Adaptive discrete-time controller design with neural network for hypersonic flight vehicle via back-stepping |
| |
Authors: | Bin Xu Fuchun Sun Chenguang Yang Daoxiang Gao Jianxin Ren |
| |
Affiliation: | 1. Department of Computer Science and Technology , Tsinghua University , Beijing, China smileface.binxu@gmail.com;3. Department of Computer Science and Technology , Tsinghua University , Beijing, China;4. School of Computing and Mathematics , Plymouth University , Plymouth, UK;5. School of Engineering , Beijing Forestry University , Beijing, China;6. School of Automation , Northwestern Polytechnical University , Xi'an, China 710070 |
| |
Abstract: | In this article, the adaptive neural controller in discrete time is investigated for the longitudinal dynamics of a generic hypersonic flight vehicle. The dynamics are decomposed into the altitude subsystem and the velocity subsystem. The altitude subsystem is transformed into the strict-feedback form from which the discrete-time model is derived by the first-order Taylor expansion. The virtual control is designed with nominal feedback and neural network (NN) approximation via back-stepping. Meanwhile, one adaptive NN controller is designed for the velocity subsystem. To avoid the circular construction problem in the practical control, the design of coefficients adopts the upper bound instead of the nominal value. Under the proposed controller, the semiglobal uniform ultimate boundedness stability is guaranteed. The square and step responses are presented in the simulation studies to show the effectiveness of the proposed control approach. |
| |
Keywords: | hypersonic flight vehicle back-stepping neural network discrete-time |
|
|