Indirect adaptive control of a two-link robot arm using regularization neural networks

Abstract

An artificial neural network was developed to control the flexibility of a two-link robot arm. The control scheme consists of two regularization networks plus proportional control. One artificial neural network acts as a system identifier using a recursive algorithm and provides time-related system information to the vibration controller. The second network acts as a vibration controller whose parameters are varied through minimization of an integral-squared-error cost function. A fixed proportional gain feedback system was used to control the rigid body of the manipulator.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>