A data-driven approach for modeling large-amplitude flow-induced oscillations of elastically mounted pitching wings

We propose and validate a data-driven approach for modeling large-amplitude flow-induced oscillations of elastically mounted pitching wings. We first train a neural networks regression model for the nonlinear aerodynamic moment using data obtained from experimental measurements during prescribed pitching oscillations and at fixed angles of attack. We then embed this model into an ordinary differential equation solver to solve the governing equation of the passive aeroelastic system with desired structural parameters. The system dynamics predicted by the proposed data-driven approach are characterized and compared with those obtained from physical experiments. The predicted and experimental pitching amplitude, frequency and aerodynamic moment responses are found to be in excellent agreement. Both the inertia-dominated mode and the hydrodynamic-dominated mode are successfully predicted. The transient growth and saturation of the pitching oscillation amplitude and the aerodynamic moment are also faithfully captured by the proposed approach. Additional test cases demonstrate the broad applicability and good scalability potential of this approach.