A neural network that uses potential-flow-derived features as inputs can predict nearby steady flows from one high-fidelity simulation and warm-start a CFD solver.
Abbott and Albert E
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.flu-dyn 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multi-Fidelity Machine Learning Applied to Steady Fluid Flows
A neural network that uses potential-flow-derived features as inputs can predict nearby steady flows from one high-fidelity simulation and warm-start a CFD solver.