Machine learning generative models for automatic design of multi-material 3D printed composite solids
| Autor: | Yigit Menguc, Thomas J. Wallin, Tianju Xue, Maurizio M. Chiaramonte, Sigrid Adriaenssens |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
Design flow Bioengineering 02 engineering and technology 010402 general chemistry Machine learning computer.software_genre 01 natural sciences Chemical Engineering (miscellaneous) Representation (mathematics) Engineering (miscellaneous) business.industry Mechanical Engineering Bayesian optimization Metamaterial 021001 nanoscience & nanotechnology Autoencoder 0104 chemical sciences Generative model Geometric design Mechanics of Materials Representative elementary volume Artificial intelligence 0210 nano-technology business computer |
| Zdroj: | Extreme Mechanics Letters. 41:100992 |
| ISSN: | 2352-4316 |
| Popis: | Mechanical metamaterials are artificial structures that exhibit unusual mechanical properties at the macroscopic level due to architected geometric design at the microscopic level. With rapid advancement of multi-material 3D printing techniques, it is possible to design mechanical metamaterials by varying spatial distributions of different base materials within a representative volume element (RVE), which is then periodically arranged into a lattice structure. The design problem is challenging, however, considering the wide design space of potentially infinitely many configurations of multi-material RVEs. We propose an optimization framework that automates the design flow. We adopt variational autoencoder (VAE), a machine learning generative model to learn a latent, reduced representation of a given RVE configuration. The reduced design space allows to perform Bayesian optimization (BayesOpt), a sequential optimization strategy, for the multi-material design problems. In this work, we select two base materials with distinct elastic moduli and use the proposed optimization scheme to design a composite solid that achieves a prescribed set of macroscopic elastic moduli. We fabricated optimal samples with multi-material 3D printing and performed experimental validation, showing that the optimization framework is reliable. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect