Tool Wear and Surface Quality Monitoring Using High Frequency CNC Machine Tool Current Signature

In this paper a machine learning approach for tool wear monitoring (TWM) and surface quality detection is proposed using high frequency current samples of a CNC turning machine main terminal. Significant frequency based features related to tool wear and surface quality are selected by univariate filter methods. Supervised machine learning methods including Support Vector Machine (SVM) and Random Forest Ensemble (RFE) are used to estimate tool wear and surface quality. Best hyper-parameter combinations of the proposed models are evaluated and found by grid search methods. Experimental studies are conducted on a CNC turning machine using a test work piece and the classification and accuracy results are presented. The presented methodology makes the set up of an on-line system for tool condition monitoring and an estimation of the work piece surface quality by the use of inexpensive and easy to install measurement hardware possible.