Anh Thang Nguyen

This study investigates the effects of cutting speed (Vc), feed rate (fz), and depth of cut (ap) on surface roughness (Ra) and Material Removal Rate (MRR) in turning operations. Fifteen experiments were conducted with Vc ranging from 100 to 180 m/min, fz from 0.050 to 0.120 mm/rev, and ap from 0.050 to 0.200 mm. Analysis of Variance (ANOVA) revealed that fz is the most influential parameter on Ra, accounting for 49.69% of the total variation, while Vc and ap show no statistically significant effects at the 95% confidence level. In contrast, MRR is significantly affected by all cutting parameters, with depth of cut contributing the most (54.27%), followed by fz (25.56%) and Vc (12.31%). Logarithmic regression models were developed to describe the responses, yielding an adjusted coefficient of determination of 0.655 for Ra and 1.000 for MRR. A multi-objective optimization problem was formulated to minimize Ra and maximize MRR, and an extended Pareto front comprising nine non-dominated solutions was obtained. The Pareto solutions were ranked using the Evaluation based on Distance from Average Solution (EDAS) method, yielding the optimal compromise solution at a Vc value of 180 m/min, fz equal to 0.085 mm/rev, and ap equal to 0.200 mm, with an Ra value of 0.525 µm and an MRR value of 3060 mm³/min. The proposed framework effectively balances surface quality and productivity in turning operations.

Dry hard turning of heat-treated SKD11 tool steel offers a sustainable alternative to grinding but poses significant challenges in maintaining surface integrity and tool life due to severe wear and high cutting temperatures. This study develops a physically interpretable, AI-assisted modeling framework that integrates empirical and machine learning methods to predict and optimize surface roughness ([ ]), tool wear ([ ]), and material removal rate (MRR). Seventeen controlled experiments were conducted under varying cutting speed ([ ]), feed rate ([ ]), and depth of cut ([ ]) conditions using CBN inserts (TNGA160404–CBN1020) in dry cutting. A hierarchical modeling approach was established, where [ ] acts as an intermediate variable linking process parameters to [ ], while MRR was computed analytically. The Response Surface Methodology (RSM) provided the baseline regression models with [ ] for [ ] and [ ] for [ ] when wear was included. Support Vector Regression (SVR) further enhanced prediction accuracy to [ ], demonstrating strong nonlinear capability and physical consistency. Multi-objective optimization using the MOPSO–TOPSIS framework achieved a balanced solution at [ ]–160[ ]m/min, [ ]–0.07[ ]mm/rev, and [ ]–0.15[ ]mm, resulting in approximately 10% reduction in surface roughness, 12% reduction in tool wear, and 8% improvement in productivity compared with baseline conditions. The proposed framework bridges physical modeling and AI-based prediction, offering a robust, explainable tool for adaptive control in precision hard turning and a reliable foundation for intelligent machining under limited-data environments.