SELF ADJUSTING RBNN FOR TWO LINK AND THREE LINK MANIPULATOR

Neha Kapoor, Jyoti Ohri

Abstract: This paper addresses the solution to the robust trajectory tracking problem in presence of uncertainties and disturbances. In this research, area worked upon is the development of an intelligent hybrid controller to ensure the accurate trajectory tracking of a robotic manipulator. The ONCC is a hybrid intelligent controller made with the combination of Radial Bias neural network (RBNN) and particle swarm optimization (PSO). PSO is used to get the optimized value of the spread factor. To check the robustness of the ONCC, firstly is applied to a 2 link and then to a 3 link SCARA manipulator tracking various trajectories and with different disturbances and uncertainties in the system. MATLAB platform has been used for simulation purpose. For validation purpose, results of the ONCC have been compared with the control results of original RBNN and the basic PD controller. Paper has been finished with the appropriate conclusions.

Keywords: Radial Bias Neural Network (RBNN), Particle Swarm Optimization (PSO), Hybrid Intelligent Controllers.

DOI: https://doi.org/10.15623/ijret.2014.0326004