Inspite of so universally accepted, control performance by NN depends on many of the varying factors such as output weights. To ensure the functional accuracy of the NN, it is required to have an defined value of these performance effecting factors. Control scheme proposed in this paper uses an emerging optimization technique naming, PSO to get the optimal value of the parameters, naming spread factor and weights of output layer in RBNN. Thus, this hybrid controller possesses the advantageous qualities of RBNN and PSO both. For the further improvement in the basic PSO algorithm, inertia weight factor of PSO is made adaptive.This projected controller has been verified by comparing it with a basic PSO and the basic RBNN controller for the trajectory tracking control of a 2-DOF remotely driven robotic manipulator. To check the robustness of the controller its performance has been checked by incorporating uncertainties naming payload masses and friction. Appropriate conclusions have been drawn in last.
Radial Bias Neural Network (RBNN), Particle Swarm Optimization (PSO), Evolutionary Neural Network (ENN), Hybrid Intelligent Controller, Remotely Driven Links Manipulator, Motion Control of Non-linear systems
Cite this paper
Neha Khurana. (2022) PSO-RBNN Based Control Design for Trajectory Tracking. International Journal of Education and Learning Systems, 7, 65-71