Robust tracking control for quadrotor with unknown nonlinear dynamics using adaptive neural network based fractional-order backstepping control |
| |
| Institution: | 1. Department of Electrical Engineering, LI3CUB Laboratory, University of Biskra, Biskra, Algeria;2. Department of Electronics, Faculty of Technology, Contantine 1 University, Constantine, Algeria;3. Department of Electrical Engineering, LGEERE Laboratory, University of El Oued, El Oued, Algeria;1. School of Automation Science and Engineering, Xi’an Jiaotong University, Xi’an 710049, China;2. SKLMSE lab, MOE Key Laboratory for Intelligent Networks and Network Security, Xi’an Jiaotong University, Xi’an 710049, China;3. Institute of Aero-engine, School of Mechanical Engineering, Xi’an Jiao Tong University, Xi’an 710049, China;1. College of Information Science and Engineering, Northeastern University, Shenyang 110819, Liaoning, People’s Republic of China;2. Doctoral School FEIT, SS Cyril and Methodius University, 18 Rugjer Boskovic Str, Karpos 2, Skopje 1000, Republic of N. Macedonia;1. College of Mathematics and Computer Science, Tongling University, Tongling, 244000, China;2. School of Electrical and Information Engineering, Jiangsu University, Zhenjiang, 212013, China;1. National Center for Applied Mathematics in Chongqing, Chongqing Normal University, Chongqing, 401331, PR China;2. Shanghai Institute of Applied Mathematics and Mechanics, Shanghai Key Laboratory of Mechanics in Energy Engineering, School of Mechanics and Engineering Science, Shanghai University, Shanghai, 200072, PR China;3. Faculty of Engineering and IT, University of Technology Sydney, NSW 2007, Australia;4. School of Mechatronic Engineering and Automation, Shanghai University, Shanghai, 200072, PR China |
| |
| Abstract: | This work aims to design a neural network-based fractional-order backstepping controller (NNFOBC) to control a multiple-input multiple-output (MIMO) quadrotor unmanned aerial vehicle (QUAV) system under uncertainties and disturbances and unknown dynamics. First, we investigated the dynamic of QUAV composed of six inter-connected nonlinear subsystems. Then, to increase the convergence speed and control precision of the classical backstepping controller (BC), we design a fractional-order BC (FOBC) that provides further degrees of freedom in the control parameters for every subsystem. Besides, designing control is a challenge as the FOBC requires knowledge of accurate mathematical model and the physical parameters of QUAV system. To address this problem, we propose an adaptive approximator that is a radial basis function neural network (RBFNN) included in FOBC to fix the unknown dynamics problem which results in the new approach NNFOBC. Furthermore, a robust control term is introduced to increase the tracking performance of a reference signal as parametric uncertainties and disturbances occur. We have used Lyapunov's theorem to derive adaptive laws of control parameters. Finally, the outcoming results confirm that the performance of the proposed NNFOBC controller outperforms both the classical BC , FOBC and a neural network-based classical BC controller (NNBC) and under parametric uncertainties and disturbances. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
