MODELS FOR PREDICTING THE MAXIMUM HEIGHT OF THE SURFACE ROUGHNESS PROFILE BASED ON AXIAL DRILLING FORCE
The functional performance and in-service quality of products are strongly influenced by surface roughness, which is a direct outcome of material removal processes. In general, surface roughness is function by the input parameters of the machining process and the extent of tool wear, the increase of which leads to an increase cutting forces, torque, acoustic emission level, vibrations, and temperature. Finding the dependence between machining parameters, tool wear indicators, and surface roughness parameters enables real-time prediction of surface quality and contributes to appropriate processing quality. In this study, based on data obtained through experiment conducted using the Taguchi design of experiment, predictive models were developed using multiple regression analysis and artificial neural networks (ANN). These models establish a relationship between input drilling parameters, axial drilling force, and the maximum height of the surface roughness profile.