@article{CUI2026, 
author = {Mutian CUI and Dongli MA and Muqing YANG and Lihang SU and Duyu GUO},
title = {Rapid prediction method for aircraft aerodynamic characteristics via multi-fidelity data-fusion of vortex lattice method and CFD},
year = {2026},
journal = {Acta Aeronautica et Astronautica Sinica},
volume = {47},
number = {20},
keywords = {multi-fidelity data-fusion, Vortex Lattice Method (VLM), aircraft conceptual design, Radial Basis Function Neural Network (RBFNN), Lambda-wing UAV},
url = {https://www.sciopen.com/article/10.7527/S1000-6893.2026.33367},
doi = {10.7527/S1000-6893.2026.33367},
abstract = {The conceptual design phase of aircraft requires extensive analysis and comparison of the aerodynamic performance for numerous configuration candidates. High-fidelity methods like Computational Fluid Dynamics (CFD) are computationally prohibitive. Rapid analysis tools like the Vortex Lattice Method (VLM) often fail to meet accuracy requirements. Single-fidelity data-driven surrogate models, which directly map geometric design variables to aerodynamic characteristics, suffer from prediction accuracy that is heavily dependent on the size and selection of training samples. To address the trade-off between accuracy, efficiency, and sample size, a rapid aerodynamic prediction method that fuses multi-fidelity data from VLM and CFD is proposed. VLM is employed to obtain low-fidelity aerodynamic parameters of a simplified wing surface model efficiently. These parameters, together with the original design variables, Mach number, and wetted surface area, form the enhanced input vector to improve the model's understanding of aerodynamic characteristics. A Radial Basis Function Neural Network (RBFNN) is employed. Based on a correction strategy using multi-fidelity difference functions, a mapping is established from low-fidelity data of simplified wing surface geometries to high-fidelity data of complete aircraft geometries, achieving the goal of reducing training sample size and improving simulation efficiency. The method is validated using a Lambda-wing UAV dataset. The results show that with 25 training samples, the high-fidelity aerodynamic parameters of UAV can be accurately predicted. The prediction accuracy for all parameters outperforms that of single-fidelity data-driven surrogate models, and is comparable to the co-Kriging method, with certain parameters even demonstrating superior prediction performance. Test samples are designed for typical engineering scenarios, with the relative prediction error of each aerodynamic coefficient not exceeding 3%, and the calculation time reduced by two orders of magnitude compared with CFD calculations. The general applicability of the method is further verified through the testing of extrapolated samples. The proposed fusion method is applied to the optimization of the Lambda-wing UAV scheme. The cruise lift-to-drag ratio of the optimal scheme is increased by 13.2%, and the predicted relative error is less than 1.2%. This effectively enhanced the design efficiency and holds certain prospects for engineering application.}
}