PSO tuned SVM-SMC Controller for the Trajectory Tracking of a Five Bar Linkage Manipulator System

Abstract

Abstract

Remarkable advantages of SVM make it one of the most widespread and successfully used estimating technique of the era especially for the non-linear systems like robotic manipulators. Control system used in trajectory tracking problems of robotic manipulator is of great importance and hence, accuracy in tracking of manipulator is directly associated to the improvement in the quality of the controller engaged. So, to improve the control performance of the SVM based control technique, it is very important to select the optimal values of its three interdependent free parameters. Hence, in this paper, PSO has been used to get optimal values of these SVM parameters.  Performance of the proposed PSO optimized SVM controller has been validated by checking its performance on a five-bar linkage robotic manipulator system having uncertainties. From validity checking point, simulation results have been compared with the results of the GA optimized SVM and the basic SVM. In last, suitable conclusions have been drawn from the study performed and it has been found that the PSO is showing its supremacy over conventional GA and the PSO optimized SVM based controller is performing best out of the three.

Keywords: Support Vector Machines, Particle Swarm Optimization, Hybrid Intelligent Controllers, Manipulators.