Intelligent data-driven aerodynamic analysis and optimization of morphing configurations

In this paper, we develop an online, data-based framework for the aircraft airfoil to be able optimally morph vertically. The proposed combines data-driven analysis, optimization, and control-theoretic tools airfoils while guaranteeing efficiency safety. It incorporates a surrogate model that is based on deep neural network used predict aerodynamic coefficients meta-heuristic optimization algorithm employed find shapes with reduced value of drag coefficient fulfill geometric lift constraints. Finally, shape controller following smooth trajectories small variations. Experimental numerical results show efficacy different flight conditions.