CNC 工具機廣泛應用於精密製造產業，加工過程中之能源消耗直接影響製造成本與碳排放，如何兼顧加工效率與能源效益已成為智慧製造之核心課題。既有CNC加工能耗相關研究已從切削參數建模、NC Code解析至製程方案最佳化等面向取得豐碩成果。在此基礎上，本研究進一步將加工過程中切削寬度與切削深度隨工件幾何與殘料分布變化之特性納入考量，建構一套從CAM規劃端出發之多目標最佳化框架，以最小化總加工時間（Ttotal）與比能耗（SECtotal）為雙目標，於加工前即取得兼顧效率與能源效益之加工參數設定。
本研究以NX CAM軟體中可調控之刀具路徑策略、刀路間距、每刀切削深度、每齒進給量與主軸轉速等五項加工參數作為決策變數。在能耗評估方面，透過解析NC Code將刀具路徑離散化為多個步距，並以體素切削模擬逐段提取各刀具位置之切削寬度與切削深度，據此計算切削功率與能耗；切削附加功率模型則由L27切削實驗建立，以切削寬度、切削深度、每齒進給量與主軸轉速作為輸入變數。在最佳化求解方面，採用非支配排序基因演算法（NSGA-II）搜尋Pareto解集合，並透過理想點決策法選取折衷解。
驗證實驗採用兩款涵蓋口袋、外輪廓與階梯等2.5D特徵之驗證工件進行實機切削驗證。折衷解之模型推估值與實測值之Ttotal 與 SECtotal誤差皆小於4%。在製程改善方面，折衷解於部分基準組對照中實現兩項目標之同時改善，最高可達Ttotal縮短58.8% 且SECtotal降低23.6%。結果顯示，本研究方法可有效反映加工過程中切削狀態之動態變化，並透過多目標最佳化於參數空間中找到兼顧加工時間與比能耗之組合，可作為加工前製程參數決策之參考。

CNC machine tools are widely used in precision manufacturing, where energy consumption directly affects manufacturing costs and carbon emissions. Existing research has achieved substantial results in cutting parameter modeling, NC Code parsing, and process-level optimization. Building upon these foundations, this study further incorporates the dynamic variations of cutting width and cutting depth caused by workpiece geometry and residual material distribution, and constructs a multi-objective optimization framework from the CAM planning stage to minimize total machining time (Ttotal) and specific cutting energy (SECtotal) simultaneously.
Five machining parameters in NX CAM are employed as decision variables: cutting pattern, stepover, depth of cut per layer, feed per tooth, and spindle speed. Tool paths are discretized into multiple steps by parsing NC Code, and voxel-based material removal simulation extracts cutting width and cutting depth at each tool position for power and energy calculation. The cutting-induced additional power model is established through L27 experiments with cutting width, cutting depth, feed per tooth, and spindle speed as inputs. NSGA-II is employed to search for the Pareto solution set, and the ideal point method selects the compromise solution.
Validation was conducted using two workpieces encompassing 2.5D features such as pockets, peripheral profiles, and steps. Prediction errors of both Ttotal and SECtotal for the compromise solutions were less than 4%. The compromise solutions achieved simultaneous improvement in both objectives under certain baseline comparisons, with reductions of up to 58.8% in Ttotal and 23.6% in SECtotal. Results demonstrate that the proposed method effectively captures dynamic cutting condition variations and identifies parameter combinations balancing machining time and specific cutting energy.

[1] A. Shokrani, V. Dhokia, and S. T. Newman, "Modelling and Verification of Energy Consumption in CNC Milling," Springer International Publishing, 2016, pp. 123-133.
[2] G. Zhao, C. Li, Z. Lv, X. Cheng, and G. Zheng, "Specific energy consumption prediction model of CNC machine tools based on tool wear," International Journal of Computer Integrated Manufacturing, vol. 33, no. 2, pp. 159-168, 2020, doi: 10.1080/0951192x.2020.1718763.
[3] A. Aramcharoen and P. T. Mativenga, "Critical factors in energy demand modelling for CNC milling and impact of toolpath strategy," Journal of Cleaner Production, vol. 78, pp. 63-74, 2014/09/01/ 2014, doi: https://doi.org/10.1016/j.jclepro.2014.04.065.
[4] Z. Jiang, D. Gao, Y. Lu, L. Kong, and Z. Shang, "Electrical energy consumption of CNC machine tools based on empirical modeling," The International Journal of Advanced Manufacturing Technology, vol. 100, no. 9-12, pp. 2255-2267, 2019, doi: 10.1007/s00170-018-2808-x.
