Accelerating discrete dislocation dynamics simulations with graph neural networks
This work addresses a bottleneck in mesoscale plasticity simulations for materials science, offering a promising acceleration method, though it is incremental as it builds on existing DDD and GNN techniques.
The authors tackled the high computational cost of discrete dislocation dynamics (DDD) simulations by replacing the expensive time-integration with a graph neural network (GNN) model trained on DDD trajectories, demonstrating that the DDD-GNN model is stable and accurately reproduces unseen ground-truth DDD simulation responses for various straining rates and obstacle densities.
Discrete dislocation dynamics (DDD) is a widely employed computational method to study plasticity at the mesoscale that connects the motion of dislocation lines to the macroscopic response of crystalline materials. However, the computational cost of DDD simulations remains a bottleneck that limits its range of applicability. Here, we introduce a new DDD-GNN framework in which the expensive time-integration of dislocation motion is entirely substituted by a graph neural network (GNN) model trained on DDD trajectories. As a first application, we demonstrate the feasibility and potential of our method on a simple yet relevant model of a dislocation line gliding through an array of obstacles. We show that the DDD-GNN model is stable and reproduces very well unseen ground-truth DDD simulation responses for a range of straining rates and obstacle densities, without the need to explicitly compute nodal forces or dislocation mobilities during time-integration. Our approach opens new promising avenues to accelerate DDD simulations and to incorporate more complex dislocation motion behaviors.