Prediction of surface roughness in end face milling based on Gaussian process regression and cause analysis considering tool vibration

Surface roughness is a technical requirement for machined products and one of the main product quality specifications. In order to avoid the costly trial-and-error process in machining parameters determination, the Gaussian process regression (GPR) was proposed for modeling and predicting the surface roughness in end face milling. Cutting experiments on C45E4 steel were conducted and the results were used for training and verifying the GPR model. Three parameters, spindle speed, feed rate, and depth of cut were considered; the experiment results showed that depth of cut is the main factor affecting the surface roughness and regression results showed that the GPR model has a good precision in predicting the surface roughness in different cutting conditions. The prediction accuracy was nearly about 84.3 %. Based on the GPR prediction model, 3D-maps of surface roughness under various cutting parameters could be obtained. It is very concise and useful to select the appropriate cutting parameters according to the maps. As experimental results did not conform to the empirical knowledge, frequency spectrums of the tool were analyzed according to the 3D-maps, it was found that tool vibration is also a crucial factor affecting the machined surface quality.