[5] C. Feng, X. Chen, J. Zhang, and Y. Huang, "A generalized analysis of energy saving strategies through experiment for CNC milling machine tools," The International Journal of Advanced Manufacturing Technology, vol. 117, no. 3-4, pp. 751-763, 2021, doi: 10.1007/s00170-021-07787-9.
[6] K. S. Sangwan and G. Kant, "Optimization of Machining Parameters for Improving Energy Efficiency using Integrated Response Surface Methodology and Genetic Algorithm Approach," Procedia CIRP, vol. 61, pp. 517-522, 2017/01/01/ 2017, doi: https://doi.org/10.1016/j.procir.2016.11.162.
[7] A. Aggarwal, H. Singh, P. Kumar, and M. Singh, "Optimizing power consumption for CNC turned parts using response surface methodology and Taguchi's technique—A comparative analysis," Journal of Materials Processing Technology, vol. 200, no. 1, pp. 373-384, 2008/05/08/ 2008, doi: https://doi.org/10.1016/j.jmatprotec.2007.09.041.
[8] G. Kant and K. S. Sangwan, "Predictive Modeling for Power Consumption in Machining Using Artificial Intelligence Techniques," Procedia CIRP, vol. 26, pp. 403-407, 2015/01/01/ 2015, doi: https://doi.org/10.1016/j.procir.2014.07.072.
[9] S. H. Sun, T. S. Wu, C. H. Yang, Y. J. Cheng, and C. H. Kuo, "Prediction of CNC Machine Tool Cutting Energy Consumption by BP Neural Network," (in 英文), Proceedings of the 14th IFToMM World Congress, no. 14th-6, pp. 58-63, 2015, doi: 10.6567/IFToMM.14TH.WC.OS20.005.
[10] G. Zhao, K. Cheng, W. Wang, Y. Liu, and Z. Dan, "A milling cutting tool selection method for machining features considering energy consumption in the STEP-NC framework," The International Journal of Advanced Manufacturing Technology, vol. 120, no. 5, pp. 3963-3981, 2022/05/01 2022, doi: 10.1007/s00170-022-08964-0.
[11] M. Brillinger, M. Wuwer, M. Abdul Hadi, and F. Haas, "Energy prediction for CNC machining with machine learning," CIRP Journal of Manufacturing Science and Technology, vol. 35, pp. 715-723, 2021/11/01/ 2021, doi: https://doi.org/10.1016/j.cirpj.2021.07.014.
[12] A.-M. Schmitt, E. Miller, A. Schiffler, and J. Schmitt, "Energy Prediction for CNC Machines Using G-Code Evaluation, Machine Learning and a Real-World Training Part," 2025: IEEE, pp. 340-347, doi: 10.1109/icmre64970.2025.10976308. [Online]. Available: https://dx.doi.org/10.1109/icmre64970.2025.10976308
[13] J. Cao, X. Xia, L. Wang, Z. Zhang, and X. Liu, "A Novel CNC Milling Energy Consumption Prediction Method Based on Program Parsing and Parallel Neural Network," Sustainability, vol. 13, no. 24, p. 13918, 2021, doi: 10.3390/su132413918.
[14] A.-M. Schmitt, E. Miller, B. Engelmann, R. Batres, and J. Schmitt, "G-code evaluation in CNC milling to predict energy consumption through Machine Learning," Advances in Industrial and Manufacturing Engineering, vol. 8, p. 100140, 2024/05/01/ 2024, doi: https://doi.org/10.1016/j.aime.2024.100140.
[15] 陳俊良, "基於切削幾何資訊之 2.5D CNC 銑削加工能耗估測研究," 碩士, 國立成功大學, 2026. Available: https://thesis.lib.ncku.edu.tw/thesis/detail/6d38211ede1876886bd6e9e00154c907/
[16] Y. He, P. Wu, Y. Li, Y. Wang, F. Tao, and Y. Wang, "A generic energy prediction model of machine tools using deep learning algorithms," Applied Energy, vol. 275, p. 115402, 2020/10/01/ 2020, doi: https://doi.org/10.1016/j.apenergy.2020.115402.
[17] Y. Xie, Y. Dai, C. Zhang, and J. Liu, "An integration model enabled deep learning for energy prediction of machine tools," Journal of Cleaner Production, vol. 495, p. 145075, 2025/03/01/ 2025, doi: https://doi.org/10.1016/j.jclepro.2025.145075.
