Robust nonlinear control using neural networks

Author

Wams, Bart ; De Vries, Rob A J

Author_Institution

Fac. of Inf. Technol. & Syst., Delft Univ. of Technol., Netherlands

Volume

3

fYear

1998

fDate

4-9 May 1998

Firstpage

2104

Abstract

In this article, the influence of uncertainty on weights and biases of neural networks on the input/output behavior is investigated. Moreover, a uncertainty description of uncertain neural networks is derived and an appropriate norm bound of the model uncertainty, which is needed for robust control design, is derived. Finally, feedback linearization is used in order to fully incorporate neural networks in standard robust l₁ model based control

Keywords

control system synthesis; feedback; linearisation techniques; neurocontrollers; nonlinear control systems; robust control; uncertain systems; I/O behavior; feedback linearization; input/output behavior; neural networks; norm bound; robust control design; robust l₁ model based control; robust nonlinear control; uncertain neural networks; uncertainty; Control system synthesis; Linear feedback control systems; Neural networks; Neurofeedback; Nonlinear control systems; Predictive control; Predictive models; Robust control; Robust stability; Uncertainty;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.687184

Filename

687184