The natural energy crisis and the increasingly serious environmental problems have imposed all industries to reduce energy consumption. During milling process, selecting a correct cutting parameters can not only greatly improve production quality and processing efficiency, but also can reduce energy consumption, in addition, tool wear also has a great impact on them. Therefore, a milling power consumption model of CNC machine tools is established based on modern machining theory is established in this article, unlike traditional energy consumption models, our model takes full account of cutting conditions and tool wear. The surface roughness of parts is one of the important indicators to measure the machining quality of machine tools. Therefore, taking milling process as research object, a multi-objective cutting parameters optimization model that takes the machining surface roughness, material removal rate (MRR) and machining energy consumption as the optimization goals was established. Furthermore, an intelligent optimization algorithm was proposed based on improved Teaching–Learning-Based Optimization (TLBO) to solve the model under various limited milling conditions. Finally, comparing experimental results of optimized parameter and empirical parameters, it shows that goals of reducing energy consumption, improving productivity and machining quality can be achieved by optimizing cutting parameters.

自然能源危机和日益严重的环境问题迫使所有行业减少能耗。在铣削过程中，选择正确的切削参数不仅可以大大提高生产质量和加工效率，而且可以降低能耗，此外，刀具的磨损也对其产生很大的影响。因此，本文建立了基于现代加工理论的数控机床铣削能耗模型，与传统的能耗模型不同，我们的模型充分考虑了切削条件和刀具磨损。零件的表面粗糙度是衡量机床加工质量的重要指标之一。因此，以铣削加工为研究对象，建立了以加工表面粗糙度，材料去除率（MRR）和加工能耗为优化目标的多目标切削参数优化模型。此外，提出了一种基于改进的基于教学-学习的优化（TLBO）的智能优化算法，以在各种有限的铣削条件下求解模型。最后，通过比较优化参数和经验参数的实验结果，表明通过优化切削参数可以达到降低能耗，提高生产率和加工质量的目的。提出了一种基于改进的基于教学-学习的优化（TLBO）的智能优化算法，以在各种有限的铣削条件下求解该模型。最后，通过比较优化参数和经验参数的实验结果，表明通过优化切削参数可以达到降低能耗，提高生产率和加工质量的目的。提出了一种基于改进的基于教学-学习的优化（TLBO）的智能优化算法，以在各种有限的铣削条件下求解该模型。最后，通过比较优化参数和经验参数的实验结果，表明通过优化切削参数可以达到降低能耗，提高生产率和加工质量的目的。