Learned Warm Starts for Steady Transonic RANS Simulations of Wing and Aircraft Configurations
Abstract
Neural surrogates can accelerate many-query aerodynamic analyses, but their standalone predictions may be insufficiently accurate or robust to support reliable design evaluations. We develop a learned warm-start formulation that predicts mean-flow and turbulence fields directly on native CFD meshes for subsequent correction by the RANS solver. A common architecture and objective structure are used across subcritical and transonic flows, including challenging conditions with shock-induced separation. A condition-modulated Transolver combines Fourier and wall features with target-gated regularization, a Sobolev-type loss, adaptive loss weighting and sampled training. Prediction requires no preliminary flow solution, and training requires no solver-residual evaluation. Extensive 3D CFD evaluations on SuperWing, the NASA Common Research Model (CRM) and DLR-F6 assess geometric and operating-condition generalization, including interpolation, extrapolation and cross-mesh deployment, using Spalart-Allmaras and k-ω SST closures on million-cell meshes. Unseen nominal cases achieve geometric-mean iteration speed-ups of approximately $2−4\times$ under a common convergence criterion based on cold-run aerodynamic coefficients. On CRM, learned initialization provides greater aggregate acceleration than nearest-condition restarts using the same solution library. Resolution invariance enables direct deployment of coarse-mesh models on finer meshes without retraining, solution interpolation or target-condition coarse solves. Including data generation and training, estimated campaign speed-ups reach $2.1−2.3\times$. No warm run diverges; fewer than 2% fail to satisfy the cold-reference convergence criterion. These results support learned initialization for repeated aerodynamic analyses, while highlighting initialization sensitivity near separation as a remaining limitation.
Related
- Mechanisms of transonic buffet over supercritical airfoils revealed by direct numerical simulations
- A Transferable Machine-Learned Potential Enabling Large-Scale Copper-Carbon Simulations from Equilibrium to Extreme Conditions
- Trainable, self-verifying variational quantum eigensolver using adiabatic warm starts
- Phase Reduction Analysis of Transonic Buffet
- Transfer learning in bayesian optimization for aircraft design
BibTeX
@misc{zafar2026learned,
title = {{Learned Warm Starts for Steady Transonic RANS Simulations of Wing and Aircraft Configurations}},
author = {Muhammad Irfan Zafar and Saleh Abuhanieh and Şahin Yiğit},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.01240},
eprint = {2611.01240},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.01240},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Learned Warm Starts for Steady Transonic RANS Simulations of Wing and Aircraft Configurations
AU - Muhammad Irfan Zafar
AU - Saleh Abuhanieh
AU - Şahin Yiğit
PY - 2026
DA - 2026/11/01
PB - arXiv
DO - 10.48550/arxiv.2611.01240
UR - https://arxiv.org/abs/2611.01240
AB - Neural surrogates can accelerate many-query aerodynamic analyses, but their standalone predictions may be insufficiently accurate or robust to support reliable design evaluations. We develop a learned warm-start formulation that predicts mean-flow and turbulence fields directly on native CFD meshes for subsequent correction by the RANS solver. A common architecture and objective structure are used across subcritical and transonic flows, including challenging conditions with shock-induced separation. A condition-modulated Transolver combines Fourier and wall features with target-gated regularization, a Sobolev-type loss, adaptive loss weighting and sampled training. Prediction requires no preliminary flow solution, and training requires no solver-residual evaluation. Extensive 3D CFD evaluations on SuperWing, the NASA Common Research Model (CRM) and DLR-F6 assess geometric and operating-condition generalization, including interpolation, extrapolation and cross-mesh deployment, using Spalart-Allmaras and k-ω SST closures on million-cell meshes. Unseen nominal cases achieve geometric-mean iteration speed-ups of approximately $2−4\times$ under a common convergence criterion based on cold-run aerodynamic coefficients. On CRM, learned initialization provides greater aggregate acceleration than nearest-condition restarts using the same solution library. Resolution invariance enables direct deployment of coarse-mesh models on finer meshes without retraining, solution interpolation or target-condition coarse solves. Including data generation and training, estimated campaign speed-ups reach $2.1−2.3\times$. No warm run diverges; fewer than 2% fail to satisfy the cold-reference convergence criterion. These results support learned initialization for repeated aerodynamic analyses, while highlighting initialization sensitivity near separation as a remaining limitation.
ER -