Composite Learning Control of Hypersonic Flight Dynamics Without Back-Stepping

In this paper, composite neural control is proposed for hypersonic flight control in presence of unknown dynamics. Using high gain observer (HGO), the controller of attitude subsystem is designed without back-stepping. This strategy simplifies the process of controller design and reduces the computation burden of parameter updating. To construct the composite neural controller, the filtered modeling error is further considered in the weight updating of RBF NN. Moreover, the composite neural controller can achieve the fast learning of system uncertainty. Simulation is presented to demonstrate the effectiveness of the design.

[1]  Zhongke Shi,et al.  Composite Neural Dynamic Surface Control of a Class of Uncertain Nonlinear Systems in Strict-Feedback Form , 2014, IEEE Transactions on Cybernetics.

[2]  Xu Bin,et al.  Adaptive neural control based on HGO for hypersonic flight vehicles , 2011 .

[3]  Yonghua Fan,et al.  Minimal-learning-parameter technique based adaptive neural control of hypersonic flight dynamics without back-stepping , 2015, Neurocomputing.

[4]  Marios M. Polycarpou,et al.  Command filtered backstepping , 2009, 2008 American Control Conference.

[5]  Licheng Jiao,et al.  Adaptive NN Backstepping Output-Feedback Control for Stochastic Nonlinear Strict-Feedback Systems With Time-Varying Delays , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[6]  Okyay Kaynak,et al.  Robust and adaptive backstepping control for nonlinear systems using RBF neural networks , 2004, IEEE Transactions on Neural Networks.

[7]  DaoXiang Gao,et al.  Dynamic Surface Control for Hypersonic Aircraft Using Fuzzy Logic System , 2007, 2007 IEEE International Conference on Automation and Logistics.

[8]  Zhongke Shi,et al.  Composite fuzzy control of a class of uncertain nonlinear systems with disturbance observer , 2015 .

[9]  Fuchun Sun,et al.  Disturbance Observer Based Composite Learning Fuzzy Control of Nonlinear Systems with Unknown Dead Zone , 2017, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[10]  Marios M. Polycarpou,et al.  Command filtered adaptive backstepping , 2010, Proceedings of the 2010 American Control Conference.

[11]  Junmin Li,et al.  Decentralized Output-Feedback Neural Control for Systems With Unknown Interconnections , 2008, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).