Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
To model dynamic stress responses in heterogeneous media under impact, this work constructs an aggregate-resolved LS-DYNA dataset across 400 impact simulations and trains a Graph Neural Operator (GNO) to predict mid-plane six-component stress tensor field evolutions. Resolving full-field continuum stress bypasses conventional penetration-depth tracking errors caused by element erosion and target rebound. Evaluated under leave-one-out cross-velocity extrapolation, the autoregressive surrogate executes rollouts in roughly 144 ms, delivering an approximate 4,000x inference speedup over single-core finite element solvers despite an admitted single-step relative L2 error of 0.6977.
Replacing costly aggregate-resolved impact simulations with graph neural operators yields a 4,000x acceleration in predicting dynamic 6-component stress tensors, sidestepping the severe erosion artifacts that compromise standard scalar penetration metrics.
Although the impact resistance of concrete has been studied extensively, a framework linking mesoscale heterogeneity to full-field stress-tensor prediction has been lacking. Data were generated with a full-scale aggregate-resolved LS-DYNA model (projectile diameter 45 mm, mass 2.13 kg, target diameter 500 mm x thickness 200 mm, mesh 10 mm), verified against published penetration experiments (Frew 2006, Hanchak 1992, Forrestal 1996) by configuration similarity. The dataset contains six-component stress-tensor fields on the X-Z mid-plane for 400 cases (4 impact velocities x 100 aggregate seeds). Three contributions are reported. First, case-by-case verification of the terminal penetration state delimited the rest-state validity of penetration depth and anchored reliable observables to rigid-body motion and field-level stress evolution. Second, a field-level graph neural operator surrogate learned the time-varying stress-field evolution and evaluated cross-velocity leave-one-out extrapolation. Third, the full-scale, aggregate-resolved, cross-velocity, per-seed database was established as a reproducible resource. Cases at 100, 135 and 200 m/s still moved at window end (negative velocity, i.e. rebound), and only one 165 m/s case arrested. Penetration depth is therefore not reported as a rest-state scalar except for the single arrested case (69.33 mm); nose-node depth differences were confirmed as numerical artifacts of displacement integration after erosion. The single-step relative L2 error was 0.6977, reported honestly; autoregressive rollout from frame 11 to 39 took about 144 ms, a speedup of about 3.6x10^3 to 4.3x10^3 relative to single-core LS-DYNA, reported as application value. Validation is bounded by configuration similarity and field-level self-consistency; the framework is a simulation-trained decision-support method within the studied parameter space.