Combining non-linear structural modeling and machine learning for tensile behavior of multi-layered randomized architected material

Architected materials allow engineers to design and develop materials with desired properties through the interplay of geometry and provide an opportunity to investigate the behavior of micro-scale structures at the macro-scale. Multi-layered Randomized Architected Material (MLRAM), inspired by polymeric structures, has the potential to act as damage detection indicators in highly redundant structures such as tensegrity structures by incorporating them into tension members of a structure. The behavior is analyzed based on the parameters, coordination number and percentage density of Long Links. This paper presents a computational model that captures the tensile behavior of this proposed architected material using a non-linear finite element method. A framework is created that captures the progressive failure of the links of MLRAM. The variation in the tensile properties is analyzed with respect to its parameters. Results show that the variation of stiffness and peak tensile capacity decreases with an increase in coordination number and percentage density of Long Links. Machine learning algorithms and artificial neural networks are evaluated to propose models that can predict the tensile properties of architected materials given their geometrical parameters.