Open AccessDevelopment of synthetic methodology of neuro-fuzzy controller adjusted by genetic algorithm
Author(s) -
Нина Андреевна Первушина,
Д. Е. Доновский,
Albina Khakimova
Publication year - 2018
Publication title -
vestnik koncerna vko «almaz - antej»
Language(s) - English
Resource type - Journals
ISSN - 2542-0542
DOI - 10.38013/2542-0542-2018-4-82-90
Subject(s) - controller (irrigation) , genetic algorithm , control theory (sociology) , computer science , fuzzy logic , inverted pendulum , object (grammar) , neuro fuzzy , fuzzy control system , algorithm , control (management) , control engineering , artificial intelligence , engineering , machine learning , nonlinear system , biology , physics , quantum mechanics , agronomy
The paper focuses on a synthetic methodology of a neuro-fuzzy controller adjusted by genetic algorithm for a dynamic control object. An algorithm for controller synthesis and a genetic algorithm for adjusting the controller's parameters have been developed. The methodology has been tested on the classical problem of stabilizing a vertical pendulum on a mobile trolley. The results obtained confirm the efficiency of the methodology and allow for the conclusion that the neuro-fuzzy controller when appropriately adjusted ensures high quality of the stabilization system, even if there are random disturbances on the dynamic object