Prediction of energy carbon emission rate in side milling machining and multi-objective optimization of cutting parameters

In view of the high energy consumption characteristics of CNC machine tools, an energy carbon emission rate (ECER) prediction model based on the improved dung beetle optimization (IDBO) algorithm combined with least squares support vector regression (LSSVR) was proposed. And the multi-objective optimization study of its relationship with machining accuracy and excision efficiency was carried out. Firstly, ECER was used as the evaluation index to carry out the orthogonal test of side milling. Secondly, the dung beetle optimization algorithm was proposed to introduce Bernoulli chaos map, dynamic adaptive step size adjustment parameters and Levy flight perturbation for the optimal solution, and the IDBO-LSSSVR-ECER prediction model was established and cross-validation experiments were carried out. Finally, a three-objective model with ECER, surface roughness and material removal rates as optimization objectives was established, and the optimal combination of process parameters was obtained based on the third generation non-dominant sorting genetic algorithm (NSGA-III). Experimental results show that the prediction accuracy of ECER is improved, and root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) are significantly reduced, and the multi-objective optimization results can provide reasonable milling parameter suggestions for the manufacturing industry.