Record Details

The Chylla-Haase problem : a neural network controller

DSpace at IIT Bombay

View Archive Info
 
 
Field Value
 
Title The Chylla-Haase problem : a neural network controller
 
Creator BHAT, A
BANAVAR, RN
 
Description This paper presents the solution to an industrial challenge problem using neural networks. The control problem statement is authored by R. W. Chylla and D. R. Haase and ap pears in a special issue of [1]. The objective is to maintain reaction temperature of a semibatch polymerization reactor at a set point inspite of a variety of conditions ranging from raw material impurity, product variety, repeated batching and varying ambient temperature. Although the reader configuration and control requirements appear simple, the realities of the problem make it a challenging problem to tackle. The controller design methodology is based on process inverse dynamics modelling. The learning data-base for the controller training is generated in an open loop fashion and Graining of the network is carried out off-line by considering the future plant outputs as the reference set points. The learning procedure is not goal directed in that an explicit goal is not defined. This paper follows the design of the controller.
 
Publisher IEEE
 
Date 2011-10-27T14:22:25Z
2011-12-15T09:12:41Z
2011-10-27T14:22:25Z
2011-12-15T09:12:41Z
1996
 
Type Proceedings Paper
 
Identifier PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON CONTROL APPLICATIONS, VOLS 1 AND 2,192-196
0-7803-4104-X
http://dspace.library.iitb.ac.in/xmlui/handle/10054/16323
http://hdl.handle.net/100/2823
 
Source IEEE International Conference on Control Applications,TRIESTE, ITALY,SEP 01-04, 1998
 
Language English