Intelligent design of mechanical metamaterials: a GCNN-based structural genome database approach

The reciprocal mapping between the geometry and properties of a unit cell is crucial for the intelligent and inverse design of advanced materials and structural systems. Beyond classical homogenization-based numerical methods, this paper presents an efficient and accurate mapping between the geometry and properties of a class of unit cells described by moving morphable components, achieved via a graph convolutional neural network. This leads to a structural genome database (SGD) approach for the intelligent design of mechanical metamaterials. Using the SGD approach, metamaterials exhibiting the Hashin-Shtrikman upper bound of bulk modulus, auxetic behavior and the unimodal property have been created, with design efficiency improved by 3-4 orders of magnitude. Additionally, transfer learning and a small amount of training data allow the SGD to predict non-local behaviors beyond a unit cell, such as optimized unit cells with critical buckling strength enhanced by nearly 200% and a bandgap metamaterial with a relative bandgap width of 51%. Experimentally validated optimized metamaterials demonstrate auxetic behavior and superior buckling resistance. The proposed SGD approach holds promise for the advanced design of multi-scale and multi-physics systems. Combining the explicit topology optimization and graph convolutional neural network, a structural genome database is constructed and provides a unified design toolbox for various mechanical metamaterials.