Adaptive dynamic surface control for small-scale unmanned helicopters using a neural network learning algorithm with the least parameters

• Published in: Chinese Control and Decision Conference pp. 6442 - 6447
• Main Authors: Zhou, Bin, Li, Peng, Zheng, Zhiqiang, Tang, Shuai
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.06.2018
• Subjects: Actuators; Adaptive dynamic surface control; Attitude control; Blades; Helicopters; Neural network; Robust control; Robustness; Rotors; Small-scale unmanned helicopter
• ISSN: 1948-9447
• DOI: 10.1109/CCDC.2018.8408262

In this paper, a novel adaptive dynamic surface control (ADSC) is proposed to address the attitude tracking problem of a small-scale unmanned helicopter which is subject to model uncertainties and external disturbances. The dynamic surface controller is designed for the nominal attitude model and a radial basis function neural network (RBFN-N) is proposed to compensate the model uncertainties and external disturbances. Moreover, a novel learning algorithm is used in the RBFNN which has the least adaptive parameters need to be adjusted so that the designed attitude control system is more practical in actual applications. At last, the overall closed-loop system is proved to be semi-globally uniformly ultimately bounded by the strict Lyapunov stability theory, and the effectiveness and the robustness of the proposed strategy are exhibited through simulations.