Abstract
In this paper, an adaptive dynamic surface control (DSC) method based on neural network for the flight path angle of an aircraft is investigated in view of the parameters uncertainty, multi-disturbance and nonlinearity of the aircraft. First, a traditional backstepping controller is derived as a base. To enhance the adaptability and robustness, radial basis function (RBF) neural networks are introduced to estimate the unknown parameters of the model online and overcome the external disturbance. In addition, two first-order low-pass filters in the dynamic surface control, which can eliminate the expansion of the differential terms and simplify the design of controller’s parameters, are devised to compute the derivative of the virtual controller. Then the parameters range of the dynamic surface controller is obtained by stability analysis, which is convenient for us to opt for and regulate these parameters independently. Eventually, the semi-global stability of closed-loop system is rigorously proved by Lyapunov method. And the simulation results of dynamic surface control and backstepping control under multiple groups of different disturbances also manifest that the derived dynamic surface controller possesses faster and more precise tracking performance, stronger adaptive ability and robustness to external disturbances than backstepping controller. Generally speaking, the adaptive dynamic surface controller engineered in this paper has considerable reference significance for the control of practical aircraft.
Highlights
Nonlinear control of aircraft is a hot spot in control field
The second section establishes the longitudinal model of aircraft, a traditional backstepping controller and adaptive dynamic surface controller based on radial basis function (RBF) neural network are derived in third section
In this paper, adaptive dynamic surface control based on RBF neural network is derived for aircraft with nonlinearity, strong coupling and uncertainty
Summary
Nonlinear control of aircraft is a hot spot in control field. The highly nonlinear, unpredictable uncertainty and strong coupling of the dynamics makes it tough to derive the control law. For the nonlinear control problem of near-space variable wing hypersonic vehicle [1], considering the influence of variable wing on modeling, the influence of parameter uncertainty and unknown disturbance, and the problem of multiple ‘‘differential expansion’’ of virtual signal, a robust adaptive dynamic surface control strategy based on backstepping is proposed [24]. (1) The adaptive dynamic surface control based on RBF neural network is extended to the tracking control of a nonlinear strict feedback aircraft system with model uncertainties and external disturbances. The second section establishes the longitudinal model of aircraft, a traditional backstepping controller and adaptive dynamic surface controller based on RBF neural network are derived in third section. The goal is to derive a dynamic surface controller with adaptive neural networks so that the flight path angle x1 of the aircraft can track the ideal trajectory x1d.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
