Neural Network Control for a Class of Stochastic Nonlinear Switched System Based on Backstepping

Authors:
Sheng Zhang;Fei Long
Affiliations:
College of Computer Science and Information Engineering, Guizhou University,Guiyang, Guizhou, P. R. China 550025;College of Computer Science and Information Engineering, Guizhou University,Guiyang, Guizhou, P. R. China 550025
Venue:
ISNN 2009 Proceedings of the 6th International Symposium on Neural Networks: Advances in Neural Networks - Part II
Year:
2009

Citing 7
Cited 0

Backstepping Controller Design for Nonlinear Stochastic Systems Under a Risk-Sensitive Cost Criterion

SIAM Journal on Control and Optimization
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Stabilization of Nonlinear Uncertain Systems

Stabilization of Nonlinear Uncertain Systems
Adaptive neural network control for switched system with unknown nonlinear part by using backstepping approach: SISO case

ISNN'06 Proceedings of the Third international conference on Advnaces in Neural Networks - Volume Part II
Variable neural networks for adaptive control of nonlinear systems

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Control of nonlinear dynamical systems using neural networks. II. Observability, identification, and control

IEEE Transactions on Neural Networks
Multilayer neural-net robot controller with guaranteed tracking performance

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we deal with the switched stabilization problem for a class of stochastic switched nonlinear systems based on RBF neural network and backstepping approach. By using the combination design technique of backstepping and neural network, an adaptive neural network switching controller is designed for the switched stabilization of stochastic switched nonlinear system with trigonal structure. It is shown that, under Stochastic Lasalle Theorem, the resulting closed-loop system is proved to be globally asymptotically stable in probability.