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

TL;DR

This paper introduces a hybrid deep learning framework combining CNN and Chebyshev-enhanced KAN to efficiently and accurately predict two-dimensional airfoil pressure distributions, outperforming traditional methods in speed and precision.

Contribution

The paper presents a novel hybrid CNN-Cheby-KAN model that encodes airfoil geometries and models complex flow fields for rapid pressure prediction, improving accuracy and efficiency over existing approaches.

Findings

Achieved MSE around 10^{-6} and R^2 > 0.999 on multiple airfoils.

Outperformed traditional MLP models in accuracy and generalizability.

Demonstrated effectiveness across various Reynolds numbers and angles of attack.

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 ($R^2$) 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.