Internal model controller with diagonal recurrent neural network for pneumatic robot servo system

Author

Wang, Xuesong ; Peng, Guangzheng ; Xue, Yang

Author_Institution

Dept. of Autom. Control, Beijing Inst. of Technol., China

Volume

3

fYear

2003

fDate

16-20 July 2003

Firstpage

1064

Abstract

A new internal model controller for pneumatic robot servo system is presented, which has a three-layer feedforward neural network as controller (NNC) and a diagonal recurrent neural network (DRNN) as model predictor (NNM). The topology structures and learning algorithm for both NNM and NNC networks are discussed in this paper. The proposed control scheme is applied to a single rod pneumatic cylinder position control system and the experiment results indicate that the system has strong robustness for variation of system parameters and significantly improves the control performances of pneumatic actuators.

Keywords

feedforward neural nets; learning systems; neurocontrollers; pneumatic actuators; pneumatic systems; position control; predictive control; recurrent neural nets; robots; robust control; servomechanisms; diagonal recurrent neural network; internal model controller; learning algorithm; model predictor; pneumatic actuators; pneumatic robot servo system; single rod pneumatic cylinder position control system; system parameters variation; three-layer feedforward neural network; topology structures; Control systems; Feedforward neural networks; Network topology; Neural networks; Position control; Predictive models; Recurrent neural networks; Robot control; Robust control; Servomechanisms;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence in Robotics and Automation, 2003. Proceedings. 2003 IEEE International Symposium on

Print_ISBN

0-7803-7866-0

Type

conf

DOI

10.1109/CIRA.2003.1222144

Filename

1222144