REVIEW 3 cited by
Physics-informed neural networks for inverse problems in supersonic flows
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Physics-informed neural networks for inverse problems in supersonic flows
read the original abstract
Accurate solutions to inverse supersonic compressible flow problems are often required for designing specialized aerospace vehicles. In particular, we consider the problem where we have data available for density gradients from Schlieren photography as well as data at the inflow and part of wall boundaries. These inverse problems are notoriously difficult and traditional methods may not be adequate to solve such ill-posed inverse problems. To this end, we employ the physics-informed neural networks (PINNs) and its extended version, extended PINNs (XPINNs), where domain decomposition allows deploying locally powerful neural networks in each subdomain, which can provide additional expressivity in subdomains, where a complex solution is expected. Apart from the governing compressible Euler equations, we also enforce the entropy conditions in order to obtain viscosity solutions. Moreover, we enforce positivity conditions on density and pressure. We consider inverse problems involving two-dimensional expansion waves, two-dimensional oblique and bow shock waves. We compare solutions obtained by PINNs and XPINNs and invoke some theoretical results that can be used to decide on the generalization errors of the two methods.
Forward citations
Cited by 3 Pith papers
-
A fast Physics-Informed Neural Networks based approach to the 2D design of turbine blades
A progressive Euler-PINN with geometry-aware dynamic loss weighting delivers CFD-comparable pressure and velocity fields for ten NACA6 blade variants across thirty subsonic points at lower computational cost than trad...
-
Sampling Distributions as Regularization in Learned Inverse Problems
Sampling distributions for generating synthetic data in neural network inverse problem solvers define an implicit regularization operator because the learned operator minimizes empirical risk and conditional expectati...
-
A fast Physics-Informed Neural Networks based approach to the 2D design of turbine blades
A progressive Euler-PINN with geometry-aware loss weighting achieves CFD-comparable pressure and velocity fields for ten NACA6 blades across 30 operating points while cutting computational cost for family-wide screening.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.