Sustainable Lubrication Strategies in Eco-friendly Machining of AISI 4140 Steel: Performance and Environmental Impact Analysis Using Machine Learning

This study encompasses extensive analysis for different aspects of industrially important 4140 steel during dry and minimum quantity lubrication-assisted turning operations. Surface roughness, tool wear, cutting forces, chip morphology and cutting temperatures were considered as technological parameters while carbon emissions and energy consumption were handled as the ecological parameters. The environmental analysis indicates that increased cutting speeds and greater depths of cut result in a substantial rise in energy consumption, with levels reaching up to 50% higher than those seen in alternative configurations. In the case of high cutting speeds, carbon emissions can potentially increase by as much as 60%. Conversely, at low cutting speeds and parameters, energy consumption emissions decrease by 42%. In terms of carbon emissions, dry machining offers a distinct advantage over MQL. Machine learning (decision tree model) is utilized to model the effects of input and output parameters to determine the optimum values of these parameters. It has provided the relationship between the dependent variables and the independent variables for sustainable machining of an industrially important material. The decision tree ML model for cutting force results showed that RMSE values are 8.7 and 11.89 for dry and MQL environments, while it was 6.83 and 1.15 for cutting temperature in dry and MQL environments, respectively. Finally, RMSE values of surface roughness are 0.19 and 0.16 for dry and MQL environments, respectively.