Integrated experimental and machine learning analysis of nano-MQL assisted turning of AA7075-T6

This study comprehensively investigates the machinability performance of dry cutting, minimum quantity lubrication (MQL), and nanoparticle-modified minimum quantity lubrication (nano-MQL) methods in turning AA7075-T6 aluminum alloy. Tool wear mechanisms were evaluated using SEM/EDS analyses; surface roughness, cutting forces, and energy consumption were compared under different cutting parameters. In addition, the obtained data were predicted and evaluated using machine learning-based correlation maps and random forest models. The results demonstrated that the cutting environment plays a decisive role in machining performance. The nano-MQL application reduced the build-up edge (BUE) height at the cutting edge by approximately 29% compared to dry cutting and presented a more stable wear morphology compared to MQL. Surface roughness values ​​were measured at their lowest levels under nano-MQL conditions for all cutting parameters; an improvement of 12–20% compared to dry cutting and 3–10% compared to MQL was achieved. The cutting forces were reduced by an average of 8–19% in the nano-MQL environment compared to dry cutting, while energy consumption savings ranged from 10–53%. The nano-MQL strategy demonstrated high performance and energy efficiency in turning AA7075-T6 alloy by reducing tool wear, improving surface quality, and lowering cutting forces and energy consumption.