Training data reduction for optimisation of fuzzy logic systems for dynamic modeling of robot manipulators by genetic algorithms

Author

Nemes, A. ; Lantos, Béla

Author_Institution

Dept. of Control Eng. & Inf. Technol., Budapest Univ. of Technol. & Econ., Hungary

Volume

3

fYear

2001

fDate

2001

Firstpage

1418

Abstract

The paper reports a novel method for the choice and reduction of the training data set for dynamic modeling of robotic manipulators (RMs) by fuzzy logic systems (FLSs) that are evolved by a genetic algorithm (GA). A multi-population, multi-objective GA is used for structure evolution and optimisation of the FLSs and constants for the precise approximation of the dynamic model (DM) and the simplicity of the FLSs and the complete DM. The initial large set of training data is considerably reduced without decreasing its representative quality

Keywords

data reduction; fuzzy logic; genetic algorithms; identification; manipulator dynamics; approximation; dynamic modeling; fuzzy logic s; multi-population multi-objective genetic algorithms; optimisation; representative quality; robot manipulators; structure evolution; training data reduction; Aerodynamics; Delta modulation; Fuzzy logic; Genetic algorithms; Least squares approximation; Manipulator dynamics; Nonlinear dynamical systems; Robots; Switches; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference, 2001. IMTC 2001. Proceedings of the 18th IEEE

Conference_Location

Budapest

ISSN

1091-5281

Print_ISBN

0-7803-6646-8

Type

conf

DOI

10.1109/IMTC.2001.929438

Filename

929438