Surrogate modelling for reliability assessment of cutting tools

Currently, cutting tool life for machining operations is correlated to process parameters through the widely applied Taylor functions. The latter are valuable expressions in established practice however their generalised nature does not allow accurate prediction of the tool’s service life or optimization of the manufacturing process due to effects of uncertainties in various input variables. These variables should be treated in a stochastic way in order to avoid employment of safety factors for quantification of uncertainty. This paper documents a procedure that allows derivation of analytical expressions for cutting tools performance employing advanced approximation methods and concepts of reliability analysis. Due to the complexity of manufacturing processes surrogate modelling (SM) methods are applied, starting from a few sample points obtained through lab or soft experiments and extending them to models able to predict/estimate the values of control values/indicators as a function of the key design variables, often referred to as limit states.