Optimization of Turning Parameters for Surface Roughness Using Rsm and Ga

The paper presents an experimental study of roughness characteristics of surface profile generated in CNC turning of AISI 1040 mild steel and optimization of machining parameters based on genetic algorithm. The three level rotatable central composite designs are employed for developing mathematical models for predicting surface roughness parameters. Response surface methodology is applied successfully in analyzing the effect of process parameters on different surface roughness parameters. The second order mathematical models in terms of machining parameters are developed based on experimental results. The experimentation is carried out considering three machining parameters, viz., depth of cut, spindle speed and feed rate as independent variables and three different roughness parameters, viz., centre line average roughness, root mean square roughness and mean line peak spacing as response variables. It is seen that the surface roughness parameters decrease with increase in depth of cut and spindle speed but increase with increase in feed rate. The models selected for optimization have been validated with F-test. The adequacy of the models of surface roughness has been established with Analysis of Variance (ANOVA). An attempt has also been made to optimize the cutting parameters using genetic algorithm to achieve minimum surface roughness.