A physics-constrained neural solver for incompressible flows without labeled data
Organizations: Department of Mechanical Engineering and Materials Science, University of Pittsburgh, Pittsburgh, PA 15261, USA
Abstract
We present a physics-constrained neural solver for incompressible flow that requires neither labeled data nor supervised pretraining. The solver enforces incompressibility and boundary conditions (BCs) to strict tolerances. We attribute the limited Reynolds numbers of existing physics-informed approaches to insufficient enforcement of these constraints, on which conventional finite-difference and finite-volume solvers depend. We therefore formulate incompressible flow as a constrained optimization problem within the physics- and equality-constrained artificial neural network (PECANN) framework: the pressure Poisson residual is minimized subject to the momentum equations, continuity equation, and BCs imposed as equality constraints on the primitive variables, while a conditionally adaptive augmented Lagrangian method enforces each constraint. The pressure Poisson objective proves critical. Across all benchmarks, replacing it with the momentum residual fails to converge to accurate solutions under identical architecture and constraint enforcement, which we attribute to the global elliptic coupling of pressure and velocity that local momentum-residual minimization lacks. For advection-dominated flows, we introduce an adaptive vanishing entropy viscosity that stabilizes training while leaving the converged solution unchanged. The solver predicts lid-driven cavity flow up to Re = 7,500 with centerline velocity profiles matching benchmark data, and is further validated on flow over a backward-facing step at Re = 800, 3D unsteady Beltrami flow, and steady and unsteady flow past a circular cylinder under an inflow-outflow configuration, for which an ablation study identifies admissible outlet BCs for velocity and pressure. From a randomly initialized network and without external perturbations, the solver captures the spontaneous onset of periodic vortex shedding in unsteady cylinder flow.
Figures & tables
| Outcome | ||||||
|---|---|---|---|---|---|---|
| ✓ | ✓ | – | – | Physical | ||
| ✓ | – | ✓ | ✓ | Spurious | ||
| ✓ | ✓ | – | ✓ | Physical | ||
| ✓ | ✓ | ✓ | – | Physical | ||
| ✓ | ✓ | ✓ | ✓ | Physical | ||
| – | ✓ | – | – | Spurious |
| Dennis and Chang [ 41 ] | |||
|---|---|---|---|
| Fornberg [ 42 ] | |||
| He and Doolen [ 43 ] | |||
| Ye et al. [ 44 ] | |||
| Calhoun [ 45 ] | |||
| Linnick and Fasel [ 46 ] |
| Gartling [ 51 ] | 6.100 | 4.850 | 10.480 |
|---|---|---|---|
| Barton [ 53 ] | 5.755 | 4.570 | 10.330 |
| Kim and Moin [ 9 ] | 5.950 | – | – |
| Guj and Stella [ 54 ] | 6.025 | 4.850 | 10.150 |
| Gresho et al. [ 55 ] | 6.100 | 4.860 | 10.490 |
| Keskar and Lyn [ 56 ] | 6.095 | 4.855 | 10.480 |
| NSFnet (VV) | NSFnet (VP) | current work (Eq. 23 ) | |
|---|---|---|---|
| n/a |
Appendix figures & tables6 assets
Supplementary material from the paper’s appendix.
Appendix
Neural PDE Solvers
Neural PDE solvers use trainable models to approximate solutions or solution operators for partial differential equations, often with physical constraints.
See all 299 papers