AI-driven prediction of critical depth of cut in ultra-precision machining of single crystal sapphire

Abstract Although sapphire is regarded as a remarkable engineering material for micro- and optical application fields owing to its exceptional mechanical, chemical, and optical properties, it has long been considered difficult to fabricate because of its pronounced anisotropy, particularly in ultra-precision machining. This study employed a two-step approach to predict the critical depth of cut (CDC), the threshold at which cracks appear on the machined surface, in ultra-precision orthogonal cutting of single crystal sapphire with respect to various cutting directions. The first step involved modeling the relationship between cutting forces and process parameters, whereas the second step focused on predicting the critical depth of cut based on the modeled forces. In the first step, machine learning algorithms were employed to predict cutting forces through data pre-processing. To develop an AI-driven model predicting anisotropic cutting-force behavior, both machining process parameters and crystallographic properties of sapphire were used as input variables for training. This model successfully captured the intricate and non-linear relationships governing force variations across distinct crystallographic orientations. In the second step, the predicted cutting forces were used as inputs for a regression model to estimate the CDC. The proposed framework was experimentally verified through orthogonal plunge-cut tests conducted on an ultra-precision CNC machining center with a 1 nm command resolution. This study demonstrated improved predictive accuracy compared with conventional approaches, offering a practical and efficient solution for optimizing ultra-precision machining processes of single crystal sapphire.