|
AUTHOR(S): Jelenka Savkovic Stevanovic
|
TITLE |
 PDF |
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 |
|
