TITLE
ABSTRACT
The theory of fuzzy sets and neural networks was aplied to non-linear process dynamics. In order to perform to state prediction necessary for the neuro- fuzzy logic controller, a neural net was trained to emulate the behavior of the system based on input/output data. Fuzzy model reduces size of the neural network requiring rank to features detected. Fuzzy logic algorithm is generated using production rules for processing corresponding neural network. The algorithm of the generalized delta rule was used to train the neural network minimizimg the sum of squares of the residual. As a case study multivariable control of the etanol recovery plant was used.
KEYWORDS
Control, processing, fuzzy, neural network, model, algorithm.
Cite this paper
Jelenka Savkovic Stevanovic. (2019) A Neuro-fuzzy Artificial Intelligence System. International Journal of Control Systems and Robotics, 4, 21-26
Copyright © 2019 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0