Designing functional materials requires a deep search through multidimensional spaces for system parameters that yield desirable material properties. For cases where conventional parameter sweeps or trial-and-error sampling are impractical, inverse methods that frame design as a constrained optimization problem present an attractive alternative. However, even efficient algorithms require time- and resource-intensive characterization of material properties many times during optimization, imposing a design bottleneck. Approaches that incorporate machine learning can help address this limitation and accelerate the discovery of materials with targeted properties. In this article, we review how to leverage machine learning to reduce dimensionality in order to effectively explore design space, accelerate property evaluation, and generate unconventional material structures with optimal properties. We also discuss promising future directions, including integration of machine learning into multiple stages of a design algorithm and interpretation of machine learning models to understand how design parameters relate to material properties. Expected final online publication date for the Annual Review of Chemical and Biomolecular Engineering, Volume 13 is October 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

/pdf/machine-learning-assisted-design-of-material-properties-25k446u6.pdf

Machine Learning-Assisted Design of Material Properties.

The kinematic and isotropic hardening behavior was investigated for high and medium entropy alloys with a single-phase face-centered cubic (FCC) structure. The cross-slip associated with screw dislocations in FCC structures is strongly influenced by local fluctuations in the spatial distribution of different atom species. The local atomic arrangements inhibit the movement of Shockley partial dislocations during plastic deformation, thereby lowering the probability of cross-slip and generating a higher back-stress. This study used a solid-solution induced back-stress model, which combines nonlinear kinematic and isotropic hardening, to investigate the effects of dislocation forest stress and back-stress in a non-equiatomic Cr12Fe42Mn24Ni22 medium entropy alloy. Based on the experimental results, numerical simulations by the finite element method were performed to validate this modeling approach. 

Solid solution induced back-stress in multi-principal element alloys: Experiment and modeling

Mechanical performance of zirconia-silica bilayer coating on aluminum alloys with varying porosities: Deep learning and microstructure-based FEM

This paper investigates the structure-property relations of thin-walled lattices under dynamic longitudinal compression, characterized by their cross-sections and heights. These relations elucidate the interactions of different geometric features of a design on mechanical response, including energy absorption. We proposed a combinatorial, key-based design system to generate different lattice designs and used the finite element method to simulate their response with the Johnson-Cook material model. Using an autoencoder, we encoded the cross-sectional images of the lattices into latent design feature vectors, which were supplied to the neural network model to generate predictions. The trained models can accurately predict lattice energy absorption curves in the key-based design system and can be extended to new designs outside of the system via transfer learning. 

/pdf/exploring-the-structure-property-relations-of-thin-walled-2d-2ua87bks.pdf

Hwan Gyo Jung

Papers

Exploration of optimal microstructure and mechanical properties in continuous microstructure space using a variational autoencoder