High-performance turning of WCu alloy using cryogenically treated tool with predictive machine learning approach and...

This research work provides an in-depth machinability evaluation of WCu alloy under variable cutting circumstances using both cryogenically treated and conventional tungsten carbide tools. Turning experimentations were designed using a Taguchi L27 orthogonal array to assess the effect of cutting speed, feed rate and depth of cut on surface roughness, tool wear, and cutting force. Cryogenic treatment at - 196 °C for 24 h considerably improved tool hardness and edge stability, which results in lower wear, reduced cutting forces, and better surface finish compared to non-treated tools. Regression modelling, residual diagnostics, and advanced machine learning algorithms including Linear Regression, Random Forest, Support Vector Regression, and Artificial Neural Networks were used to predict individual machining responses. Random Forest attained the highest prediction accuracy for cutting force (R² = 0.96 under cryogenic conditions), whereas tool wear prediction showed moderate accuracy (R² ≈ 0.5). Surface roughness prediction was poor for all models, which indicates impact of unmeasured dynamic factors. Grey Relational Analysis identified the optimal machining parameters as 1200 rpm cutting speed, 0.04 mm/rev feed rate, and 0.5 mm depth of cut. Grey Relational Analysis integrated multi-response outcomes and revealed that optimal machining parameters for both tool types are 1200 rpm cutting speed, 0.04 mm/rev feed rate, and 0.5 mm depth of cut. Overall, the study confirms that cryogenic treatment substantially enhances machinability of WCu alloy and, when combined with data-driven predictive modelling, provides a robust pathway for optimizing precision turning operations in industrial applications.