Identification of a nonlinear multi stand rolling system by a structured recurrent neural network

Author

Hintz, Christian ; Rau, Martin ; Schröder, Dierk

Author_Institution

Inst. for Electr. Drive Syst., Tech. Univ. Munchen, Germany

Volume

2

fYear

2000

fDate

2000

Firstpage

1121

Abstract

In this paper, the authors present an identification method for mechatronic systems consisting of a linear part with unknown parameters and an unknown nonlinearity (systems with an isolated nonlinearity). A structured recurrent neural network is used to identify the unknown parameters of the known signal flow chart. The novelty of this approach is the simultaneous identification of the parameters of the linear part and the nonlinearity. Prior structural and parameter knowledge are used in a natural way

Keywords

identification; mechatronics; motion control; nonlinear control systems; process control; recurrent neural nets; rolling mills; identification method; known signal flow chart; mechatronic systems; nonlinear multi stand rolling system identification; parameter knowledge; structural knowledge; structured recurrent neural network; unknown parameters; Control nonlinearities; Couplings; Flowcharts; Mechatronics; Neural networks; Neurofeedback; Optimal control; Recurrent neural networks; Signal processing; State estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Industry Applications Conference, 2000. Conference Record of the 2000 IEEE

Conference_Location

Rome

ISSN

0197-2618

Print_ISBN

0-7803-6401-5

Type

conf

DOI

10.1109/IAS.2000.881972

Filename

881972