Control Power Optimization using Artificial Intelligence for Forward Swept Wing and Hybrid Wing Body Aircraft

摘要

Many futuristic aircraft such as the Hybrid Wing Body have numerous control surfaces that can result in large hinge moments, high actuation power demands, and large actuator forces/moments. Also, there is no unique relationship between control inputs and the aircraft response; distinct sets of control surface deflections may result in the same aircraft response, but with large differences in actuation power. An Artificial Neural Network and Genetic Algorithm were used here for the control allocation optimization problem of a Hybrid Wing Body to minimize the Sum of Absolute Values of Hinge Moments by more than 14% for a 2.5-G pull-up maneuver. To test the versatility of the same optimization process for different aircraft configurations, the present paper also investigates its application on the Forward Swept Wing aircraft A method to improve the robustness of the process is also presented. Constraints on the load factor and longitudinal pitch rate were added to the optimization to preserve the trim constraints on the control deflections. Another method was developed using stability derivatives. This new method provided better results, and the computational time was reduced by two orders of magnitude. A hybrid scheme combining both methods was also developed to provide a real-time estimate of the optimum control deflection schedules to trim the airplane and minimize the actuation power for changing flight conditions (Mach number, altitude and load factor) in a pull-up maneuver.