Surface Roughness Prediction in CNC Hole Turning of 3X13 Steel using Support Vector Machine Algorithm

This paper presents research on a prediction method of surface roughness in the hole turning process of 3X13 steel. The experimental matrix was designed by using the Central Composite Design (CCD) with four input parameters including cutting speed, feed rate, cutting depth, and tool nose radius. Using the response surface method (RSM), a quadratic poly-nomial model was proposed to predict the surface roughness. Besides, another method that was used to predict surface roughness was the Sup-port Vector Machine (SVM) algorithm. Using SVM, the predicted surface roughness was more accurate than that one when predicting surface roughness using RSM method. Using RSM, the mean absolute error and mean square error between experimental and expect results were 13.37 % and 3.93 %, respectively. While, using SVM, these values were only 2.80 % and 0.17 %, respectively. The SVM can be used to improve the prediction accuracy of surface roughness in hole turning process of 3X13 steel.