[18] T. S. Prasad, S. Timothy, N. H. Reddy, and M. Y. Basavaraja, "Optimization of specific energy consumption in turning of GFRP composites using particle swarm optimization," AIP Conference Proceedings, vol. 3237, no. 1, p. 070005, 2025, doi: 10.1063/5.0248634.
[19] C. Li, Q. Xiao, Y. Tang, and L. Li, "A method integrating Taguchi, RSM and MOPSO to CNC machining parameters optimization for energy saving," Journal of Cleaner Production, vol. 135, pp. 263-275, 2016/11/01/ 2016, doi: https://doi.org/10.1016/j.jclepro.2016.06.097.
[20] X. Chen, C. Li, Y. Jin, and L. Li, "Optimization of cutting parameters with a sustainable consideration of electrical energy and embodied energy of materials," The International Journal of Advanced Manufacturing Technology, vol. 96, no. 1-4, pp. 775-788, 2018, doi: 10.1007/s00170-018-1647-0.
[21] Y. Xiao, Z. Jiang, Q. Gu, W. Yan, and R. Wang, "A novel approach to CNC machining center processing parameters optimization considering energy-saving and low-cost," Journal of Manufacturing Systems, vol. 59, pp. 535-548, 2021/04/01/ 2021, doi: https://doi.org/10.1016/j.jmsy.2021.03.023.
[22] P. Wang, Q. Bai, K. Cheng, L. Zhao, and Y. Zhang, "Multi-Objective Optimization of Micro-Milling Parameters—The Trade-Offs between Machining Quality, Efficiency, and Sustainability in the Fabrication of Thin-Walled Microstructures," Applied Sciences, vol. 13, no. 16, p. 9392doi: 10.3390/app13169392.
[23] L. Hu et al., "Minimising the machining energy consumption of a machine tool by sequencing the features of a part," Energy, vol. 121, pp. 292-305, 2017/02/15/ 2017, doi: https://doi.org/10.1016/j.energy.2017.01.039.
[24] H. Wang, R. Y. Zhong, G. Liu, W. Mu, X. Tian, and D. Leng, "An optimization model for energy-efficient machining for sustainable production," Journal of Cleaner Production, vol. 232, pp. 1121-1133, 2019/09/20/ 2019, doi: https://doi.org/10.1016/j.jclepro.2019.05.271.
[25] C. Feng, Y. Wu, W. Li, B. Qiu, J. Zhang, and X. Xu, "Energy consumption optimisation for machining processes based on numerical control programs," Advanced Engineering Informatics, vol. 57, p. 102101, 2023/08/01/ 2023, doi: https://doi.org/10.1016/j.aei.2023.102101.
[26] X. X. Li, W. D. Li, and F. Z. He, "A multi-granularity NC program optimization approach for energy efficient machining," Advances in Engineering Software, vol. 115, pp. 75-86, 2018/01/01/ 2018, doi: https://doi.org/10.1016/j.advengsoft.2017.08.014.
[27] G. Campatelli, L. Lorenzini, and A. Scippa, "Optimization of process parameters using a Response Surface Method for minimizing power consumption in the milling of carbon steel," Journal of Cleaner Production, vol. 66, pp. 309-316, 2014/03/01/ 2014, doi: https://doi.org/10.1016/j.jclepro.2013.10.025.
[28] M. P. Groover, Fundamentals of Modern Manufacturing: Materials, Processes, and Systems. Wiley, 2020.
[29] K. Deb, A. Pratap, S. Agarwal, and T. Meyarivan, "A fast and elitist multiobjective genetic algorithm: NSGA-II," IEEE Transactions on Evolutionary Computation, vol. 6, no. 2, pp. 182-197, 2002, doi: 10.1109/4235.996017.
[30] J. Blank and K. Deb, "Pymoo: Multi-Objective Optimization in Python," IEEE Access, vol. 8, pp. 89497-89509, 2020, doi: 10.1109/ACCESS.2020.2990567.
[31] K. Deb, "Multi-objective Optimisation Using Evolutionary Algorithms: An Introduction," in Multi-objective Evolutionary Optimisation for Product Design and Manufacturing, L. Wang, A. H. C. Ng, and K. Deb Eds. London: Springer London, 2011, pp. 3-34.
[32] J. Blank. "Part IV: Analysis of Convergence." https://pymoo.org/getting_started/part_4.html (accessed.
[33] J. Zhou, C. Liu, and K. Li, "PV array reconfiguration with electrical energy storage system for power system frequency regulation," Frontiers in Energy Research, vol. 10, 2022, doi: 10.3389/fenrg.2022.971628.