Carbon Emissions and Parameter Optimization for Machine Tool Processing

The imposition of carbon taxes on goods imported by the European Union can considerably affect economic development. Computer numerical control (CNC) machine tools are indispensable in manufacturing, and reducing their environmental impact is crucial. Most machining pollution is produced during the operation of these tools. In this study, the carbon emissions of machine tools during energy consumption (EC) and machining processes were examined. Next, EC models were curve-fit using the least-squares method, and the leave-one-out method was employed to enhance the fairness and stability of the training process. In this manner, second-order power consumption models were obtained. On the basis of these models, this study conducted multiobjective optimization for effectively reducing carbon emissions, minimizing processing times, and maximizing surface quality. Three optimization algorithms—particle swarm optimization (PSO), the genetic algorithm (GA), and gray wolf optimization (GWO)—were used for the multiobjective optimization, and the GWO algorithm was found to yield the best results. Implementation of the GWO-optimized parameters in an actual machining process resulted in reductions of 54.4%, 16.3%, and 14.7% in carbon emissions, processing time, and surface roughness, respectively. Thus, the method proposed in this article can achieve efficient green manufacturing without sacrificing machining quality, thereby contributing to sustainable machining operations.