A Hybrid CNN-Cheby-KAN Framework for Efficient Prediction of Two-Dimensional Airfoil Pressure Distribution

2025/11/05 by Yaohong Chen, Chen, Yaohong, Luchi Zhang +9
Engineering · Physics and Astronomy · #76G25 (Primary) 68T07 #Biomimetic flight and propulsion mechanisms #FOS: Physical sciences #Fluid Dynamics (physics.flu-dyn) #Fluid Dynamics and Vibration Analysis #Model Reduction and Neural Networks

paper · pdf · doi:10.48550/arxiv.2511.03223

openalex publication_date 2025/11/05 · openalex created_date 2025/11/07 · openalex updated_date 2026/07/28

Abstract

The accurate prediction of airfoil pressure distribution is essential for aerodynamic performance evaluation, yet traditional methods such as computational fluid dynamics (CFD) and wind tunnel testing have certain bottlenecks. This paper proposes a hybrid deep learning model combining a Convolutional Neural Network (CNN) and a Chebyshev-enhanced Kolmogorov-Arnold Network (Cheby-KAN) for efficient and accurate prediction of the two-dimensional airfoil flow field. The CNN learns 1549 types of airfoils and encodes airfoil geometries into a compact 16-dimensional feature vector, while the Cheby-KAN models complex nonlinear mappings from flight conditions and spatial coordinates to pressure values. Experiments on multiple airfoils--including RAE2822, NACA0012, e387, and mh38--under various Reynolds numbers and angles of attack demonstrate that the proposed method achieves a mean squared error (MSE) on the order of 10^-6 and a coefficient of determination (R²) exceeding 0.999. The model significantly outperforms traditional Multilayer Perceptrons (MLPs) in accuracy and generalizability, with acceptable computational overhead. These results indicate that the hybrid CNN-Cheby-KAN framework offers a promising data-driven approach for rapid aerodynamic prediction.

Citations

• KAN: Kolmogorov-Arnold Networks
• Fast sparse flow field prediction around airfoils via multi-head perceptron based deep learning architecture
• Deep Learning Methods for Reynolds-Averaged Navier–Stokes Simulations of Airfoil Flows
• Accelerating Eulerian Fluid Simulation With Convolutional Networks
• Gradient-based learning applied to document recognition

Related

• Accelerated Airfoil Design Using Neural Network Approaches
• Towards high-accuracy deep learning inference of compressible turbulent flows over aerofoils
• Efficient aerodynamic coefficients prediction with a long sequence neural network
• Deep Learning Methods for Reynolds-Averaged Navier–Stokes Simulations of Airfoil Flows
• Application of Convolutional Neural Network to Predict Airfoil Lift Coefficient