Using Multiple Linear Regression and Artificial Neural Network to Predict Surface Roughness in Turning Operations

Quality of surface roughness has a great impact on machine parts during their useful life. The machining process is more complex, and therefore, it is very hard to develop a comprehensive model involving all cutting parameters. In this paper, the surface roughness is measured during turning operation at different cutting parameters such as speed, feed rate, and depth of cut. Two mathematical models are developed to predict the surface roughness and to select the required surface roughness by using the Multi-regression model and Artificial Neural Networks (ANN). To test the developed models, 27 pieces of steel alloy HRC15 were operated and the roughness of their surfaces measured. The results showed that the ANN model estimates the surface roughness with high accuracy compared to the multiple regression model with the average deviation from the real values of about 1%.