Multiple Linear Regression Model for Prediction of Roughness of Grind Surface

Abstract

Multiple linear regression is process of attempting linear relation between response and a set of variables. In the present work, the roughness of grind surface was considered as a regressed variable during cylindrical grinding operation performed on lathe machine. The data was generated after performing experiments with varying regressor variables i.e. grinding wheel rotation (RPM), feed motion (mm/rev), and grinding depth cut (mm). These independent variables are varied in sequential manner using central composite design (CCD) under Response surface methodology (RSM). Regression coefficients are estimated to develop linear regression model. Later on, inference of regressor variables on regressed variable is done to interpret the regression model. The value of R2 and Adjusted R2 are found to be 95% and 94% respectively which suggests that model can be correlated with experimental data. Multicollinearity among regressor variables is done to check the correlations for assurance of interpretation of individual regressor variable over regressed variable. A hypothesis testing was done for predicting roughness of grind surface for 95 % confidence interval and found acceptable. Regression model is validated with additional experimental values of roughness of grind surface and found within acceptable range (max. 10% absolute error). Regression model can be interpreted as reduction in roughness of grind surface with increase in grinding wheel (RPM) whereas it increases with increase in grinding depth (mm) and feed motion (mm/rev).