-informed neural networks have no mechanism to express this functionally in their outputs, and thus are restricted to obtain the solutions only for one computational domain with each training procedure. Using the proposed framework, three new facilities become available. First, the governing equations are solvable on a set of computational domains containing irregular geometries with high variations with respect to each other but requiring training only once. Second, after training the introduced framework on the set, it is now able to predict the solutions on domains with unseen geometries from seen and unseen categories as well. The former and the latter both lead to savings in computational costs. Finally, all the advantages of the point-cloud based neural network for irregular geometries, already used for supervised learning, are transferred to the proposed physics-informed framework. The effectiveness of our framework is shown through the method of manufactured solutions and thermally-driven flow for forward and inverse problems.

References in corpus (11)

• Physics-Constrained Deep Learning for High-dimensional Surrogate Modeling and Uncertainty Quantification without Labeled Data
• Prediction of Aerodynamic Flow Fields Using Convolutional Neural Networks
• Stiff-PINN: Physics-Informed Neural Network for Stiff Chemical Kinetics
• Physics-informed graph neural Galerkin networks: A unified framework for solving PDE-governed forward and inverse problems
• A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries
• PhyCRNet: Physics-informed Convolutional-Recurrent Network for Solving Spatiotemporal PDEs
• Simulation of multi-species flow and heat transfer using physics-informed neural networks
• Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
• Explore missing flow dynamics by physics-informed deep learning: the parameterised governing systems
• Point-Cloud Deep Learning of Porous Media for Permeability Prediction
• CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

Cited by in corpus (12)

• Transfer learning based physics-informed neural networks for solving inverse problems in engineering structures under different loading scenarios
• Deep Learning in Deterministic Computational Mechanics
• Pre-training strategy for solving evolution equations based on physics-informed neural networks
• Physics-informed MeshGraphNets (PI-MGNs): Neural finite element solvers for non-stationary and nonlinear simulations on arbitrary meshes
• DrivAerNet: A Parametric Car Dataset for Data-Driven Aerodynamic Design and Prediction
• Local neural operator for solving transient partial differential equations on varied domains
• Geometry-aware framework for deep energy method: an application to structural mechanics with hyperelastic materials
• Input convex neural networks: universal approximation theorem and implementation for isotropic polyconvex hyperelastic energies
• Machine learning study to identify collective flow in small and large colliding systems
• DrivAer Transformer: A high-precision and fast prediction method for vehicle aerodynamic drag coefficient based on the DrivAerNet++ dataset
• PIPE: Process Informed Parameter Estimation, a learning based approach to task generalized system identification
• LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks