Adaptive neural network asymptotic tracking control for nonstrict feedback stochastic nonlinear systems

Yongchao Liu; Qidan Zhu

doi:10.1016/j.neunet.2021.06.011

Adaptive neural network asymptotic tracking control for nonstrict feedback stochastic nonlinear systems

Neural Netw. 2021 Nov:143:283-290. doi: 10.1016/j.neunet.2021.06.011. Epub 2021 Jun 12.

Authors

Yongchao Liu¹, Qidan Zhu²

Affiliations

¹ College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, 150001, China; Key laboratory of Intelligent Technology and Application of Marine Equipment (Harbin Engineering University), Ministry of Education, Harbin, 150001, China.
² College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, 150001, China; Key laboratory of Intelligent Technology and Application of Marine Equipment (Harbin Engineering University), Ministry of Education, Harbin, 150001, China. Electronic address: heu406@126.com.

PMID: 34166891
DOI: 10.1016/j.neunet.2021.06.011

Abstract

The adaptive neural network asymptotic tracking control issue of nonstrict feedback stochastic nonlinear systems is studied in our article by adopting backstepping algorithm. Compared with the existing research, the hypothesis about unknown virtual control coefficients (UVCC) is overcome in the control design. By using the bound estimation scheme and some smooth functions, associating with approximation-based neural network, the asymptotic tracking controller is recursively constructed. With the aid of Lyapunov function and beneficial inequalities, the asymptotic convergence character and stability with stochastic disturbance and unknown UVCC can be ensured. Finally, the theoretical finding is verified via a simulation example.

Keywords: Asymptotic tracking control; Backstepping algorithm; Neural network; Stochastic nonlinear systems.

MeSH terms

Algorithms
Computer Simulation
Feedback
Neural Networks, Computer*
Nonlinear Dynamics*