Optimization of Material Removal Rate and Surface Roughness of AISI 316L under Dry Turning Process using Genetic Algorithm

Abstract

The turning process is one of the most common machining operations in various manufacturing industries. It is conducted by eroding the rotating workpiece using a tool that moves in a linear motion. This study examined the genetic algorithm (GA) as the optimization method for the dry turning process of AISI 316L. GA is a meta-heuristic method that imitates the principle of natural selection, in which the most suitable individuals are selected for reproduction to produce the next generation of offspring. The optimization process was started by executing the selected experimental design based on the process parameters and their levels. The tool nose radius, cutting speed, feed rate, and depth of cut were selected as the process parameters in this study. The outcome of this step was a fitness function that explained the relationship between the process parameters and the material removal rate (MRR) or the surface roughness (SR). GA used the fitness function to produce the optimal process parameters with the highest MRR and the lowest SR in a separate optimization process. The optimization methodology developed in this study can be utilized to predict the optimum value of the MRR and SR for the dry turning process and with less than a 7% deviation from the actual value.