An adaptive neuro-fuzzy architecture for intelligent control of a servo system and its experimental evaluation

Author

Aras, Ayse Cisel ; Kayacan, Erdal ; Oniz, Yesim ; Kaynak, Okyay ; Abiyev, Rahib

Author_Institution

Dept. of Electr. & Electron. Eng., Bogazici Univ., Istanbul, Turkey

fYear

2010

fDate

4-7 July 2010

Firstpage

68

Lastpage

73

Abstract

In this paper the development of an adaptive neuro-fuzzy architecture for the speed control of a servo system with nonlinear load is presented. The synthesis of the structure is described and a learning algorithm for the neuro-fuzzy control system is derived. The supervised learning algorithm is used to train the unknown coefficients of the system, and then the fuzzy rules of the neuro-fuzzy system are generated. A number of simulation studies are carried out, and the results are compared with those obtained with a PI controller tuned using desired time response characteristics. These and the experimental studies presented show that the neuro-fuzzy control system has a better control performance than the conventional PI controller.

Keywords

PI control; adaptive control; control system synthesis; fuzzy neural nets; intelligent control; learning (artificial intelligence); neurocontrollers; servomechanisms; velocity control; DC motor; PI control; adaptive neuro-fuzzy architecture; fuzzy rules; intelligent control; servo system; speed control; supervised learning algorithm; Brushless DC motors; Load modeling; Servomotors; Torque;

fLanguage

English

Publisher

ieee

Conference_Titel

Industrial Electronics (ISIE), 2010 IEEE International Symposium on

Conference_Location

Bari

Print_ISBN

978-1-4244-6390-9

Type

conf

DOI

10.1109/ISIE.2010.5637706

Filename

5637706