Neural Net-Based H∞ Control for a Class of Nonlinear Systems

Authors:
Chun-Liang Lin;Tsai-Yuan Lin
Affiliations:
Institute of Automatic Control Engineering, Feng Chia University, Taichung, Taiwan 40724, R.O.C. E-mail: chunlin@fcu.edu.tw;Institute of Automatic Control Engineering, Feng Chia University, Taichung, Taiwan 40724, R.O.C.
Venue:
Neural Processing Letters
Year:
2002

Citing 7
Cited 0

Matrix analysis

Matrix analysis
On the approximate realization of continuous mappings by neural networks

Neural Networks
The H∞ control problem

The H∞ control problem
Artificial Neural Networks for Modelling and Control of Non-Linear Systems

Artificial Neural Networks for Modelling and Control of Non-Linear Systems
Analysis and design of fuzzy controller and fuzzy observer

IEEE Transactions on Fuzzy Systems
An approach to stability criteria of neural-network control systems

IEEE Transactions on Neural Networks
Neural network-based control design: an LMI approach

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

A novel neural net-based approach for H∞ control design of a class of nonlinear continuous-time systems is presented. In the proposed frameworks, the nonlinear system models are approximated by multilayer neural networks. The neural networks are piecewisely interpolated to generate a linear differential inclusion models by which a linear state feedback H∞ control law can be constructed. It is shown that finding the permissible control gain matrices can be transformed to a standard linear matrix inequality problem and solved using the available computer software.