Record Details

Perturbation signal design for neural network based identification of multivariable nonlinear systems

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title Perturbation signal design for neural network based identification of multivariable nonlinear systems
 
Creator KULKARNI, PS
GUDI, RD
 
Subject models
input signal design
hybrid model
neural networks
nonlinear model identification
 
Description The paper focuses on issues in experimental design for identification of nonlinear multivariable systems. Perturbation signal design is analyzed for a hybrid model structure consisting of linear and neural network structures. Input signals, designed to minimize the effects of nonlinearities during the linear model identification for the multivariable case, have been proposed and its properties have been theoretically established, The superiority of the proposed perturbation signal and the hybrid model has been demonstrated through extensive cross validations. The utility of the obtained models for control has also been proved through a case study involving MPC of a nonlinear multivariable neutralization plant.
 
Publisher CANADIAN SOC CHEMICAL ENGINEERING
 
Date 2011-07-19T12:20:28Z
2011-12-26T12:51:12Z
2011-12-27T05:37:42Z
2011-07-19T12:20:28Z
2011-12-26T12:51:12Z
2011-12-27T05:37:42Z
2002
 
Type Article
 
Identifier CANADIAN JOURNAL OF CHEMICAL ENGINEERING, 80(1), 144-152
0008-4034
http://dspace.library.iitb.ac.in/xmlui/handle/10054/5297
http://hdl.handle.net/10054/5297
 
Language en