Hybrid Modeling Approach for Predicting Tool Temperature in Metal Cutting Processes

Excessive heat generated during metal cutting negatively impacts the cutting process by accelerating tool wear through thermal effects and inducing undesirable tensile residual stresses in the workpiece. Accurate prediction of tool temperature is crucial for extending tool life and preserving workpiece integrity. This paper introduces a novel hybrid modeling approach that integrates engagement simulations with regression models derived from orthogonal cutting simulations, enabling fast and efficient temperature predictions. The hybrid model was validated using experimental data from turning processes. While the model demonstrated high accuracy in predicting cutting forces, notable discrepancies were observed between experimental and predicted results for heat transfer to the tool. Despite these limitations, the proposed model shows significant potential for optimizing machining parameters and enhancing productivity with minimal computational effort.