Sliding Mode Control of Robot Manipulators Based on Neural Network Reaching Law

Author

Chen, Zhimei ; Zhang, Jinggang ; Wang, Zhenyan ; Zeng, Jianchao

Author_Institution

Taiyuan Univ. of Sci. & Technol., Taiyuan

fYear

2007

fDate

May 30 2007-June 1 2007

Firstpage

370

Lastpage

373

Abstract

A new neural network sliding mode control method of robot manipulators is proposed, which is formed by incorporating sliding mode variable structure control (SMVSC) and neural network reaching law. The reaching law parameters are regulated adaptively by two feedforward neural networks (FNNs) respectively. This method converts a multi-input system into n single-input systems. Its control arithmetic is simple and easy to implement. It can not only eliminate the chattering of sliding mode control and strengthen the system robustness, but also improve the character of reaching phase. Tracking errors can promptly converge to a neighborhood of zero. The simulation results of two-degree-of-freedom robot manipulators prove the effectiveness of this scheme.

Keywords

control engineering computing; feedforward neural nets; manipulators; variable structure systems; control arithmetic; feedforward neural networks; multi-input system; neural network reaching law; single-input systems; sliding mode variable structure control; two-degree-of-freedom robot manipulators; Arithmetic; Artificial neural networks; Automatic control; Control systems; Manipulators; Neural networks; Nonlinear control systems; Robot control; Robotics and automation; Sliding mode control; feedforward neural network; reaching law; robot manipulators; sliding mode control;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Automation, 2007. ICCA 2007. IEEE International Conference on

Conference_Location

Guangzhou

Print_ISBN

978-1-4244-0818-4

Electronic_ISBN

978-1-4244-0818-4

Type

conf

DOI

10.1109/ICCA.2007.4376382

Filename

4376382