Data-efficient inverse design of spinodoid metamaterials

TL;DR

This paper introduces a data-efficient neural network surrogate model for inverse design of spinodoid metamaterials, enabling multi-objective optimization with significantly less data than previous methods.

Contribution

The authors develop a neural network surrogate that inherently satisfies permutation equivariance, reducing data requirements for inverse design of complex metamaterials.

Findings

Achieves accurate inverse design with only 75 data points

Surrogate model is differentiable and suitable for gradient-based optimization

Demonstrates successful multi-objective inverse design tasks

Abstract

We create an data-efficient and accurate surrogate model for structure-property linkages of spinodoid metamaterials with only 75 data points -- far fewer than the several thousands used in prior works -- and demonstrate its use in multi-objective inverse design. The inverse problem of finding a material microstructure that leads to given bulk properties is of great interest in mechanics and materials science. These inverse design tasks often require a large dataset, which can become unaffordable when considering material behavior that requires more expensive simulations or experiments. We generate a data-efficient surrogate for the mapping between the characteristics of the local material structure and the effective elasticity tensor and use it to inversely design structures with multiple objectives simultaneously. The presented neural network-based surrogate model achieves its data efficiency by inherently satisfying certain requirements, such as equivariance with respect to permutations of structure parameters, which avoids having to learn them from data. The resulting surrogate of the forward model is differentiable, allowing its direct use in gradient-based optimization for the inverse design problem. We demonstrate in three inverse design tasks of varying complexity that this approach yields reliable results while requiring significantly less training data than previous approaches based on neural-network surrogates. This paves the way for inverse design involving nonlinear mechanical behavior, where data efficiency is currently the limiting factor.