Exploring the structure-property relations of thin-walled, 2D extruded lattices using neural networks
It addresses the need for efficient design optimization in materials science, particularly for energy-absorbing structures, but is incremental as it builds on existing neural network and simulation methods.
This paper tackled the problem of predicting mechanical properties like energy absorption for thin-walled lattices under compression by developing a neural network model that uses an autoencoder to encode cross-sectional images, achieving accurate predictions within a design system and extending to new designs via transfer learning.
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.