Qizhe Lin

Multi-Fidelity Physics-Informed Graph Neural Networks for 3D Gear Contact Stress Prediction Under Extreme Gradients

This study develops a multi-fidelity physics-informed graph surrogate combining a coarse learning graph, peak-sensitive KDTree projection, gated message passing, and a regularized least-squares finite-difference equilibrium residual that outperforms distance-weighted averaging at one fixed graph resolution.