数控铣削能耗预测及切削参数多目标优化研究OA北大核心CSTPCD

To study the energy-saving optimization of CNC milling machine, this paper firstly designs the experimental scheme of CNC milling with 316L stainless steel as the machining object, and the experimental data analysis is made. Then, the experimental data are employed as the samples, and BP neural network is applied to build the prediction model of the energy consumption of CNC machine tools, and the structure of the BP neural network is optimized by using dung-beetle-roach optimization ( DBO ) algorithm to build the DBO-BP neural network based on the CNC machine tool energy consumption prediction model. By comparing the two models before and after optimization, the DBO-BP neural network model with higher prediction accuracy and stability and the machining cost are selected to build a multi-objective optimization model of milling parameters, and NSGA-Ⅱ is applied to solve the multi-objective optimization model of milling parameters to obtain the optimal solution set, and finally entropy right TOPSIS is applied to determine the optimal solution set. By comparing the specific energy consumption and machining cost before and after optimization, the optimized cutting parameters reduce the specific energy consumption and machining cost by 33.84％ and 5％ respectively. Our study shows the optimized cutting parameters achieve higher energy efficiency and save machining cost.