Grinding is one of the technologies for surface finishing of large scale of material. This paper deals with grinding of titanium alloy Ti6Al4V with silicon carbide grinding wheel. Ti6Al4V is the most widely used titanium alloy. Its utilization can be found in medical, aerospace, chemical and other industries. This experiment deals with evaluating of surface roughness after grinding. The roughness parameters (Ra, Rz) were measured on each specimen ten times. Also cutting forces were measured while grinding each specimen. All these measured values were evaluated and presentated in graphs.

This paper deals with evaluation of ground surface of Ti6Al4V alloy according to surface roughness. This titanium alloy has large scale of utilization, it is used for implants and surgical instruments. Significant problem during grinding of titanium alloys is generation of large amount of heat which can cause surface cracks, increase hardness of surface and increase of tool wear. Each specimen was ground on surface grinding machine by diferent cutting conditions. The roughness parameters Ra, Rq, Rz and Rt were measured five times on each specimen in each axis (axis y -direction of feed rate, axis x -perpendicular to the feed rate). The values of the roughness parameters (Ra, Rq, Rt and Rz) are presentated in the graphs where we can see the influence of the cutting conditions on these roughness parameters.

This paper investigates the influence of Artificial Neural Network (ANN) architectures on its prediction capability when machining nickel based super alloy. The ANN was employed to determine surface roughness parameter Ra through cutting conditions, tool wear and process monitoring indices such a cutting force components. The ANN structure was optimized by methods like a reduction of input vector parameters, dimensions of input data pattern, combined reduction and modification of hidden layers. Calculated and experimentally measured values were compared for each optimized ANN model. The work concludes that optimization of ANN has significant influence on prediction capability and accuracy for the task proposed.

The single tool grains affect the workpiece surface during grinding in the separated areas of deformation. The elastic and consequently plastic deformations occur at the engagement of grains. The friction of grain and material likewise the friction of elementary chip and grain acts simultaneously. These phenomena are accompanied with an origination of great amount of heat and high pressures and that is the reason for residual stress origin and formation in the ground surface. The residual stress is an important factor in influencing usable properties of machine parts. The stress influences not only the dynamical load capacity of surface but the durability and quality of design units as well. This stress is considered as the source of so called technological notches, having an influence on corrosion resistance, wear resistance, and dimension stability of machine parts.

This paper reports the preparation and characterization of thin transparent nanolayers with phase composition ZrF 4 and different modification of SiO 2 with special focus on affecting the surface roughness of the material and the way of exclusion of the thin nanolayer on the surface of the polished aluminium material. The thin nanolayer was prepared by the sol-gel method. The final treatment based on PTFE was applied on the surface of some samples. This treatment is suitable for increasing wear resistance. The films were characterized with help of SEM microscopy and EDS analysis. The surface roughness was measured with classical surface roughness tester. The results on this theme have already published but not on the polished surface of the aluminium material. The results from the experiment show the problems with application of these nanolayers because a cracks were found on the surface of the material and deformations of the layer after application of the PTFE final layer. The surface layer formation is discussed.