Physics-Informed-Neural-Network-Based Fast Prediction Method for Scramjet Nozzle Flow
AIAA Journal · 24.06.2026 · 1-13
DOI: 10.2514/1.j067324 ↗Kurz gefasst
Fachartikel in der Zeitschrift AIAA Journal, online erschienen am 24.06.2026. Verfasst von Shuhong Tong und 5 weiteren Autor:innen. Die Arbeit nennt 24 Literaturangaben. Gefördert von: National Key Laboratory of Advanced Technology for Cross-Domain Flight, Outstanding Star Program of Zhiqiang Fund.
Abstract (Originalsprache)
To enable fast, efficient, and reliable prediction of the nozzle flowfield to assist optimization design and knowledge discovery, this study investigates a dual data- and knowledge-driven model approach for nozzle flowfield prediction. Traditional data-driven flowfield prediction models exhibit limitations in prediction accuracy and physical interpretability, and the skewed distribution characteristics of raw computational fluid dynamics (CFD) data significantly constrain the effectiveness of model training. To address these issues, a structured grid bilinear data enhancement (SGBDE) method is proposed, which effectively improves the distribution characteristics of the CFD data. Simultaneously, a physics-informed neural network (PINN) framework is constructed by incorporating Euler equation constraints and flow physical quantity vector structure constraints, thereby enhancing the model’s generalization capability. By integrating SGBDE and PINN, DE-PINN is constructed. Experimental validation shows that the coefficient of determination [Formula: see text] for physical quantity predictions by DE-PINN exceeds 0.997, significantly outperforming other models. Ablation experiments further validate the individual effectiveness and synergistic interaction of SGBDE and physics-informed constraints, demonstrating excellent application potential, providing new technical support for nozzle optimization, and offering important references for intelligent flowfield prediction.
Förderung
- National Key Laboratory of Advanced Technology for Cross-Domain Flight
- Outstanding Star Program of Zhiqiang Fund
Zitieren
APA
Tong, S., Tian, Y., Deng, X., Ma, Y., Chen, E., & Chen, C. (2026). Physics-Informed-Neural-Network-Based Fast Prediction Method for Scramjet Nozzle Flow. AIAA Journal, 1-13. https://doi.org/10.2514/1.j067324
Vancouver
Tong S, Tian Y, Deng X, Ma Y, Chen E, Chen C. Physics-Informed-Neural-Network-Based Fast Prediction Method for Scramjet Nozzle Flow. AIAA Journal. 2026:1-13. doi:10.2514/1.j067324
BibTeX
@article{Tong2026,
author = {Tong, Shuhong and Tian, Ye and Deng, Xue and Ma, Yue and Chen, Erda and Chen, Chunmei},
title = {Physics-Informed-Neural-Network-Based Fast Prediction Method for Scramjet Nozzle Flow},
journal = {AIAA Journal},
year = {2026},
pages = {1--13},
doi = {10.2514/1.j067324}
}
EUVIMED