Intelligent Prediction of Tool Wear in Ball-End Milling Process Based on Dimensionless Cutting Force Ratio

Abstract

This research proposed an in-process tool wear prediction during the ball-end milling process by utilizing the cutting force ratio. The dimensionless cutting force ratio is proposed to cut off the effects of the work material and the combination of cutting conditions. The in-process tool wear prediction model is developed by employing the exponential function, which consists of the spindle speed, the feed rate, the depth of cut, the tool diameter, and the cutting force ratio. The experimentally obtained results showed that the cutting force ratio can be utilized to predict the tool wear of ball-end milling tool. The new cutting tests have been employed to verify the model and the results run satisfaction. It has been proved that the in-process tool wear prediction model can be used to predict the tool wear regardless of the cutting conditions with the highly acceptable prediction accuracy.