EGD-ANN model to predict actuators displacements for an open-loop morphing wing system

Resin-based fiber composite material have received much attention in aerospace composite engineering, particularly in aircraft morphing structures due to their higher mechanical characteristic, stiffness and for their... [ view full abstract ]

Resin-based fiber composite material have received much attention in aerospace composite engineering, particularly in aircraft morphing structures due to their higher mechanical characteristic, stiffness and for their potential in greatly reducing structural mass of modern designs. Aircraft morphing is referred to as the ability of change geometry in flight; formally ailerons, flaps, spoilers and control devices were considered morphing. In this work , the empirical modeling of a dynamic morphing wing system was studied. The morphing wing was controlled using four electric actuators situated inside of the wing model. The main role of these actuators is to modify the upper surface made of a flexible material such that the laminar-to-turbulent flow transition point moves close to the wing trailing edge, thus causing less viscous drag. This concept is developed to operate under various flow conditions by changing the wing shape. Four linear variable differential transducers (LVDT) are used to indicate the positions of the four actuators and four dial indicators gage are positioned outside the wing to measure the deflection of the flexible composite skin on four actuation points. The relationship between the Dial indicator’s values and the LVDT’s values for a same set-point command signal has a nondeterministic and unpredictable behavior. The values of the displacement given by LVDT is different than that given by dial indicators. In this work, an Artificial Neural Network (ANN) model was investigated and created to predict the displacements of the skin in real time. The reposed model was trained using Extended Great Deluge (EGD) algorithm.
Keywords: neural networks, prediction, morphing wing, optimization skin, extended great deluge.