5 papers · 1 filter
Spatio-Temporal Uncertainty-Modulated Physics-Informed Neural Networks for Solving Hyperbolic Conservation Laws with Strong Shocks
Darui Zhao, Ze Tao, Fujun Liu
Physics-Informed Neural Networks (PINNs) frequently encounter difficulties in accurately resolving shock waves within high-speed compressible flows, a failure largely attributed to…
LSTM-PINN for Steady-State Electrothermal Transport: Preserving Multi-Field Consis tency in Strongly Coupled Heat and Fluid Flow
Yuqing Zhou, Ze Tao, Hanxuan Wang +1
Steady-state electrothermal systems involve strongly coupled heat transfer, fluid flow, and electric-potential transport, creating severe numerical challenges for standard physics-…
PICS: A Partition-of-unity Information-geometric Certified Solver for Coupled Partial Differential Equations
Ze Tao, Hongfu Zhou, Hanbing Liang +1
Coupled partial differential equations underpin a wide range of multiphysics systems, yet existing neural PDE solvers still struggle to resolve localized high-risk regions and ofte…
A Residual-Attention Physics-Informed Neural Network for Irregular Interfaces and Multi-Peak Transport Fields
Baitong Zhou, Ze Tao, Fujun Liu +1
In complex engineering systems such as electro-thermal-fluid coupling, rapid and accurate prediction of multi-physics fields is essential for advanced applications like digital twi…
A Unified Benchmark Study of Shock-Like Problems in Two-Dimensional Steady Electrohydrodynamic Flow Based on LSTM-PINN
Chao Lin, Ze Tao, Fujun Liu
Accurately resolving steady electrohydrodynamic (EHD) flows presents a formidable computational challenge due to the strong nonlinear coupling between charged-particle density, vel…