Unsteady aerodynamic identification based on recurrent neural networks
Authors:
Open Access
- 15 December 2020
- journal article
- research article
- Published by JVE International Ltd. in Journal of Vibroengineering
- Vol. 23 (2) , 449-458
Abstract
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.Keywords
This publication has 23 references indexed in Scilit:
- Dynamic mode decomposition of numerical and experimental dataJournal of Fluid Mechanics, 2010
- Investigation of flow over an oscillating airfoilJournal of Fluid Mechanics, 2004
- Reduced-order modeling: new approaches for computational physicsProgress in Aerospace Sciences, 2004
- Reduced-Order Models for Nonlinear Unsteady AerodynamicsAIAA Journal, 2001
- MODELING OF FLUID-STRUCTURE INTERACTIONAnnual Review of Fluid Mechanics, 2001
- Proper Orthogonal Decomposition Technique for Transonic Unsteady Aerodynamic FlowsAIAA Journal, 2000
- Solution of the Unsteady Euler Equations Using an Implicit Dual-Time MethodAIAA Journal, 1998
- Toward a Unified Lift Model for Use in Rotor Blade Stability AnalysesJournal of the American Helicopter Society, 1985
- Prediction of Dynamic Stall and Unsteady Airloads for Rotor BladesJournal of the American Helicopter Society, 1982
- Approximate Riemann solvers, parameter vectors, and difference schemesJournal of Computational Physics, 1981