Research on Unsteady Aerodynamics Modeling Based on Back Propagation Algorithm at High Angle of Attack

Abstract

with the BP algorithm, this paper sets up the High angle of attack unsteady aerodynamic neural network model. By using the large-amplitude pitch oscillation dynamic test data of some slender model in high-speed wind tunnel, this paper trains and verifies the BP neural network model and discusses elements which may influence the arithmetic speed and prediction accuracy of the neural network model. Test results show that the established BP neural network model matches the wind tunnel test results nicely and has relatively good capacity to predict the High angle of attack unsteady aerodynamics.