Optimisation of Energy Consumption in Milling of Inconel 718 Alloy and Prediction Model with Machine Learning

Authors : Hakan Yurtkuran, Güven Demirtaş, Birol Yazarlı, Ahmet Sertan Özpak, Semih Zorlu

Pages : 296-307

Doi:10.52795/mateca.1792370

View : 99 | Download : 163

Publication Date : 2025-12-30

Article Type : Research Paper

Abstract :This study aims to optimize power consumption observed while milling Inconel 718 superalloy—well known for its poor machinability—and to develop machine learning-based prediction models. Experiments were carried out on a Taksan TMC 500 V CNC milling machining center at three cutting speeds (40, 60, and 90 m/min) under four distinct cutting conditions: dry, Minimum Quantity Lubrication (MQL), cryogenic, and cryogenic+MQL. Energy consumption was monitored in real-time using a KAEL Multiser signal analyzer and the collected data were analyzed through ANOVA and regression approaches. The ANOVA results revealed that cutting speed is the most significant factor influencing energy demand (p<0.001), whereas cooling/lubrication strategies exhibited no statistically significant effect. To address class imbalance the dataset was augmented via a SMOTE-based method and ensemble and regression-based ML models (Random Forest, Gradient Boosting, Linear Regression) were trained for power prediction. The findings indicated that the Gradient Boosting algorithm consistently achieved superior accuracy across all cutting environments with performance levels reaching R²≈0.97 and RMSE≈7 W. Results indicate that combining experimental data with computational methods is effective for decreasing energy consumption in machining and advancing sustainable production goals. The proposed methodology contributes to enhancing both efficiency and environmental sustainability in the industrial processing of Inconel 718.
Keywords : Frezeleme, Enerji Tüketimi, MMY, Makine Öğrenimi, SMOTE

ORIGINAL ARTICLE URL