Journal of Astronautics ›› 2021, Vol. 42 ›› Issue (10): 1237-1245.doi: 10.3873/j.issn.1000-1328.2021.10.005

Previous Articles     Next Articles

Adaptive Neural Network Fault Tolerant Control of  Launch Vehicle Attitude System

MA Yan ru, SHI Xiao rong, LIU Hua hua, LIANG Xiao hui, WANG Qing   

  1. 1.School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China; 2. Beijing Institute of Control and Electronics Technology, Beijing 100038, China; 3. School of Automation, Northwestern Polytechnical University, Xi’an 710072, China
  • Received:2020-09-27 Revised:2021-03-07 Online:2021-10-15 Published:2021-10-15

Abstract: In this paper, an adaptive neural network nonlinear fault tolerant control law is proposed for a launch vehicle attitude tracking system considering the influence of interference, actuator fault and model uncertainty. The control algorithm combines the continuous terminal sliding mode control, radial basis neural network and adaptive control methods. Firstly, based on the sliding mode control theory, a fast terminal sliding mode surface is designed to ensure that the system tracking error can converge to zero in a finite time. Then, based on the terminal sliding mode surface, a continuous terminal sliding mode control law based on the adaptive radial basis function neural network estimation is proposed. The neural network with adaptive parameters is used to approximate the system parameters and improve the anti interference performance, and the smooth continuous control strategy is used to eliminate the vibration phenomenon in the terminal sliding mode. The convergence and global stability of the closed loop system are proved by the Lyapunov’s analysis method. Using numerical simulation, it is verified that the terminal sliding mode control law based on the adaptive radial basis function neural network proposed has better tracking performance and accuracy.

Key words: Launch vehicle attitude tracking system, Actuator faults, Fault tolerant control, Sliding mode control, Adaptive radial basis neural network

CLC Number: