Inverting the structure–property map of truss metamaterials by deep learning

Significance

More than a decade of research has been devoted to leveraging the rich mechanical playground of periodically assembled truss metamaterials. The enormous design space of manufacturable unit cells, however, has made the inverse design a challenge: How does one efficiently identify a complex truss that has given target properties? We answer this question by a data-driven method, which instantly (once trained, within milliseconds) generates not one but a variety of truss unit cells, whose effective response closely matches a given (fully anisotropic) stiffness tensor. Moreover, our framework to smoothly transition between different unit cells enables the design of lightweight structures with spatially varying, locally optimized properties, for applications from wave guiding to artificial bone.

Abstract

Inspired by crystallography, the periodic assembly of trusses into architected materials has enjoyed popularity for more than a decade and produced countless cellular structures with beneficial mechanical properties. Despite the successful and steady enrichment of the truss design space, the inverse design has remained a challenge: While predicting effective truss properties is now commonplace, efficiently identifying architectures that have homogeneous or spatially varying target properties has remained a roadblock to applications from lightweight structures to biomimetic implants. To overcome this gap, we propose a deep-learning framework, which combines neural networks with enforced physical constraints, to predict truss architectures with fully tailored anisotropic stiffness. Trained on millions of unit cells, it covers an enormous design space of topologically distinct truss lattices and accurately identifies architectures matching previously unseen stiffness responses. We demonstrate the application to patient-specific bone implants matching clinical stiffness data, and we discuss the extension to spatially graded cellular structures with locally optimal properties.