FFV-PINN: A Fast Physics-Informed Neural Network with Simplified Finite Volume Discretization and Residual Correction
arXiv:2603.24114 · doi:10.1016/j.cma.2025.118139
Abstract
Physics-informed neural networks (PINNs) have emerged as a major research focus. However, today's PINNs encounter several limitations. Firstly, during the construction of the loss function using automatic differentiation, PINNs often neglect information from neighboring points, which hinders their ability to enforce physical constraints and diminishes their accuracy. Furthermore, issues such as instability and poor convergence persist during PINN training, limiting their applicability to complex fluid dynamics problems. To address these challenges, a fast physics-informed neural network framework that integrates a simplified finite volume method (FVM) and residual correction loss term has been proposed, referred to as Fast Finite Volume PINN (FFV-PINN). FFV-PINN utilizes a simplified FVM discretization for the convection term, with an accompanying improvement in the dispersion and dissipation behavior. Unlike traditional FVM, the FFV-PINN outputs can be simply and directly harnessed to approximate values on control surfaces, thereby simplifying the discretization process. Moreover, a residual correction loss term is introduced to significantly accelerates convergence and improves training efficiency. To validate the performance, we solve a series of challenging problems -- including flow in the two-dimensional steady and unsteady lid-driven cavity, three-dimensional steady lid-driven cavity, backward-facing step flows, and natural convection at high Reynolds number and Rayleigh number. Notably, the FFV-PINN can achieve data-free solutions for the lid-driven cavity flow at Re = 10000 and natural convection at Ra = 1e8 for the first time in PINN literature, even while requiring only 680s and 231s. It further highlights the effectiveness of FFV-PINN in improving both speed and accuracy, marking another step forward in the progression of PINNs as competitive neural PDE solvers.
References in corpus (17)
- Neural Architecture Search with Reinforcement Learning
- CAN-PINN: A Fast Physics-Informed Neural Network Based on Coupled-Automatic-Numerical Differentiation Method
- A two-stage physics-informed neural network method based on conserved quantities and applications in localized wave solutions
- An Expert's Guide to Training Physics-informed Neural Networks
- Optimizing a DIscrete Loss (ODIL) to solve forward and inverse problems for partial differential equations using machine learning tools
- Challenges in Training PINNs: A Loss Landscape Perspective
- PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks
- Hybrid Finite Difference with the Physics-informed Neural Network for solving PDE in complex geometries
- Solution multiplicity and effects of data and eddy viscosity on Navier-Stokes solutions inferred by physics-informed neural networks
- Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
- TSONN: Time-stepping-oriented neural network for solving partial differential equations
- AQ-PINNs: Attention-Enhanced Quantum Physics-Informed Neural Networks for Carbon-Efficient Climate Modeling
- Linear Stability Analysis of Physics-Informed Random Projection Neural Networks for ODEs
- Guaranteeing Conservation Laws with Projection in Physics-Informed Neural Networks
- Finite Volume Physical Informed Neural Network (FV-PINN) with Reduced Derivative Order for Incompressible Flows
- Coupled Integral PINN for Discontinuity
- Unified theoretical guarantees for stability, consistency, and convergence in neural PDE solvers from non-IID data to physics-informed networks