A Mutation Co-evolution Clone Algorithm-Based Dynamic Recurrent Neural Network for Decoupling Control of Parallel Manipulator

Author

Sun, Jian ; Ding, Yongsheng

Author_Institution

Coll. of Inf. Sci. & Technol., Donghua Univ., Shanghai, China

fYear

2009

fDate

6-7 June 2009

Firstpage

142

Lastpage

145

Abstract

Parallel manipulator is very complicate nonlinear, Strong coupling system. In this work, a decoupling controller was presented for parallel manipulator based on an improved dynamic recurrent neural network (IDRNN). IDRNN was trained by a mutation co-evolution clone algorithm. Finally, the control performance of the proposed control approach is illustrated through the comparison studies with robot tracking control approach.

Keywords

manipulator dynamics; nonlinear control systems; position control; recurrent neural nets; coupling system; decoupling control; dynamic recurrent neural network; mutation coevolution clone algorithm; nonlinear system; parallel manipulator; robot tracking control approach; Cloning; Concurrent computing; Control systems; Educational technology; Genetic mutations; Heuristic algorithms; Manipulator dynamics; Nonlinear control systems; Recurrent neural networks; Textile technology; Decoupling control; Dynamic Recurrent Neural Network; Mutation Co-evolution;

fLanguage

English

Publisher

ieee

Conference_Titel

Future Computer and Communication, 2009. FCC '09. International Conference on

Conference_Location

Wuhan

Print_ISBN

978-0-7695-3676-7

Type

conf

DOI

10.1109/FCC.2009.28

Filename

5235684