Machine-Learning-Powered, Rapid, Accurate, and Multi-Target Mechanical Metamaterials Inverse Design

Multi-target inverse design, which involves designing multiple targets with different optimization objectives, becomes a key focus in mechanical metamaterials (MMs) design. Specifically, many practical applications impose varying requirements for different sections. For instance, the heel of a sole demands to provide support, while the arch should be comfortable, adequately supportive, and lightweight. However, existing approaches, such as topology optimization, typically focus on optimizing MMs for specific objectives, e.g., high strength. Worse, these approaches are often inaccurate and time-consuming, even just for a single target. In this work, based on graded triply periodic minimal surface (TPMS) architectures, a machine-learning-powered approach is proposed for rapid, accurate, and multi-target MM inverse design by employing a six-parallel pipeline network architecture and utilizing deep networks to map structural parameters to mechanical curves. The most suitable results are selected based on the target curves and other performance requirements, which can be derived from the structural parameters. The approach achieves a normalized root-mean-square error (NRMSE) of 2.49% on the test dataset and outputs corresponding design parameters within seconds, simultaneously meeting multiple targets. Finally, such an approach is demonstrated in designing soles suitable for various gait scenarios and foot deformity treatments.