Stabilization control of an inverted pendulum by complex-valued neuro-fuzzy learning algorithm

Author

Arai, Jin ; Hata, Ryusuke ; Murase, Kazuyuki

Author_Institution

Grad. Sch. of Eng., Univ. of Fukui, Fukui, Japan

fYear

2014

Firstpage

649

Lastpage

654

Abstract

As an automatic generation method of the fuzzy rules, the complex-valued neuro-fuzzy (CVNF) learning algorithm has been suggested. That is a method expanded the conventional neuro-fuzzy (NF) learning algorithm into the complex domain. The purpose of this study is to verify the effectiveness of the CVNF by performing the stabilization control of an inverted pendulum using CVNF, and comparing it with NF. As a result, the control of the inverted pendulum was possible in CVNF with higher precision than in NF.

Keywords

fuzzy control; fuzzy neural nets; learning systems; neurocontrollers; nonlinear control systems; pendulums; stability; CVNF learning algorithm; automatic generation method; complex-valued neuro-fuzzy learning algorithm; fuzzy rules; inverted pendulum; stabilization control; Approximation algorithms; Educational institutions; Fuzzy logic; Gravity; Noise measurement; Training; Training data; Complex-valued neural networks; Fuzzy; Inverted pendulum; Neural networks; Neuro-fuzzy;

fLanguage

English

Publisher

ieee

Conference_Titel

Soft Computing and Intelligent Systems (SCIS), 2014 Joint 7th International Conference on and Advanced Intelligent Systems (ISIS), 15th International Symposium on

Type

conf

DOI

10.1109/SCIS-ISIS.2014.7044664

Filename

7044664