Comparative Prediction and Modelling of Surface Roughness in Milling of AL-7075 Using Regression Analysis and Neural Network

Abstract

The surface roughness (Ra) of machine parts effects significantly the fatigue strength, corrosion resistance and aesthetic appeal of them. Therefore, Ra is an important parameter in manufacturing process. In this research, Ra of Aluminum Al-7075 in milling process is predicted and minimized. Ra minimization has to be in standard mathematical model formula. In order to predict minimum Ra value, developing a model is taken to deal with real Ra experimental data of the milling process. Two model approaches which are Regression and Artificial Neural Network (ANN) are proposed for minimum Ra value prediction. The studied process parameters were: speed of cut, feed rate and depth of cut. Regression and ANN were used to investigate the effect of these parameters on Ra through 27 cases of study, where full Analysis of Ra besides to determining regression equation and optimum process parameters are achieved. This study results show that each of Regression & ANN models had reduced minimum Ra in very similar value by 0.987. This similarity reflects the promise approach of this study in predicting Ra in AL-7075 milling, unlike previous studies that either the regression or the Artificial intelligence method was the dominant in results.

Modeling and Prediction of Surface Roughness in the End Milling Process using Multiple Regression Analysis and Artificial Neural Network

“…For prediction of surface roughness, ANN model showed better results than multiple regression analysis. Hossein et al [12], in their research, predicted and minimized surface roughness in process of milling. They used two model approaches which are Artificial Neural Network and Multiple regression analysis.…”