HomoGenius: a Foundation Model of Homogenization for Rapid Prediction of Effective Mechanical Properties using Neural Operators
- URL: http://arxiv.org/abs/2404.07943v1
- Date: Mon, 18 Mar 2024 06:47:35 GMT
- Title: HomoGenius: a Foundation Model of Homogenization for Rapid Prediction of Effective Mechanical Properties using Neural Operators
- Authors: Yizheng Wang, Xiang Li, Ziming Yan, Yuqing Du, Jinshuai Bai, Bokai Liu, Timon Rabczuk, Yinghua Liu,
- Abstract summary: Homogenization is an essential tool for studying multiscale physical phenomena.
We propose a numerical homogenization model based on operator learning: HomoGenius.
The proposed model can quickly provide homogenization results for arbitrary geometries, materials, and resolutions.
- Score: 12.845932824311182
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Homogenization is an essential tool for studying multiscale physical phenomena. However, traditional numerical homogenization, heavily reliant on finite element analysis, requires extensive computation costs, particularly in handling complex geometries, materials, and high-resolution problems. To address these limitations, we propose a numerical homogenization model based on operator learning: HomoGenius. The proposed model can quickly provide homogenization results for arbitrary geometries, materials, and resolutions, increasing the efficiency by a factor of 80 compared to traditional numerical homogenization methods. We validate effectiveness of our model in predicting the effective elastic modulus on periodic materials (TPMS: Triply Periodic Minimal Surface), including complex geometries, various Poisson's ratios and elastic modulus, and different resolutions for training and testing. The results show that our model possesses high precision, super efficiency, and learning capability.
Related papers
- A Multi-Grained Symmetric Differential Equation Model for Learning
Protein-Ligand Binding Dynamics [74.93549765488103]
In drug discovery, molecular dynamics simulation provides a powerful tool for predicting binding affinities, estimating transport properties, and exploring pocket sites.
We propose NeuralMD, the first machine learning surrogate that can facilitate numerical MD and provide accurate simulations in protein-ligand binding.
We show the efficiency and effectiveness of NeuralMD, with a 2000$times$ speedup over standard numerical MD simulation and outperforming all other ML approaches by up to 80% under the stability metric.
arXiv Detail & Related papers (2024-01-26T09:35:17Z) - Discovering Interpretable Physical Models using Symbolic Regression and
Discrete Exterior Calculus [55.2480439325792]
We propose a framework that combines Symbolic Regression (SR) and Discrete Exterior Calculus (DEC) for the automated discovery of physical models.
DEC provides building blocks for the discrete analogue of field theories, which are beyond the state-of-the-art applications of SR to physical problems.
We prove the effectiveness of our methodology by re-discovering three models of Continuum Physics from synthetic experimental data.
arXiv Detail & Related papers (2023-10-10T13:23:05Z) - Generalized Neural Closure Models with Interpretability [28.269731698116257]
We develop a novel and versatile methodology of unified neural partial delay differential equations.
We augment existing/low-fidelity dynamical models directly in their partial differential equation (PDE) forms with both Markovian and non-Markovian neural network (NN) closure parameterizations.
We demonstrate the new generalized neural closure models (gnCMs) framework using four sets of experiments based on advecting nonlinear waves, shocks, and ocean acidification models.
arXiv Detail & Related papers (2023-01-15T21:57:43Z) - Message Passing Neural PDE Solvers [60.77761603258397]
We build a neural message passing solver, replacing allally designed components in the graph with backprop-optimized neural function approximators.
We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes.
We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
arXiv Detail & Related papers (2022-02-07T17:47:46Z) - Equivariant vector field network for many-body system modeling [65.22203086172019]
Equivariant Vector Field Network (EVFN) is built on a novel equivariant basis and the associated scalarization and vectorization layers.
We evaluate our method on predicting trajectories of simulated Newton mechanics systems with both full and partially observed data.
arXiv Detail & Related papers (2021-10-26T14:26:25Z) - A deep learning driven pseudospectral PCE based FFT homogenization
algorithm for complex microstructures [68.8204255655161]
It is shown that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches.
It is shown, that the proposed method is able to predict central moments of interest while being magnitudes faster to evaluate than traditional approaches.
arXiv Detail & Related papers (2021-10-26T07:02:14Z) - Hybridized Methods for Quantum Simulation in the Interaction Picture [69.02115180674885]
We provide a framework that allows different simulation methods to be hybridized and thereby improve performance for interaction picture simulations.
Physical applications of these hybridized methods yield a gate complexity scaling as $log2 Lambda$ in the electric cutoff.
For the general problem of Hamiltonian simulation subject to dynamical constraints, these methods yield a query complexity independent of the penalty parameter $lambda$ used to impose an energy cost.
arXiv Detail & Related papers (2021-09-07T20:01:22Z) - Thermodynamics-based Artificial Neural Networks (TANN) for multiscale
modeling of materials with inelastic microstructure [0.0]
Multiscale, homogenization approaches are often used for performing reliable, accurate predictions of the macroscopic mechanical behavior of inelastic materials.
Data-driven approaches based on deep learning have risen as a promising alternative to replace ad-hoc laws and speed-up numerical methods.
Here, we propose Thermodynamics-based Artificial Neural Networks (TANN) for the modeling of mechanical materials with inelastic and complex microstructure.
arXiv Detail & Related papers (2021-08-30T11:50:38Z) - A data-driven peridynamic continuum model for upscaling molecular
dynamics [3.1196544696082613]
We propose a learning framework to extract, from molecular dynamics data, an optimal Linear Peridynamic Solid model.
We provide sufficient well-posedness conditions for discretized LPS models with sign-changing influence functions.
This framework guarantees that the resulting model is mathematically well-posed, physically consistent, and that it generalizes well to settings that are different from the ones used during training.
arXiv Detail & Related papers (2021-08-04T07:07:47Z) - Polyconvex anisotropic hyperelasticity with neural networks [1.7616042687330642]
convex machine learning based models for finite deformations are proposed.
The models are calibrated with highly challenging simulation data of cubic lattice metamaterials.
The data for the data approach is based on mechanical considerations and does not require additional experimental or simulation capabilities.
arXiv Detail & Related papers (2021-06-20T15:33:31Z) - Heterogeneous Tensor Mixture Models in High Dimensions [5.656785831541303]
We consider the problem of jointly introducing a flexible high-dimensional tensor mixture model with heterogeneous covariances.
We show that our method converges geometrically to a neighborhood that is statistical of the true parameter.
Our analysis identifies important brain regions for diagnosis in an autism spectrum disorder.
arXiv Detail & Related papers (2021-04-15T21:06:16Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.