GA and PSO optimised SVM controller for manipulator
by Neha Kapoor; Jyoti Ohri
International Journal of Computational Systems Engineering (IJCSYSE), Vol. 2, No. 3, 2016

Abstract: Robotic manipulators have inherent characteristics of being highly nonlinear and strongly coupled. Accuracy in the path tracking of robotic manipulator depends upon the characteristics and capability of the control system used for it. Hence, perfection in tracking of manipulator is directly associated to the improvement in the quality of the controller engaged. It has been observed from literature that with optimal values of control parameters, SVM is one of the most emerging control schemes for nonlinear systems. Performance of the SVM-based controller highly relies on the perfect selection of its free parameters. In this paper, GA and PSO have been used to get optimal values of these SVM parameters. A simulation study has been performed on a two DOF robotic manipulator with independent revolute joints with actuator dynamics. From validity checking point, simulation results have been compared with the results of the basic SVM and NN-based controllers with friction as disturbance. In last, suitable conclusions have been drawn from the study performed and it has been found that the PSO optimised SVM-based controller is performing best.

Online publication date: Thu, 08-Sep-2016

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computational Systems Engineering (IJCSYSE):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com