A Model-Free Neuro-Fuzzy Predictive Controller for Compensation of Nonlinear Plant Inertia and Time Delay

Article type: Research Article

Authors: Yordanova, Snejana^{; *} | Ichtev, Alexandar

Affiliations: Faculty of Automation, Technical University of Sofia, 8 Kliment Ohridski Blvd., Sofia 1000, Bulgaria. E-mails: [email protected], [email protected]

Correspondence: [*] Corresponding author.

Abstract: The aim is to develop simple for industrial use neuro-fuzzy (NF) predictive controllers (NFPCs) that improve the system performance and stability compensating the nonlinear plant inertia and time delay. A NF plant predictor is trained from real time plant control data and validated to supply a main model-free fuzzy logic controller with predicted plant information. A proper prediction horizon is determined via simulation investigations. The NFPC closed loop system stability is validated based on a parallel distributed compensation (PDC) approximation of the NFPC. The PDC can easily be embedded in industrial controllers. The proposed approach is applied for the real time air temperature control in a laboratory dryer. The improvements are reduced overshoot and settling time.

Keywords: fuzzy logic control, genetic algorithms, Lyapunov stability, fuzzy logic plant predictor, real time temperature control

Journal: Informatica, vol. 28, no. 4, pp. 749-766, 2017