Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex Boundary

Wei Li (National University of Singapore) · Guoqing Wang (University of Electronic Science and Technology of China) · Tianyu Li (Fudan University) · ChuYu Zhou (School of Physics, Northwest University, Xi’an 710127, China) · Chenxi Lan (University of Electronic Science and Technology of China) · Rongyu Du (University of Electronic Science and Technology of China) · Guoguo Xin (Northwest University Xi'an) · Xun Liu (Beijing Institute of Space Mechanics and Electricity) · Hangzhou Yang (Northwest University Xi'an)

2d blocked cavity flow2d cylinder wake flowaccurate solutionsbenchmark scenarios boundary conditionsboundary-constrained mechanismcomprehensive experimentsdistance metric networkhybrid boundary pinninterior regionsnavier-stokes equationspartial differential equations physics-informed neural networkspinn-based approachespretrained networkstate-of-the-art performance

Physics-informed neural networks (PINN) have achieved notable success in solving partial differential equations (PDE), yet solving the Navier-Stokes equations (NSE) with complex boundary conditions remains a challenging task. In this paper, we introduce a novel Hybrid Boundary PINN (HB-PINN) method that combines a pretrained network for efficient initialization with a boundary-constrained mechanism. The HB-PINN method features a primary network focused on inner domain points and a distance metric network that enhances predictions at the boundaries, ensuring accurate solutions for both boundary and interior regions. Comprehensive experiments have been conducted on the NSE under complex boundary conditions, including the 2D cylinder wake flow and the 2D blocked cavity flow with a segmented inlet. The proposed method achieves state-of-the-art (SOTA) performance on these benchmark scenarios, demonstrating significantly improved accuracy over existing PINN-based approaches.