Unsteady aerodynamic identification based on recurrent neural networks

Journal of Vibroengineering

Tuanyuan Zhang¹  Ruiqun Ma²  Bo Zhang²  Jinglong Han² 

[1] China Academy of Aerospace Aerodynamics, Beijing, 100074, China;State Key Laboratory of Mechanics and Control of Mechanical Structures, Nanjing University of Aeronautics and Astronautics, Nanjing, 210016, China;

关键词: unsteady aerodynamic identification;    recurrent neural networks;    computational fluid dynamics;    high angle of attack;    reduced order model;   

DOI  :  10.21595/jve.2020.21612

来源: DOAJ

【 摘 要 】

The dynamic stall at high angle of attack is an important aerodynamic problem faced by aircraft, and it has always been a hotspot of aerodynamic research. The traditional reduced order model (ROM) methods needs to establish an accurate model, and has a high demand for experience. In this paper, a novel nonlinear aerodynamic identification method based on recurrent neural networks (RNNs) is proposed. The computational fluid dynamics (CFD) method is used to calculate the unsteady aerodynamic parameters of the NACA0012 airfoil. A group of sinusoidal chirp signals with variable amplitude and frequency are adopted as the excitation signals, and the obtained data are used to train the recurrent neural networks, and the ROM of the nonlinear aerodynamic model of high angle of attack dynamic stall is obtained. Finally, the aerodynamic parameters of a group of composite sinusoidal motion signals different from the training signals are predicted by the trained neural networks model and compared with the CFD results.

【 授权许可】

Unknown