Search

Milling is one type of cutting process that is most often used in the manufacturing industry. Flank wear is a wear phenomenon on the cutter that usually occurs in milling. This wear can affect the accuracy of the product and the quality of the cutting finish surface and can cause damage to the cutting tool. This paper will discuss how to improve the accuracy of cutting tool wear predictions based on vibration signals obtained from the machining process. The signals from the milling process are decomposed by Variational Mode Decomposition (VMD) method before being applied to the machine learning algorithm. As a comparison level of accuracy, the root mean square error (RMSE) parameter is used to determine the error between the actual value and the predicted value of the trained model. The results of the experiments show that using the VMD decomposition feature can improve the performance of the Support Vector Machine (SVM) algorithm in predicting tool wear when compared to those using the time and frequency domain features or those using only the time domain features [ABSTRACT FROM AUTHOR]