logo
CanyamAI summaries for academic research
language
MobileMobile
  • Phone FeatureWeChat Mini Program
EnglishEnglish
noticeNotice
BlogBlog
delete
arrow
Return

Resolving problems in closed loop nonlinear process identification using IRN

delete1996-10-01
delete7
PRE
AI
Y
Yi Cheng
T
Thomas W. Karjala
D
D. M. Himmelblau
DOI：10.1016/0098-1354(95)00243-Xdelete
deleteOriginal
deleteOriginal request for help
deleteShare
deleteSave
Abstract

Abstract

En 中文
The feasibility of identifying a nonlinear dynamic process model by an IRN (internal recurrent neural network) using the process input and output data collected under closed loop control is considered in the paper. Conditions under which an IRN can be used for identification under closed loop control, and the problem of setting the initial conditions of an IRN, are discussed. A method to improve the accuracy of prediction of an IRN is proposed. Two simulation studies, one for a CSTR, and another for a packed distillation column, show that an IRN is a promising model for identifying dynamic nonlinear processes under closed loop control. (C) 1996 Published by Elsevier Science Ltd
Keywords:
SYSTEMS
AI Summary

AI Summary

Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.

Journal

C
Computers and Chemical Engineering
IF:
3.9
Papers:
8.1K
Citations:
1.7W

Organization

No organization information available