Authors: Neha Kapoor; Jyoti Ohri
Addresses: Department of Electrical Engineering, National Institute of Technology, Kurukshetra-136118, India ' Department of Electrical Engineering, National Institute of Technology, Kurukshetra-136118, India
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.
Keywords: genetic algorithms; GAs; neural networks; particle swarm optimisation; PSO; support vector machines; SVM; nonlinear systems; hybrid control; controller design; robotic manipulators; path tracking; robot tracking; robot control; manipulator control; simulation; revolute joints; actuator dynamics; optimal control; control optimisation
International Journal of Computational Systems Engineering, 2016 Vol.2 No.3, pp.121 - 130
Received: 03 Mar 2015
Accepted: 27 Aug 2015
Published online: 08 Sep 2016 *