Towards an accurate estimation of heat flux distribution in metal cutting by machine learning

Abstract

This study presents a machine learning-based approach for inverse identification of heat flux distribution on the rake face of the cutting tools in machining. This approach includes temperature measurements from thermocouples embedded in the tool and heat transfer finite element (FE) simulations to create the data required to train the ML model. The identified heat flux distribution is compared with the distribution from FE machining simulations for validation. The results show a clear potential to estimate the heat flux distribution in machining more efficiently by using an ML-based inverse approach.