Experimental and machine learning comparison for measurement the machinability of nickel based alloy in pursuit of sustainability

Abstract

Inconel 718 super alloy, which is widely used in the aerospace industry, has a high fracture resistance, and withstand to high temperatures. The alloy contains mainly Nickel, Chromium and Molybdenum elements in its chemical composition put it among difficult to cut materials. In this context, this study aims to improve the machinability of Inconel 718 superalloy by examining the effect of dry and MQL machining environments while measuring machinability indicators during milling. Tribological aspects considered since the wear, friction and lubrication behavior have a dramatic impact on responses such as tool wear, surface integrity and chip morphology. Microstructural and graphical results were assessed in terms of varying levels of cutting parameters and lubrication conditions. Comparison analysis between MQL and dry media indicated that MQL produces better surface topography and chip morphology, longer tool life in addition to improvement on surface roughness (up to 23.7 %) and cutting temperatures (up to 27.4 %). The root mean square error (RMSE) and coefficient of determination (R2) metrics were utilized to evaluate the findings in the course of machine learning. According to the mean and 95 % confidence interval of RMSE, error rates were found to be good and R2 varied between 67 % and 98 %. Predicted results are in a good agreement with the experimental data which indicated the applicability of machine learning algorithms on sustainable methods of machining.