Title :
On the use of recurrent neuro-fuzzy networks for predictive control
Author :
Sadeghian, A.R. ; Lavers, J.D.
Author_Institution :
Dept. of Math, Phys. & Comput. Sci., Ryerson Univ., Toronto, Ont., Canada
Abstract :
This paper presents the application of recurrent neuro-fuzzy networks for the predictive control of nonlinear, multivariable, complex systems such as electric arc furnaces. The main objectives are to investigate the capability of adaptive neuro-fuzzy networks to predict the V-I characteristics of electric arc furnaces and to compare the performance of the proposed predictors with that of the feedforward neuro-fuzzy predictors. The novelties of this work are to propose the notion of approximate prediction and to implement it using a recurrent neuro-fuzzy structure suitable for long-term prediction. Successful implementations of recurrent neuro-fuzzy predictors are described and their performances are illustrated
Keywords :
adaptive control; arc furnaces; fuzzy control; fuzzy neural nets; large-scale systems; multivariable control systems; neurocontrollers; nonlinear control systems; predictive control; recurrent neural nets; V-I characteristics prediction; approximate prediction; electric arc furnaces; feedforward neuro-fuzzy predictors; long-term prediction; nonlinear multivariable complex systems; predictive control; recurrent neuro-fuzzy networks; Adaptive systems; Furnaces; Fuzzy logic; Fuzzy neural networks; Inference algorithms; Neural networks; Predictive control; Recurrent neural networks; Steel; Voltage fluctuations;
Conference_Titel :
IFSA World Congress and 20th NAFIPS International Conference, 2001. Joint 9th
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-7078-3
DOI :
10.1109/NAFIPS.2001.944257
