Adaptive Sliding Mode Control for Attitude and Altitude System of a Quadcopter UAV via Neural Network

• Published in: IEEE access 2021, Vol.9, p.40076-40085
• Main Authors: Nguyen, Ngoc Phi, Mung, Nguyen Xuan, Thanh, Ha Le Nhu Ngoc, Huynh, Tuan Tu, Lam, Ngoc Tam, Hong, Sung Kyung
• Format: Article
• Language: English
• Subjects: Adaptive control; Adaptive sliding mode; Algorithms; Altitude; Attitude control; Attitudes; Back propagation; Back propagation networks; Backpropagation; Control methods; Control stability; Controllers; Disturbance observers; Dynamic models; Mathematical model; Neural networks; Nonlinear dynamical systems; quadrotor; Sliding mode control; Uncertainty; Unmanned aerial vehicles
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2021.3064883

In this article, a sliding mode control based on neural networks is proposed for attitude and altitude system of quadcopter under external disturbances. First, the dynamic model of the quadcopter is considered under external disturbances. Sliding mode controllers are then integrated with neural network algorithm to achieve the time-varying sliding surface; their coefficients in sliding surface are adjusted through backpropagation law. The disturbance observer is also combined with sliding mode controllers to estimate and handle the external disturbances. Finally, the Lyapunov theory is applied to validate the stability of suggested control method. The performance of proposed sliding mode control has been evaluated using a numerical simulation. The results show that the attitude and altitude controller based on suggested algorithm has a better tracking performance and disturbance rejection.