Title :
Design of New PID Neural Network Models for the Control of Vertical-Joint Industry Robot
Author :
Ding Du-Kun ; Xie Cun-Xi ; Zhang Tie ; Zou Yan-Biao
Author_Institution :
Coll. of Mech. & Automotive Eng., South China Univ. of Technol., Guangzhou
Abstract :
To meet the needs of variation of industry robot´s joints transfer functions, New PID neural network models are proposed. Firstly, the robot joints´ dynamic analysis has been done and the joints´ transfer functions can be set up. Secondly, the PID controllers at different positions have been designed and the PID controller´s parameters, which are the proportional coefficient, the integral coefficient and the differential coefficient, can be attained. On the basis, the relationship models between the PID parameters and the joints´ angular position, angular velocity, angular acceleration have been set up by the neural network technology. Finally, the PID controllers at the next sample time have been designed by the guide of the neural network models. The result shows that the PID controllers, which are designed by the guide of the models, have fast respond, which can meet the satisfaction of working.
Keywords :
industrial robots; neurocontrollers; three-term control; PID controllers; PID neural network models; industry robot´s joints; transfer functions; vertical-joint industry robot; Computer industry; Electrical equipment industry; Industrial control; Motion control; Neural networks; Robot control; Robot kinematics; Service robots; Three-term control; Transfer functions;
Conference_Titel :
Intelligent Systems and Applications, 2009. ISA 2009. International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-3893-8
Electronic_ISBN :
978-1-4244-3894-5
DOI :
10.1109/IWISA.2009.5072822