Tribological impact and surface roughness prediction in nano-MQL assisted AA2024 machining

Abstract

In this study, we investigate the tribological influence of incorporating nano MoS₂ particles into the MQL environment during the turning of Aluminium Alloy AA2024. In nano-minimum quantity lubrication (nano-MQL) technique, a very tiny amount of high-performance lubricant is applied straight to the cutting zone. Generally, the lubricant is applied in nanodroplets, which are substantially smaller than standard minimum quantity lubrication (MQL) droplets. Achieving a desired surface roughness is crucial in machining operations. The experiment explores the influence of various machining parameters on surface roughness (R_a). In addition, four machine learning models are used to estimate the surface roughness and compare the experimental value to the anticipated values. For the coefficient of determination (R²), mean absolute percentage error (MAPE), and mean square error (MSE) were all used to assess how accurate the projected values were. Machine learning models Gradient boosting, linear regression and Random Forest has estimated the following R-squared values 1.000, 0.999 and 0.959 respectively. Experimental results reveal that nano-MQL significantly improves surface quality and tool wear, achieving a surface roughness of 0.8399 µm and 0.024 mm tool wear at 339.12 m/min cutting speed, 0.1 mm/rev feed rate, 0.25 mm depth of cut. The average surface roughness decreases by 28% when compared with dry cutting environment.