A new strategy for controlling non-linear systems

Author

Srivastava, Smriti ; Singh, Madhlusudan ; Hanmandlu, M.

Author_Institution

NSIT, New Delhi, India

Volume

6

fYear

2004

fDate

10-13 Oct. 2004

Firstpage

5911

Abstract

A new strategy for the controller consisting of linear and non-linear parts for the non-linear systems is presented. The linear part contains an adaptive fast transversal filter (FTF) algorithm and the non-linear part is driven by a neural network, which is driven by a separate algorithm. The basic concept in using the combination is that the non-linear part of the controller operates on non-linear error signal to make it adhere to the set point and the linear part tries to maintain the linearity between the two points. The method is most suitable for few number of data set. It has been tested on two examples and the results are found to be accurate.

Keywords

least mean squares methods; linear systems; neurocontrollers; nonlinear control systems; transversal filters; LMS algorithm; adaptive fast transversal filter algorithm; neural network; nonlinear systems control; Artificial neural networks; Control systems; Convergence; Difference equations; Error correction; Neural networks; Nonlinear control systems; Sampling methods; Testing; Transversal filters;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 2004 IEEE International Conference on

ISSN

1062-922X

Print_ISBN

0-7803-8566-7

Type

conf

DOI

10.1109/ICSMC.2004.1401140

Filename

1401140