AI-driven wear monitoring of PVD TiAlN coated carbide insert in sustainable machining of Hastelloy C276: An industry 4.0 perspective

Abstract

• AI-based predictive models, including DNN, XGBoost, and SVR, were utilized to monitor wear on PVD TiAlN-coated carbide inserts. • Nanofluid-enhanced MQL with 0.6 % alumina concentration effectively reduced tool wear and improved lubrication efficiency. • XGBoost outperformed other models with an R² of 0.94, MSE of 0.0016, and RMSE of 0.04, highlighting its robustness for wear prediction. This research explores the application of AI-based predictive models for monitoring wear on PVD TiAlN-coated carbide inserts during the sustainable machining of Hastelloy C276. A minimum quantity lubrication (MQL) system, enhanced with alumina nanofluids, is employed to reduce wear and improve cooling efficiency. Machine learning techniques, including deep neural networks (DNN), extreme gradient boosting (XGBoost), and support vector regression (SVR), were utilized to predict tool wear based on machining parameters. Experimental findings demonstrate that nanofluid-enhanced lubrication effectively minimized tool wear, with the optimal alumina concentration determined to be 0.6 %. Among the models, XGBoost outperformed the others, achieving an R 2 value of 0.9924, a RMSE of 0.002, a MAE of 0.0017, and a MAPE of 0.6 %. Sensitivity analysis indicated that cutting speed had the most significant influence on wear, with a Spearman correlation coefficient of 0.94. This study underscores the potential of combining sustainable lubrication techniques with AI-driven wear monitoring to improve tool longevity and machining efficiency, supporting the principles of Industry 4.0.