Deep Learning for Size‐Agnostic Inverse Design of Random‐Network 3D Printed Mechanical Metamaterials

Abstract

Practical applications of mechanical metamaterials often involve solving inverse problems where the objective is to find the (multiple) microarchitectures that give rise to a given set of properties. The limited resolution of additive manufacturing techniques often requires solving such inverse problems for specific sizes. One should, therefore, find multiple microarchitectural designs that exhibit the desired properties for a specimen with given dimensions. Moreover, the candidate microarchitectures should be resistant to fatigue and fracture, meaning that peak stresses should be minimized as well. Such a multi‐objective inverse design problem is formidably difficult to solve but its solution is the key to real‐world applications of mechanical metamaterials. Here, we propose a modular approach titled “Deep‐DRAM” that combines four decoupled models, including two deep learning models (DLM), a deep generative model (DGM) based on conditional variational autoencoders (CVAE), and direct finite element (FE) simulations. Deep‐DRAM (deep learning for the design of random‐network metamaterials) integrates these models into a unified framework capable of finding many solutions to the multi‐objective inverse design problem posed here. All microarchitectural designs are based on random‐network (RN) unit cells with ordered lattices. The first DLM predicts the anisotropic elastic properties of RN unit cells given their microarchitectural design while the other one does the same with the additional input of specimen dimensions. The DGM generates unit cells that give rise to a given set of elastic properties. The integrated framework first introduces the desired elastic properties to the DGM, which returns a set of candidate designs. The candidate designs, together with the target specimen dimensions are then passed to the DLM which predicts their actual elastic properties considering the specimen size. After a filtering step based on the closeness of the actual properties to the desired ones, the last step uses direct FE simulations to identify the designs with the minimum peak stresses. Using an extensive set of simulations as well as experiments performed on 3D printed specimens, we demonstrate that: 1) the predictions of the deep learning models are in agreement with FE simulations and experimental observations, 2) an enlarged envelope of achievable elastic properties (including such rare combinations as double‐auxetic behavior and high stiffness) is realized using the proposed approach, and 3) the proposed framework can provide many solutions to the multi‐objective inverse design problem posed here.This article is protected by copyright. All rights reserved