Nonlinear model predictive control utilizing a neuro-fuzzy predictor

Jonas B. Waller*, Jinglu Hu, Kotaro Hirasawa

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


This paper applies a quasi-ARMAX modeling technique, recently presented in the literature, to a process control framework. The use of this quasi-ARMAX modeling technique in nonlinear model predictive control (NMPC) formulations applied to simple nonlinear process control examples is investigated. The quasi-ARMAX predictor can be interpreted as a neuro-fuzzy predictor, and this neuro-fuzzy predictor is computationally straightforward and has showed excellent prediction capabilities. The predictor is thus well suited for NMPC purposes. Furthermore, the parameters of the neuro-fuzzy model can be argued to have explicit meaning, thus making the procedure of tuning the NMPC system more transparent when using the neuro-fuzzy predictor.

Original languageEnglish
Pages (from-to)39-44
Number of pages6
JournalResearch Reports on Information Science and Electrical Engineering of Kyushu University
Issue number1
Publication statusPublished - 2001 Dec 1
Externally publishedYes


  • Model predictive control
  • Neuro fuzzy models
  • Nonlinear control
  • Nonlinear identification

ASJC Scopus subject areas

  • Computer Science(all)
  • Electrical and Electronic Engineering


Dive into the research topics of 'Nonlinear model predictive control utilizing a neuro-fuzzy predictor'. Together they form a unique fingerprint.

Cite this