AI RESEARCH
PVD-ONet: A Multi-scale Neural Operator Method for Singularly Perturbed Boundary Layer Problems
arXiv CS.LG
•
ArXi:2507.21437v2 Announce Type: replace Physics-informed neural networks and Physics-informed DeepONet excel in solving partial differential equations; however, they often fail to converge for singularly perturbed problems. To address this, we propose two novel frameworks, Prandtl-Van Dyke neural network(PVD-Net) and its operator learning extension Prandtl-Van Dyke Deep Operator Network (PVD-ONet), which rely solely on governing equations without data.