Approximate Feedback Linearisation Using Multilayer Neural Networks

Authors:
Shouling He;Rolf Unbehauen
Affiliations:
Fellow, IEEE. E-mail: Email: he@late.e-technik.uni-erlangen.de;Fellow, IEEE. E-mail: Email: he@late.e-technik.uni-erlangen.de
Venue:
Neural Processing Letters
Year:
1998

Citing 7
Cited 0

Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks

Neural Networks
Nonlinear control via uniform system approximation

Systems & Control Letters
Approximate Feedback Linearization: A Homotopy Operator Approach

SIAM Journal on Control and Optimization
Multilayer neural networks for solving a class of partial differential equations

Neural Networks
Nonlinear Control Systems: An Introduction

Nonlinear Control Systems: An Introduction
Neural Networks for Optimization and Signal Processing

Neural Networks for Optimization and Signal Processing
A neural approach for control of nonlinear systems with feedback linearization

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we introduce the approximate feedback linearisation usingmultilayer feedforward neural networks. We propose to approximate a basisof the one-dimensional codistribution of an affine nonlinear system withthe derivative of a multilayer neural network [6] and form a change ofcoordinates with n multilayer neural networks [5]. In this paper we willprove that the transformation can define a local diffeomorphism, withwhich a local stabilising feedback law can be designed for a kind ofnon-linearisable nonlinear systems.