Predictive Controller Based on Fuzzy-Neural model with multiple recurrent nodes

Margarita Terziyska, Yancho Todorov, Michail Petrov

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

A nonlinear predictive controller based on a recurrent neuro-fuzzy model is presented in this paper. Neuro-fuzzy model is realized with the T-S inference mechanism and includes global and local (after the rules layer) feedbacks. The proposed model is coupled with an optimization approach for computation of the control actions into a model based predictive controller. The efficiency of the proposed control policy is proved by simulation experiments to control a Continuous Stirred Tank Reactor (CSTR).
Original languageEnglish
Title of host publicationInternational Conference "FOOD SCIENCE, ENGINEERING AND TECHNOLOGIES – 2013“, 18-19 October 2013, Plovdiv
Pages63-68
VolumeLX
Publication statusPublished - 2013
MoE publication typeA4 Article in a conference publication
EventFood Science, Engineering and Technologies - Plovdiv, Bulgaria
Duration: 18 Oct 201319 Oct 2013

Conference

ConferenceFood Science, Engineering and Technologies
CountryBulgaria
CityPlovdiv
Period18/10/201319/10/2013

Keywords

  • process control
  • artificial intelligence
  • fuzzy systems
  • neural networks
  • optimizaiton

Fingerprint Dive into the research topics of 'Predictive Controller Based on Fuzzy-Neural model with multiple recurrent nodes'. Together they form a unique fingerprint.

Cite this