Comparitive performance analysis of various training algorithms for control of CSTR process using narma-L2 control

Author

Jeyachandran, C. ; Rajaram, M.

Author_Institution

Sathyabama Univ., Chennai, India

fYear

2011

fDate

8-9 Dec. 2011

Firstpage

5

Lastpage

10

Abstract

In recent years, there has been an expansive growth in the study and implementation of neural networks over a spectrum of research domains. The NARMA model is an exact representation of the input-output behaviour of finite dimensional non-linear discrete time dynamical systems in the neighborhood of the equilibrium state. To implement neural network based NARMA-L2 control, first step is modeling of the process for system identification and the second step is the controller design. Neural network based NARMA-L2 controller is implemented for a CSTR process using Levenberg-Marquardt algorithm, Scaled Conjugate Gradient algorithm and their performance are compared.

Keywords

chemical reactors; conjugate gradient methods; control system synthesis; discrete time systems; multidimensional systems; neurocontrollers; nonlinear dynamical systems; process control; Levenberg-Marquardt algorithm; NARMA-L2 control; comparitive performance analysis; continuous stirred tank reactor process; controller design; equilibrium state; finite dimensional nonlinear discrete time dynamical system; neural network; scaled conjugate gradient algorithm; system identification; training algorithm; Artificial neural networks; Process control; CSTR process; Levenberg-Marquardt algorithm; NARMA-L2 control; Scaled Conjucate Gradient algorithm; System identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Trendz in Information Sciences and Computing (TISC), 2011 3rd International Conference on

Conference_Location

Chennai

Print_ISBN

978-1-4673-0134-3

Type

conf

DOI

10.1109/TISC.2011.6169075

Filename

6169075