A machine learning model for flank wear prediction in face milling of Inconel 718

Optimization of flank wear width (VB) progression during face milling Inconel 718 is challenging due to the synergistic effect cutting parameters on complex mechanisms and failure modes. The lack quantitative understanding between VB conditions limits development tool life extension. In this study, a Gaussian kernel ridge regression was employed develop model for using multi-layer physical vapor deposition-TiAlN/NbN-coated carbide inserts with input feature speed, feed rate, axial depth cut, length. showed root mean square error 30.9 (49.7) μm R2 0.93 (0.81) in full fit (5-fold cross-validation test). statistics along cross-plot analyses suggested that had high predictive ability. A new promising condition at speed 40 m/min, rate 0.08 mm/tooth, cut 0.9 mm designed experimentally validated. measured predicted agreed well each other. This thus applicable prediction optimization real operation 718.