Untitled Item

Computer numerical control (CNC) machining tools emit considerable amounts of carbon through their energy consumption,material waste and coolant usage and these emissions can harm the environment, society and public health. This study investigates the influence of four machining parameters on carbon emissions for a Mytech 850VS (Vertical Spindle) CNC machine tool. Analysis of Variance revealed that the cutting speed is the most influential parameter explaining 43.44 % of the variance in carbon emissions. Out of the five machine learning techniques that were evaluated the XGBoost algorithm was found to have the highest performance for predicting carbon emissions. Shapley plots confirmed the key role of the cutting speed . Furthermore novel metaheuristic algorithms were employed to identify the optimal combinations of cutting parameters for minimizing carbon emissions. This integrated approach is a robust framework for mitigating the environmental impact of machining processes aligning with sustainability objectives. This study’s insights into the influences of specific cutting parameters on carbon emissions can contribute to sustainability goals by reducing the environmental footprint of machining operations. By optimizing the machining parameters the manufacturers can successfully decrease the environmental impacts while enhancing the process efficiency.