Neural Network Layers for Prediction of Positive Definite Elastic Stiffness Tensors

03/25/2022
by   Charles F Jekel, et al.
0

Machine learning models can be used to predict physical quantities like homogenized elasticity stiffness tensors, which must always be symmetric positive definite (SPD) based on conservation arguments. Two datasets of homogenized elasticity tensors of lattice materials are presented as examples, where it is desired to obtain models that map unit cell geometric and material parameters to their homogenized stiffness. Fitting a model to SPD data does not guarantee the model's predictions will remain SPD. Existing Cholsesky factorization and Eigendecomposition schemes are abstracted in this work as transformation layers which enforce the SPD condition. These layers can be included in many popular machine learning models to enforce SPD behavior. This work investigates the effects that different positivity functions have on the layers and how their inclusion affects model accuracy. Commonly used models are considered, including polynomials, radial basis functions, and neural networks. Ultimately it is shown that a single SPD layer improves the model's average prediction accuracy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/16/2021

Stochastic modelling of symmetric positive-definite material tensors

Spatial symmetries and invariances play an important role in the descrip...
research
11/28/2022

Structure-Preserving Invariant Interpolation Schemes for Invertible Second-Order Tensors

Tensor interpolation is an essential step for tensor data analysis in va...
research
06/22/2023

StrainNet: Predicting crystal structure elastic properties using SE(3)-equivariant graph neural networks

Accurately predicting the elastic properties of crystalline solids is vi...
research
06/25/2020

Geometric Prediction: Moving Beyond Scalars

Many quantities we are interested in predicting are geometric tensors; w...
research
01/15/2022

Edge-based Tensor prediction via graph neural networks

Message-passing neural networks (MPNN) have shown extremely high efficie...
research
09/05/2022

Free material optimization of thermal conductivity tensors with asymmetric components

Free Material Optimization (FMO), a branch of topology optimization, in ...

Please sign up or login with your details

Forgot password? Click here to reset