Optimization of Process Parameters for Turning Operation on D3 Die Steel

Abstract

This research aims to determine the optimal Surface Roughness for machining D3 die steel alloy with uncoated carbide inserts. It will do this by studying the most efficient turning parameters, such as cutting speed, feed, and depth of cut. Models have been generated using a variety of statistical modeling approaches, including Genetic Algorithm with Response Surface Methodology. This research aimed to use the regression technique to develop a model that could predict surface roughness. It has also been investigated if the Taguchi Technique may be used to optimize process parameters. To decide the primary boundaries affecting Surface Unpleasantness, we used Signal-to-Noise (S/N) ratio and Analysis of Variance (ANOVA) tests. This paper aims to contribute valuable insights into achieving the best Surface Roughness outcomes in the machining process for D3 die steel alloy with Uncoated Carbide Inserts. The utilization of Genetic Algorithm and Response Surface Methodology showcases a robust approach for modelling intricate parameter interactions. If you know the values of the parameters, you may use the Regression Technique to forecast the surface roughness. Process parameter optimization may be made more systematic with the use of the Taguchi Technique.