A model for the kinematical analysis of a six degrees of freedom parallel robot

Abstract

The paper presents neural model for the kinematical analysis of six dof parallel robot. The modelling consists of two stages. The first stage is choosing a three-layer perceptron type neural network and it will be trained so that it will learn a set of training data well enough. The second stage means testing the model obtained through training, during the generalization phase. Both tasks was carried out using personal software.