Prediction of Surface Roughness in Plasma Jet Cutting Process Using Neural Network Model

Abstract

A tribological system is a complex non-linear system composed of the elements that are connected structurally and functionally. Tribomechanical system structure is made of elements, characteristics of elements and interaction of these elements. Function of tribomechanical system is the transformation of inputs into the technical output. The aim of this paper is to present an overview of artificial neural networks, its development and possible applications of neural networks in the analysis of the results values of certain parameters in tribological related research. The possibility of artificial neural networks application to solve complex nonlinear problems and to identify bio-tribological characteristics of ceramic materials in terms of abrasion resistance and coefficient of friction is presented.