On-line learning fuzzy relational model based dynamic matrix control of an openloop unstable process

M. Demircan, M.C. Camurdan, Bruce Postlethwaite

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Fuzzy Relational Models (FRM) are used when implementing a dynamic matrix control (DMC) algorithm on a nonlinear process which exhibits multiplicity of steady state solutions. Following Ozkan, Ozkan and Camurdan, the openloop unstable equilibrium point of the process is first stabilized by an analog proportional only controller. DMC is then used to control this stabilized system. Both servo and regulatory control are investigated. Locally and globally obtained fixed and globally obtained variable FRMs are used. In some runs the recursive least squares (RLS) algorithm is also used to update the relational array so as to provide on-line learning. It is shown by simulations that FRMs that are identified in a local region performed as well as those that are identified in the whole operating region. On the other hand the performance of the system was found to be poor if a variable model is used.
Original languageEnglish
Pages (from-to)421-428
Number of pages7
JournalChemical Engineering Research and Design
Volume77
Issue number5
DOIs
Publication statusPublished - Jul 1999

Keywords

  • dynamic matrix control
  • fuzzy relational models
  • adaptive control

Fingerprint Dive into the research topics of 'On-line learning fuzzy relational model based dynamic matrix control of an openloop unstable process'. Together they form a unique fingerprint.

  • Cite this