作者: Huanqing Wang , Bing Chen , Chong Lin
DOI: 10.1002/ACS.2300
关键词: Dead zone 、 Quartic function 、 Control theory 、 Backstepping 、 Tracking error 、 Nonlinear system 、 Stochastic neural network 、 Uniform boundedness 、 Computer science 、 Control theory
摘要: SUMMARY This paper considers the problem of adaptive neural tracking control for a class nonlinear stochastic pure-feedback systems with unknown dead zone. Based on radial basis function networks' online approximation capability, novel controller is presented via backstepping technique. It shown that proposed guarantees all signals closed-loop system are semi-globally, uniformly bounded in probability, and error converges to an arbitrarily small neighborhood around origin sense mean quartic value. Simulation results further illustrate effectiveness suggested scheme. Copyright © 2012 John Wiley & Sons, Ltd.