LatticeGraphNet: A two-scale graph neural operator for simulating lattice structures
This provides an efficient surrogate model for evaluating mechanical responses of lattices and structures, which is incremental as it applies existing graph neural operator methods to a specific domain.
The paper tackles the problem of computationally expensive nonlinear finite-element simulations for 3D lattice structures by introducing LatticeGraphNet, a two-scale graph neural operator that serves as a surrogate model. The result is a significant reduction in inference time while maintaining high accuracy for unseen simulations.
This study introduces a two-scale Graph Neural Operator (GNO), namely, LatticeGraphNet (LGN), designed as a surrogate model for costly nonlinear finite-element simulations of three-dimensional latticed parts and structures. LGN has two networks: LGN-i, learning the reduced dynamics of lattices, and LGN-ii, learning the mapping from the reduced representation onto the tetrahedral mesh. LGN can predict deformation for arbitrary lattices, therefore the name operator. Our approach significantly reduces inference time while maintaining high accuracy for unseen simulations, establishing the use of GNOs as efficient surrogate models for evaluating mechanical responses of lattices and structures.