POSITION CONTROL FOR FLIXEBLE JOINT MANIPULATOR USING ARTIFICIAL NEURAL Network

Abstract

The control of a rotating single flexible link manipulator and/or a two-coupled flexible link manipulator arm is a highly nonlinear problem. Due to the distributed flexibility. The Mechanical system of a flexible joint two-degree manipulator robot arm has been designed and implemented by using stepper motor, movement axis and External Model Circuit (EMC) for controller. The (EMC) includes Buffer, stepper motor driver and programmable Input/Output. This system is controlled by using two method .The first is Artificial Neural Networks (ANN). The neural network has a feed-forward topology and learning algorithm used Back-Propagation. The second is direct method to supply the program with co-ordinates as positioning data for initializing the robot arm.