In many engineering applications, determining stagnation point heat flux is essential, especially in aerospace. Traditional CFD is accurate but slow for preliminary design. We explore Physics-Informed Neural Networks (PINNs) as a fast alternative on an axisymmetric blunt-nose body with variable nose radius. PINNs achieve accuracy comparable to CFD while dramatically improving computational efficiency.
Yaşar, H. A., & Sevinc, O. K. (2024). Physics Informed Neural Networks for Enhanced Critical Heat Flux Prediction in Hypersonic Flows. AIAA Aviation Forum. https://doi.org/10.2514/6.2024-4203
@inproceedings{YasarSevinc2024AIAA,
title = {Physics Informed Neural Networks for Enhanced Critical Heat Flux Prediction in Hypersonic Flows},
author = {Yaşar, Hüseyin Avni and Sevinc, Oguz Kaan},
booktitle = {AIAA Aviation Forum},
year = {2024},
doi = {10.2514/6.2024-4203}
}