Using RSM and GA to Predict Surface Roughness Based on Process Parameters in CNC Turning of AL7075-T6

Surface roughness is a common indicator of the quality characteristics for machining processes. The machining process is more complex, and therefore, it is very hard to determine the effects of process parameters on surface quality in all turning operations. The present work deals with the study and development of a regression model to predict surface roughness in terms of geometrical parameter, nose radius of cutting tool TNMG insert and machining parameters, cutting speed and cutting feed rate for machining AL7075-T6, using Response Surface Methodology (RSM). The surface roughness of machined surface was measured by Mitutoyo Surftest SJ201. The second order mathematical model in terms of machining parameters was developed for predicting surface roughness. The adequacy of the model was checked by employing ANOVA. The direct and interaction effects were graphically plotted which helps to study the significance of these parameters on surface roughness. An attempt has also been made to optimize the surface roughness prediction model using Genetic Algorithm (GA) to optimize the objective function.