This article presents analyses and prediction of machining power during end milling of Inconel 718 for different geometric features namely angular slot, half slot, square pocket, rectangular pocket, and blind hole. The experimental study revealed that among the machining features examined, angular slot required the highest specific cutting energy, while blind holes consumed the least, across different machining conditions. A 40% increase in cutting speed raised specific cutting energy by 4–9%, while a similar increase in feed rate lowered specific cutting energy by 40–44% across all profiles. Doubling depth of cut reduced specific cutting energy by 50% for angular slots, half slots, square pockets, and rectangular pockets, but increased it for blind holes. Power prediction models were developed using multisensor data, employing two machine learning and two deep learning architectures. The performance of the four power prediction models was compared for all geometric profiles using both raw data and statistical feature data extracted from machining signals from force dynamometer, accelerometer, and acoustic emission (AE) sensors. Long–Short-Term Memory model outperformed other models in case of raw data for all geometric profiles. The Random Forest Regression method consistently fared better for power predictions models developed based on feature-extracted data. Predictive models trained without AE sensor data performed better than those trained with AE.
Read full abstract