Abstract
The aim of this paper is based on neural network model for tribological analyses of an Epoxy composite system. The created epoxy based composites with aramidic powders, were tribologically tested with diverse parameters in order to obtain the following properties: wear rate and friction coefficient. With all the studied tribological properties was created a Neural Network (NN) model. The created NN model can perform optimisations for concentration of aramidic powder in final used composites for different domains of applications. Keywords: epoxy composites, bloc on ring, friction coefficient, neural network analysis, optimisations