Skip to content

A fast prediction approach for airfoil flow field based on the deep neural network framework

Sep 2026 · Proceedings of the Institution of Mechanical Engineers. Part G, Journal of Aerospace Engineering · 0 citations · 57 references

TL;DR

The results show that ParaAero-Net performs effectively in small-sample aerodynamic prediction of two-dimensional airfoils and achieves good reconstruction of both flow-field structures and aerodynamic coefficients.

Abstract

A rapid aerodynamic prediction framework, termed ParaAero-Net, is proposed for low-Mach-number two-dimensional airfoils under small-sample conditions. Unlike conventional data-driven approaches that focus only on either flow-field reconstruction or aerodynamic coefficient prediction, ParaAero-Net integrates geometry-aware full-field reconstruction and wall aerodynamic quantity prediction within a unified framework. The first module, Physics-informed U-Net Attention module (PIUA), is developed for flow-field prediction by integrating attention mechanisms with soft physical constraints, enabling rapid inference with relatively low network complexity. The second module, Hybrid MLP-XGBoost Regressor module (HMXR), is established for aerodynamic coefficient prediction by decoupling aerodynamic response prediction from flow-field prediction. In this way, the prediction accuracy of aerodynamic coefficients is improved while detailed flow-field reconstruction capability is retained. The results show that ParaAero-Net performs effectively in small-sample aerodynamic prediction of two-dimensional airfoils and achieves good reconstruction of both flow-field structures and aerodynamic coefficients. For the cases considered in this study, a maximum fitting accuracy of 99.8% is achieved.

View source

Similar papers

Conference Open access Aug 2026

Hypersonic flow field prediction based on U-Net and flow field domain optimization

This study proposes a model that combines signed distance function (SDF) domain optimization, near-wall adaptive weight, and a U-Net neural network that increases the prediction accuracy of the pressure field and temperature field by 56% and 50%, respectively.

Jing-Ze Zou, Wen-Qing Zhang, Bo-Tao Jin et al. · 0 citations
#machine learning Preprint Aug 2026

A Residual Learning Approach for Unsteady Aerodynamic Load Prediction

This paper investigates the feasibility of using residual learning to improve unsteady aerodynamic load prediction for aeroelastic applications. The machine learning technique selected for the study is the long short-term memory (LSTM) neural network, which is used for its suitability for sequential data with aerodynam...

Divya Sanghi, C. Cesnik · 0 citations
Open access 2026

Velocity Prediction in Hypersonic Flow via Prior-Guided Data Fusion and Physics-Informed Learning

Accurate velocity prediction of bodies under hypersonic flow is crucial for aerospace engineering and safety evaluation. However, unsteady aerodynamic effects coupled with sparse and noisy experimental data make accurate velocity prediction challenging. Taking conical-end cylinder as example, a prior-guided data fusion...

Feng-Hu Yang, Heng Liu, Hong-Ling Xia et al. · 0 citations
Aug 2026

Investigation of Neural Network-Based Calibration of the Geko Turbulence Model for High-Lift Airfoil Flow Prediction

Accurate prediction of aerodynamic forces for high-lift configurations remains challenging in CFD due to turbulence modeling limitations. This study applies neural network-based calibration to the Generalized κ–ω (GEKO) model to improve flow prediction over a multi-element airfoil. Baseline SST-κ–ω and GEKO models matc...

Kaushik Chavali, Raghul Subramani, Shankar Kaira et al. · 0 citations
Open access Sep 2026

Physics-Informed Neural Network Framework for Ship Roll Motion Prediction with Adaptive Loss Balancing

The results demonstrate that incorporating adaptive loss balancing into the physics-informed BP neural-network framework can improve roll motion prediction accuracy without introducing a substantial additional computational burden.

Li-Feng Hu, Xin-Yu Mu, Jie Liu et al. · 0 citations
Aug 2026

Toward a Foundation-Model Paradigm for Aerodynamic Prediction in Three-Dimensional Design

The proposed methodology for efficiently constructing accurate surrogate models for design purposes by first pretraining a large-scale model on diverse geometries and then fine-tuning it with a few more detailed task-specific samples achieves a 0.36% error on surface-flow prediction.

Yunjia Yang, Babak Gholami, Caglar Guerbuez et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.