Robust Tool Wear Monitoring Using Systematic Feature Selection in Turning Processes With Consideration of Uncertainties

This paper describes a robust tool wear monitoring scheme for turning processes using low-cost sensors. A feature normalization scheme is proposed to eliminate the dependence of signal features on cutting conditions, cutting tools, and workpiece materials. In addition, a systematic feature selection procedure in conjunction with automated signal preprocessing parameter selection is presented to select the feature set that maximizes the performance of the predictive tool wear model. The tool wear model is built using a type-2 fuzzy basis function network (FBFN), which is capable of estimating the uncertainty bounds associated with tool wear measurement. Experimental results show that the tool wear model built with the selected features exhibits high accuracy, generalized applicability, and exemplary robustness: The model trained using 4140 steel turning test data could predict the tool wear for Inconel 718 turning with a root-mean-square error (RMSE) of 7.80 μm and requests tool changes with a 6% margin on average. Furthermore, the developed method was successfully applied to tool wear monitoring of Ti–6Al–4V alloy despite different mechanisms of tool wear, i.e., crater wear instead of flank wear.