An FEA surrogate model with Boundary Oriented Graph Embedding approach

08/30/2021
by   XingYu Fu, et al.
5

In this work, we present a Boundary Oriented Graph Embedding (BOGE) approach for the Graph Neural Network (GNN) to serve as a general surrogate model for regressing physical fields and solving boundary value problems. Providing shortcuts for both boundary elements and local neighbor elements, the BOGE approach can embed structured mesh elements into the graph and performs an efficient regression on large-scale triangular-mesh-based FEA results, which cannot be realized by other machine-learning-based surrogate methods. Focusing on the cantilever beam problem, our BOGE approach cannot only fit the distribution of stress fields but also regresses the topological optimization results, which show its potential of realizing abstract decision-making design process. The BOGE approach with 3-layer DeepGCN model achieves the regression with MSE of 0.011706 (2.41% MAPE) for stress field prediction and 0.002735 MSE (with 1.58% elements having error larger than 0.01) for topological optimization. The overall concept of the BOGE approach paves the way for a general and efficient deep-learning-based FEA simulator that will benefit both industry and design-related areas.

READ FULL TEXT

page 2

page 11

page 13

page 16

page 17

research
07/25/2023

Multi-GPU Approach for Training of Graph ML Models on large CFD Meshes

Mesh-based numerical solvers are an important part in many design tool c...
research
06/16/2023

Learning CO_2 plume migration in faulted reservoirs with Graph Neural Networks

Deep-learning-based surrogate models provide an efficient complement to ...
research
06/06/2022

Deep Learning-based FEA surrogate for sub-sea pressure vessel

During the design process of an autonomous underwater vehicle (AUV), the...
research
03/20/2022

An Adaptive and Scalable ANN-based Model-Order-Reduction Method for Large-Scale TO Designs

Topology Optimization (TO) provides a systematic approach for obtaining ...
research
11/10/2020

Topology of Frame Field Design for Hex Meshing

In the past decade frame fields have emerged as a promising approach for...
research
02/17/2023

SE(3) symmetry lets graph neural networks learn arterial velocity estimation from small datasets

Hemodynamic velocity fields in coronary arteries could be the basis of v...
research
06/09/2023

Multiscale modeling of dislocations: Combining peridynamics with gradient elasticity

Modeling dislocations is an inherently multiscale problem as one needs t...

Please sign up or login with your details

Forgot password? Click here to reset