The rapid development of additive manufacturing technologies has enabled the fabrication of truss metamaterials, i.e., a novel class of lightweight-yet-strong materials with engineered complex hierarchical structures. Manipulating the architecture over chemical composition dramatically expands the achievable materials design space, allowing to largely control the mechanical response of metamaterials. Despite the great advances made in this area, designing three-dimensional (3D) truss metamaterials under complex or extreme conditions with programmable response is still a challenge. We are investigating a paradigm to design 3D truss metamaterials with complex programmable mechanical responses both under quasi-static and dynamic loading based on graph neural networks (GNNs). By combining the ability of our GNN-based model to accurately predict the mechanical response across multiple orders of magnitude and the explorative power of deep reinforcement learning, our goal is to inverse design truss metamaterials for compressive loading up to 30 % of strain and dynamic transmissibility with desired attenuation gaps, opening the way for full materials design freedom.
Project is currently funded by: Federal