Modeling of Surface Roughness in Plasma Jet Cutting Process of Thick Structural Steel

Today highly competitive market and demands for obtain high surface finish and machining of complex shape geometries replace conventional machining processes with non-conventional. Plasma jet cutting is one of these non-conventional processes that primary uses a thermal energy of highly ionized gas to cut specified material and blow molten metal away. Main advantages of plasma jet cutting process are high speed of cutting, cutting different types of materials, the quality of cut and moderate to low investment costs. This paper presents experimental results concerning the surface roughness variation at plasma jet cutting of structural steel S235JRG2 plate thickness of 15 mm. Using the experimental data artificial neural network (ANN) model was developed in order to predict the surface roughness in terms of two input parameters, cutting current and cutting speed. After the prediction accuracy of the developed model was validated, the model was used for analyzing influence of input parameters on process response values.