Characterizing Machining Indicators with Machine Learning Models Under Cellulose Nanocrystal and Graphene-Based Nanofluid Conditions

With outstanding physical properties such as superior ductility and strength, ultra-high strength steels (UHSS) have recently been broadly preferred as industrial materials. In this context, this study investigates the machinability of UHSS S1100 material under different cooling/lubricating conditions. The efficacy of environmentally friendly cooling/lubricating techniques, namely dry, MQL and nanofluid cellulose nanocrystal and graphene nanoplatelets-based MQL, was investigated with different cutting parameters. This novel study evaluated the influence of machining conditions and parameters on responses such as tool wear, surface roughness, energy consumption, cutting temperatures and chip morphology while incorporating machine learning. In addition, correlation analysis was performed with machine learning and the relationships between input and output parameters were evaluated. Lubricating methods such as pure MQL, cellulose nanocrystal and graphene nanoplatelets-based nanofluid are pivotal in heat transfer management and decrease cutting temperatures, tool wear and energy consumption. NGPN-based nanofluid and pure MQL environments at low feed rates and high cutting speeds resulted in the best surface quality. This work provides important insights into the machinability improvement of UHSS S1100 material implementing nanofluids and machine learning models.