Abstract
Aiming at the difficulty of post-stall maneuvering control modeling and control of advanced aircraft under unsteady aerodynamics, a control method with high control accuracy and fast computation speed is proposed based on Radial Basis Function (RBF) network with minimum parameters learning (MPL) and dynamic surface control (DSC) method. Firstly, the aerodynamic characteristics of post-stall maneuvers are analyzed based on the experimental data of large-scale oscillation wind tunnels, and the key factors affecting the unsteady aerodynamic forces are obtained. Then, an accurate unsteady aerodynamic model is established based on the improved extreme learning machine (ELM) method. Secondly, the influence of unsteady aerodynamic forces on the control of post-stall maneuvers is considered. For the uncertainty of advanced aircraft model, high angle of attack flight control laws based on RBF-DSC are designed. In order to improve the calculation speed of the above control law and optimize the parameters, a post-stall maneuver control law method based on MPL-RBF-DSC is designed, and the stability of the method is proved. The coordinated allocation of the conventional aerodynamic surfaces and thrust vectors is realized based on the daisy chain method. Finally, the typical maneuver simulation of “Cobra” is carried out, which highlights the advantages of the design method in this paper, such as high control accuracy, short calculation time and strong robustness.
Highlights
Air combat simulation shows that advanced fighters with high maneuverability and agility can achieve rapid occupancy, firing of predecessors and effective evasion in the process of short-range air combat, which provides important technical support for enhancing operational efficiency and improving survival probability
Shi et al.: Minimum Parameters Learning-Based Dynamic Surface Control angle of attack, and the corresponding unsteady aerodynamic modeling methods have become the research hotspot for aircraft flying at high angle of attack [5]
The multi-kernel neural networks and the modeling of the nonlinear unsteady aerodynamics at constant or varying flow conditions is proposed in [8], and the results indicate that the proposed multi-kernel neural networks outperform the single-kernel Radial Basis Function (RBF) neural networks in modeling noise-free and noisy aerodynamics at a constant Mach number, as well as in predicting the aerodynamic loads with varying Mach numbers
Summary
Air combat simulation shows that advanced fighters with high maneuverability and agility can achieve rapid occupancy, firing of predecessors and effective evasion in the process of short-range air combat, which provides important technical support for enhancing operational efficiency and improving survival probability. How to obtain aerodynamic data at high angle of attack and establish accurate unsteady aerodynamic model is the primary challenge for advanced fighter during the post-stall maneuver [3], [4]. J. Shi et al.: Minimum Parameters Learning-Based Dynamic Surface Control angle of attack, and the corresponding unsteady aerodynamic modeling methods have become the research hotspot for aircraft flying at high angle of attack [5]. In [9], the paper presents an innovative unsteady aerodynamic modeling method based on the improved Extreme Learning Machine (ELM), which is further successfully applied into the biaxial coupled oscillation during the post stall maneuver flight.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
