Direct adaptive neural control of nonlinear strict-feedback systems with unmodeled dynamics using small-gain approach

2015 ◽  
Vol 30 (6) ◽  
pp. 906-927 ◽  
Author(s):  
Huanqing Wang ◽  
Hongyan Yang ◽  
Xiaoping Liu ◽  
Liang Liu ◽  
Shuai Li
Keyword(s):  
Neural Control ◽  
Unmodeled Dynamics ◽  
Feedback Systems ◽  
Adaptive Neural Control ◽  
Small Gain ◽  
Strict Feedback

scholarly journals Robust Adaptive Neural Backstepping Control for a Class of Nonlinear Systems with Dynamic Uncertainties

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Hongyan Yang ◽  
Huanqing Wang ◽  
Hamid Reza Karimi
Keyword(s):  
Neural Control ◽  
Unmodeled Dynamics ◽  
Rbf Neural Networks ◽  
Feedback Systems ◽  
Adaptive Neural Control ◽  
Control Approach ◽  
Closed Loop Systems ◽  
Control Scheme ◽  
Nonlinear Uncertainties ◽  
Robust Adaptive

This paper is concerned with adaptive neural control of nonlinear strict-feedback systems with nonlinear uncertainties, unmodeled dynamics, and dynamic disturbances. To overcome the difficulty from the unmodeled dynamics, a dynamic signal is introduced. Radical basis function (RBF) neural networks are employed to model the packaged unknown nonlinearities, and then an adaptive neural control approach is developed by using backstepping technique. The proposed controller guarantees semiglobal boundedness of all the signals in the closed-loop systems. A simulation example is given to show the effectiveness of the presented control scheme.

scholarly journals Adaptive Neural Control for Nonaffine Pure-Feedback System Based on Extreme Learning Machine

2019 ◽  
Vol 2019 ◽  
pp. 1-13
Author(s):  
Chenyang Xu ◽  
Humin Lei ◽  
Jiong Li ◽  
Jikun Ye ◽  
Dongyang Zhang
Keyword(s):  
Extreme Learning Machine ◽  
Neural Control ◽  
Control Method ◽  
Tracking Error ◽  
Adjustment Process ◽  
Equivalent Transformation ◽  
State Variables ◽  
Feedback Systems ◽  
Adaptive Neural Control ◽  
Learning Machine

For nonaffine pure-feedback systems, an adaptive neural control method based on extreme learning machine (ELM) is proposed in this paper. Different from the existing methods, this scheme firstly converts the original system into a nonaffine system containing only one unknown term by equivalent transformation, thus avoiding the cumbersome and complex indirect design process of traditional backstepping methods. Secondly, a high-performance finite-time-convergence-differentiator (FD) is designed, through which the system state variables and their derivatives are accurately estimated to ensure the control effect. Thirdly, based on the implicit function theorem, the ELM neural network is introduced to approximate the uncertain items of the system, which simplifies the repeated adjustment process of the network training parameters. Meanwhile, the minimum learning parameter algorithm (MLP) is adopted to design the adaptive law for the norm of the network weight vector, which significantly reduces calculations. And it is theoretically proved that the closed-loop control system is stable and the tracking error is bounded. Finally, the effectiveness of the designed controller is verified by simulation.

Sign in / Sign up

Export Citation Format

Share Document