Deep neural network modeling for CFD simulation of drone bioinspired morphing wings

Abstract

In this paper we present a deep neural network modelling using Computational Fluid Dynamics (CFD) simulations data in order to optimize control of bioinspired morphing wings of a drone. Drones flight needs to consider variation in aerodynamic conditions that cannot all be optimized using a fixed aerodynamic profile. Nature solves this issue as birds are changing continuously the shape of their wings depending of the aerodynamic current requirements. One important issue for fixed wing drone is the landing as it is unable to control and most of the time consequences are some damages at the nose. An optimized shape of the wing at landing will avoid this situation. Another issue is that wings with a maximum surface are sensitive to stronger head winds; while wings with a small surface allowing the drone to fly faster. A wing with a morphing surface could adapt its aerial surface to optimize aerodynamic performance to specific flight situations. A morphing wing needs to be controlled in an optimized manner taking into account current aerodynamics parameters. Predicting optimized positions of the wing needs to consider (CFD) prior simulation parameters. The scenarios for flight require an important number of CFD simulation to address different conditions and geometric shapes. We compare in this paper neural network architecture suitable to predict wing shape according to current conditions. Deep neural network (DNN) is trained using data resulted out of CFD simulations to estimate flight conditions.