Evaluating the surface characteristics of Stellite -6 super alloy during end milling using titanium nitride coated binary inserts

The prediction of the surface roughness of Stellite 6 super alloy using Physical Vapour Deposition (PVD) coated TiN inserts is shown in this research. End Milling is the manufacturing process that was carried out for the purpose of the investigation. Magnetron sputtering is a procedure that is used to cover the insert with titanium nitride so that it has a higher resistance to wear. When the coat is being applied on the insert, there is also an adjustment made to the parameters of the sputtering process. Stellite 6 is a type of superalloy that is based on cobalt and possesses excellent resistance to corrosion as well as wear. Stellite 6, when coated on steel, reportedly extends the component's useful life by making it more resistant to rust and corrosion. Yet, using a more traditional machining method might be quite challenging when working with this super alloy. Because of this, it is necessary to use inserts that have a higher resistance to wear when carrying out machining. The PVD-Magntron Sputtering method was used to coat the end milling inserts that were utilised for machining over the course of this research. Magnetron sputtering is a process that produces a coating that is not just low friction but also wear resistant. The sputtering power was changed for the coating of the inserts, and the influence of the coating on the machining process was taken into account. For the purposes of this research, the cutting parameters that were chosen were the axial depth of cut, the cutting feed, and the cutting speed. In order to determine whether or not it is effective, the influence of cutting parameters on the surface roughness was analysed and measured. An Artificial Neural Network-based model has been trained, verified, and tested to predict the surface roughness for the aim of verifying the experimental findings. This was done in order to validate the outcomes of the experiments. The outcomes that were predicted by ANN are found to be extremely similar to the findings of the experiments.