Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
arXiv:2103.06685 · doi:10.1016/j.cma.2021.114211
Abstract
Constitutive models are widely used for modeling complex systems in science and engineering, where first-principle-based, well-resolved simulations are often prohibitively expensive. For example, in fluid dynamics, constitutive models are required to describe nonlocal, unresolved physics such as turbulence and laminar-turbulent transition. However, traditional constitutive models based on partial differential equations (PDEs) often lack robustness and are too rigid to accommodate diverse calibration datasets. We propose a frame-independent, nonlocal constitutive model based on a vector-cloud neural network that can be learned with data. The model predicts the closure variable at a point based on the flow information in its neighborhood. Such nonlocal information is represented by a group of points, each having a feature vector attached to it, and thus the input is referred to as vector cloud. The cloud is mapped to the closure variable through a frame-independent neural network, invariant both to coordinate translation and rotation and to the ordering of points in the cloud. As such, the network can deal with any number of arbitrarily arranged grid points and thus is suitable for unstructured meshes in fluid simulations. The merits of the proposed network are demonstrated for scalar transport PDEs on a family of parameterized periodic hill geometries. The vector-cloud neural network is a promising tool not only as nonlocal constitutive models and but also as general surrogate models for PDEs on irregular domains.
References in corpus (27)
- On representing chemical environments
- Deep Potential Molecular Dynamics: a scalable model with the accuracy of quantum mechanics
- Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
- Data-driven computational mechanics
- A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data
- PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network
- A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
- Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
- Thermodynamics-based Artificial Neural Networks for constitutive modeling
- Deep Potential: a general representation of a many-body potential energy surface
- Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression
- DeePCG: constructing coarse-grained models via deep neural networks
- Learning Constitutive Relations from Indirect Observations Using Deep Neural Networks
- Learning Constitutive Relations using Symmetric Positive Definite Neural Networks
- Multipole Graph Neural Operator for Parametric Partial Differential Equations
- Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
- Neural Operator: Graph Kernel Network for Partial Differential Equations
- Raman Spectrum and Polarizability of Liquid Water from Deep Neural Networks
- Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
- DeepCFD: Efficient Steady-State Laminar Flow Approximation with Deep Convolutional Neural Networks
- Turbulence closure modeling with data-driven techniques: physical compatibility and consistency considerations
- Learning nonlocal constitutive models with neural networks
- Physics-Informed Echo State Networks
- Machine Learning Surrogate Models for Landau Fluid Closure
- Pushing the limit of molecular dynamics with ab initio accuracy to 100 million atoms with machine learning
- Integrating Machine Learning with Physics-Based Modeling
- Short- and long-term prediction of a chaotic flow: A physics-constrained reservoir computing approach