Intelligent Prediction of Surface Micro-hardness after Milling Based on Smooth Support Vector Regression

摘要

Surface micro-hardness is a major factor affecting the performance of a component. The machined surface micro-hardness is strongly influenced by the external conditions during the machining processes. In machining process development, it is highly desirable to predict the micro-hardness of a machined surface. For this purpose, an intelligent prediction model using smooth support vector regression (SSVR) of the entire end milling system is developed to investigate the influence of cutting conditions on the surface micro-hardness of the machined workpiece. Our observations and conclusions are mainly concentrated on the effect of surface micro-hardness with a set of constant parameters, such as cutting speed, feed rate, cutting depth and milling cutter. The data are analyzed by different experiments in contrast: BP, standard SVR and SSVR based model respectively. The results of analysis demonstrate that the SSVR based model is faster in speed, higher in accuracy than the other two. The prediction model leads to a good understanding of the influence of cutting conditions on surface micro-hardness in end milling.