Achieving sustainability by identifying the influences of cutting parameters on the carbon emissions of a milling process

This study shows the impact of the cutting parameters on the carbon emissions of a three-axis milling machine. The experiment was conducted based on Taguchi’s experimental design. An L9 orthogonal array was used for the experimental analysis in which the cutting parameters and flowmeter rate were taken as the input parameters. The output parameters after each experiment were the carbon emissions. After the experiment, the carbon emissions data was predicted using various machine learning methods, and each method was compared using metrics such as RMSE, MAE, and R-squared. The results obtained showed that XGBoost showed the best accuracy with an RMSE of 0.0007129, MAE of 0.0004476, and an R² value of 1. Also, in this study, the Shapley Additive explanations (SHAP) plots are being used to identify the spindle speed as the most influencing factor affecting the emissions. Overall, this research provided a framework that optimizes the machining process to minimize the environmental impact while maintaining production efficiency.