Iterated learning and multiscale modeling of history-dependent architectured metamaterials

TL;DR

This paper presents an iterative neural network modeling approach for history-dependent architectured metamaterials, demonstrating convergence to accurate, transferable surrogates with minimal data through transfer learning and large-scale simulation feedback.

Contribution

It introduces an iterative transfer learning method for neural network surrogates that efficiently models history-dependent metamaterials, improving accuracy and transferability.

Findings

Iterative training enhances surrogate accuracy.

Transfer learning reduces data requirements.

Method achieves convergence to high-fidelity models.

Abstract

Neural network based models have emerged as a powerful tool in multiscale modeling of materials. One promising approach is to use a neural network based model, trained using data generated from repeated solution of an expensive small scale model, as a surrogate for the small scale model in application scale simulations. Such approaches have been shown to have the potential accuracy of concurrent multiscale methods like FE2, but at the cost comparable to empirical methods like classical constitutive models or parameter passing. A key question is to understand how much and what kind of data is necessary to obtain an accurate surrogate. This paper examines this question for history dependent elastic-plastic behavior of an architected metamaterial modeled as a truss. We introduce an iterative approach where we use the rich arbitrary class of trajectories to train an initial model, but then iteratively update the class of trajectories with those that arise in large scale simulation and use transfer learning to update the model. We show that such an approach converges to a highly accurate surrogate, and one that is transferable.