Ability to forecast unsteady aerodynamic forces of flapping airfoils by artificial neural network

摘要: The ability of artificial neural networks (ANN) to model the unsteady aerodynamic force coefficients flapping motion kinematics has been studied. A was developed based on multi-layer perception (MLP) and Levenberg–Marquardt optimization algorithm. data were divided into two groups for training prediction test ANN model. phase led a very satisfactory calibration attempt predict forces both lift coefficient drag showed that is able simulate its corresponding forces. shape simulated found be similar numerical results. These encouraging results make it possible consider interesting new prospects modelling systems, which are highly non-linear systems.