An equivariant neural operator for developing nonlocal tensorial constitutive models
From MaRDI portal
(Redirected from Publication:6162914)
Abstract: Developing robust constitutive models is a fundamental and longstanding problem for accelerating the simulation of complicated physics. Machine learning provides promising tools to construct constitutive models based on various calibration data. In this work, we propose a neural operator to develop nonlocal constitutive models for tensorial quantities through a vector-cloud neural network with equivariance (VCNN-e). The VCNN-e respects all the invariance properties desired by constitutive models, faithfully reflects the region of influence in physics, and is applicable to different spatial resolutions. By design, the model guarantees that the predicted tensor is invariant to the frame translation and ordering (permutation) of the neighboring points. Furthermore, it is equivariant to the frame rotation, i.e., the output tensor co-rotates with the coordinate frame. We evaluate the VCNN-e by using it to emulate the Reynolds stress transport model for turbulent flows, which directly computes the Reynolds stress tensor to close the Reynolds-averaged Navier--Stokes (RANS) equations. The evaluation is performed in two situations: (1) emulating the Reynolds stress model through synthetic data generated from the Reynolds stress transport equations with closure models, and (2) predicting the Reynolds stress by learning from data generated from direct numerical simulations. Such a priori evaluations of the proposed network pave the way for developing and calibrating robust and nonlocal, non-equilibrium closure models for the RANS equations.
Recommendations
- Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
- Learning nonlocal constitutive models with neural networks
- Peridynamic neural operators: a data-driven nonlocal constitutive model for complex material responses
- A new family of constitutive artificial neural networks towards automated model discovery
- Learning constitutive relations from indirect observations using deep neural networks
Cites work
- A more general effective-viscosity hypothesis
- Deep Potential: A General Representation of a Many-Body Potential Energy Surface
- Ensemble Kalman method for learning turbulence models from indirect observation data
- Flows over periodic hills of parameterized geometries: a dataset for data-driven turbulence modeling from direct simulations
- Frame Invariance and Scalability of Neural Operators for Partial Differential Equations
- Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
- scientific article; zbMATH DE number 975242 (Why is no real title available?)
- Incompact3d: A powerful tool to tackle turbulence problems with up to O(10⁵) computational cores
- Learning constitutive relations from indirect observations using deep neural networks
- Learning constitutive relations using symmetric positive definite neural networks
- Learning nonlocal constitutive models with neural networks
- Modelling the pressure–strain correlation of turbulence: an invariant dynamical systems approach
- On explicit algebraic stress models for complex turbulent flows
- Progress in the development of a Reynolds-stress turbulence closure
- Representation of stress tensor perturbations with application in machine-learning-assisted turbulence modeling
- Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
- RotEqNet: rotation-equivariant network for fluid systems with symmetric high-order tensors
- Solution of the implicitly discretized fluid flow equations by operator- splitting
- Surrogate modeling for fluid flows based on physics-constrained deep learning without simulation data
- The return to isotropy of homogeneous turbulence
- Turbulent Flows
- Uniformly accurate machine learning-based hydrodynamic models for kinetic equations
Cited in
(5)- RotEqNet: rotation-equivariant network for fluid systems with symmetric high-order tensors
- A data-driven turbulence modeling for the Reynolds stress tensor transport equation
- Variational assimilation of transonic shock-wave boundary-layer interaction using sparse pressure measurements
- CGKN: a deep learning framework for modeling complex dynamical systems and efficient data assimilation
- Scientific machine learning for closure models in multiscale problems: a review
This page was built for publication: An equivariant neural operator for developing nonlocal tensorial constitutive models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6162914)
