Control on 3-D Fixable Wing Flutter Using an Adaptive Neural Controller


An adaptive neural controller to control on flutter in 3-D flexible wing isproposed. The aeroelastic model was based on the coupling between structure-of theequivalent plate (wing) and the aerodynamic model that is based on a hybrid unsteadypanel methodTime domain simulations were used to examine the dynamic aeroelasticinstabilities of the system (e.g. the onset of flutter and limit cycle oscillation). Thestructure of the controller consists of two models namely modified Elman neuralnetwork (MENN) and feedforward multi-layer Perceptron (MLP). The MENN modelis trained with off-line and on-line stages to guarantee that the outputs of the modelaccurately represent the plunge motion of the wing and this neural model acts as theidentifier. The feedforward neural controller is trained off-line and adaptive weightsare implemented on-line to find the generalized control action (function of additionlift force), which controls the plunge motion of the wing. The general backpropagation algorithm is used to learn the feedforward neural controller and theneural identifier. The simulation results show the effectiveness of the proposedcontrol algorithm; this is demonstrated by the minimized tracking error to zeroapproximation with very acceptable settling time.