Experimental and machine learning evaluation of Al2O3 nanofluid lubricants for surface roughness reduction and thermal conductivity enhancement in superfinishing

This study explores the enhancement of surface roughness and thermal conductivity by using the aluminum oxide (Al₂O₃) nanoparticles into Gr-6004 lubricant oil during the superfinishing of gudgeon pins. Nanofluids were synthesized with varying Al₂O₃ volume fractions ranging from 0.1% to 0.8%, and their tribological and thermophysical performance was evaluated. The results revealed a significant improvement in surface finish, with the lowest surface roughness achieved using a 0.1% nanoparticle volume fraction, resulting in a 57% reduction compared to the base oil. Additionally, thermal conductivity improved progressively with increasing nanoparticle concentration, reaching a peak enhancement of 16.66% at 0.8% volume fraction. These improvements are attributed to the synergistic effects of nanoparticle dispersion and the inherent properties of Al₂O₃.The findings demonstrate that Al₂O₃ based nanolubricants offer an alternative to improve both functional surface quality and heat transfer in finishing operations. This approach provides a potential solution for precision applications where conventional lubricants fall short in balancing tribological and thermal demands. Moreover, the results highlight the potential for integrating nanofluid-based strategies into advanced manufacturing practices. The supervised machine learning models were applied to predict surface roughness and thermal conductivity trends, confirming strong alignment with the experimental data and reducing dependence on extensive trial-and-error testing.