15 papers
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…
High-Fidelity Reconstruction of Charge Boundary Layers and Sharp Interfaces in Electro-Thermal-Convective Flows via Residual-Attention PINNs
Baitong Zhou, Ze Tao, Ke Xu +2
Accurate reconstruction of localized extreme structures remains a critical bottleneck in the physics-informed modeling of electro-thermal-convective flows. Although conventional ph…
LNN-PINN: A Unified Physics-Only Training Framework with Liquid Residual Blocks
Ze Tao, Hanxuan Wang, Fujun Liu
Physics-informed neural networks (PINNs) have attracted considerable attention for their ability to integrate partial differential equation priors into deep learning frameworks; ho…
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-…
Bias Inheritance in Neural-Symbolic Discovery of Constitutive Closures Under Function-Class Mismatch
Hanbing Liang, Ze Tao, Fujun Liu
We investigate the data-driven discovery of constitutive closures in nonlinear reaction-diffusion systems with known governing PDE structures. Our objective is to robustly recover…
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…