Adaptive Dynamic Surface Control for Aircraft With Multiple Disturbances Based on Radial Basis Network

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 semiglobal 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. INDEX TERMS Adaptive neural network, dynamic surface control, disturbances, backstepping, aircraft.

Adaptive Robust Position Control of Electro-Hydraulic Servo Systems with Large Uncertainties and Disturbances

“…By virtue of the excellent properties of their self-learning capability and online weightadaptive mechanisms, radial basis function (RBF) neural networks (NNs) have been employed in various fields such as robot manipulators [17][18][19][20], magnetic levitation systems [21], aircraft [22], hydraulic systems [5,[23][24][25][26], and so on to approximate the unknown dynamic components of control systems. For EHSSs, Z. Yao et al introduced multilayer RBF NNs to approximate partly mismatched and matched uncertainties [5], and semiglobal asymptotic stability was achieved accordingly.…”

Observer-Based Fault Tolerant Control for a Class of Nonlinear Systems via Filter and Neural Network

“…In [22], a control method combined robust technique with ANN was proposed for aircraft, such method can guarantee that the output tracking error converges to a small region of zero. In [23], an ANN-based control strategy was proposed for an airplane in the presence of parameter uncertainties and multi-disturbances. Such method utilized ANN to approximate the unknown functions appearing in systems, dynamic surface control was introduced to deal with the expansion of the differential terms in back-stepping technique.…”