A mechanism-data hybrid-driven modeling method for predicting machine tool-cutting energy consumption

Abstract

High-quality development in the manufacturing industry is often accompanied by high energy consumption. The accurate prediction of the energy consumption of computer numerical control (CNC) machine tools, which plays a vital role in manufacturing, is of great importance in energy conservation. However, the existing research ignores the impact of multi-factor energy losses on the performance of machine tool energy consumption prediction models. The existing models must be selected and verified several times to determine the appropriate hyperparameters. Therefore, in this study, a machine tool energy consumption prediction method based on a mechanism and data-driven model that considers multi-factor energy losses and hyperparameter dynamic self-optimization is proposed to improve the accuracy and reduce the difficulty of hyperparameter tuning. The proposed multi-factor energy-loss prediction model is based on the theoretical prediction model of machine-tool cutting energy consumption. After creating the model, a hyperparameter search space embedding a tree-structured Parzen estimator (TPE) was designed based on Hyperopt to dynamically self-optimize the hyperparameters in the deep neural network (DNN) model. Finally, two sets of experiments were designed for verification and comparison with the theoretical and data models. The results showed that the energy consumption prediction performances of the proposed hybrid model in the two sets of experiments were 99% and 97%.

Keywords

Mechanism-data hybrid-driven / Cutting energy consumption / Hyperopt / Hyperparameters tuning

References

[1] IEA (2022) World energy outlook 2022. IEA, Paris. https://www.iea.org/reports/world-energy-outlook-2022, License: CC BY 4.0 (report); CC BY NC SA 4.0 (Annex A)

[2] Sihag N, Sangwan KS. A systematic literature review on machine tool energy consumption. J Clean Prod. 2020, 275: 123125

[3] Gutowski T, Dahmus J, Thiriez A (2006) Electrical energy requirements for manufacturing processes. In: The 13th CIRP international conference on life cycle engineering, Leuven, Belgium, 31 May‒2 June

[4] Lv J, Tang R, Tang W, et al. . An investigation into reducing the spindle acceleration energy consumption of machine tools. J Clean Prod. 2017, 143: 794-803

[5] Zhou L, Li F, Zhao F, et al. . Characterizing the effect of process variables on energy consumption in end milling. Int J Adv Manuf Technol. 2019, 101: 2837-2848

[6] Li B, Tian X, Zhang M. Modeling and multi-objective optimization method of machine tool energy consumption considering tool wear. Int J Precis Eng Manuf Green Technol. 2022, 9: 127-141

[7] Zhang T, Liu Z, Sun X, et al. . Investigation on specific milling energy and energy efficiency in high-speed milling based on energy flow theory. Energy. 2020, 192: 116596

[8] Shi KN, Zhang DH, Liu N, et al. . A novel energy consumption model for milling process considering tool wear progression. J Clean Prod. 2018, 184: 152-159

[9] Rodrigues AR, Coelho RT. Influence of the tool edge geometry on specific cutting energy at high-speed cutting. J Braz Soc Mech Sci Eng. 2007, 29(3): 279-283

[10] Pawar SS, Bera TC, Sangwan KS. Towards energy efficient milling of variable curved geometries. J Manuf Process. 2023, 94: 497-511

[11] Shi KN, Liu N, Liu CL, et al. . Indirect approach for predicting cutting force coefficients and power consumption in milling process. Adv Manuf. 2021, 10(1): 101-113

[12] Zhao G, Su Y, Zheng G, et al. . Tool tip cutting specific energy prediction model and the influence of machining parameters and tool wear in milling. Proc Inst Mech Eng Part B J Eng Manuf. 2020, 234: 1346-1354

[13] Sealy MP, Liu ZY, Zhang D, et al. . Energy consumption and modeling in precision hard milling. J Clean Prod. 2016, 135: 1591-1601

[14] Liu X, Han L, Wu S, et al. . Influence of blade curvature characteristics on energy consumption in machining process. Int J Adv Manuf Technol. 2022, 121: 1867-1885

[15] Wang B, Liu Z, Song Q, et al. . Proper selection of cutting parameters and cutting tool angle to lower the specific cutting energy during high-speed machining of 7050-T7451 aluminum alloy. J Clean Prod. 2016, 129: 292-304

[16] Tao F, Qi Q, Liu A, et al. . Data-driven smart manufacturing. J Manuf Syst. 2018, 48: 157-169

[17] Lngkvist M, Karlsson L, Loutfi A. A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recogn Lett. 2014, 42: 11-24

[18] Xie D, Chen GR, Wan F, et al. . Modeling of CNC machine tool energy consumption and optimization study based on neural network and genetic algorithm. Mech Eng Intell Syst. 2012, 195(196): 770-776

[19] Kant G, Sangwan KS. Predictive modelling for energy consumption in machining using artificial neural network. Procedia CIRP. 2015, 37: 205-210

[20] Liu Z, Guo Y. A hybrid approach to integrate machine learning and process mechanics for the prediction of specific cutting energy. CIRP Ann. 2018, 67: 57-60

[21] He Y, Wu PC, Li YF, et al. . A generic energy prediction model of machine tools using deep learning algorithms. Appl Energy. 2020, 275: 115402

[22] Huang BB, Jiang GZ, Yan W et al (2021) Data-driven method for predicting energy consumption of machine tool spindle acceleration. In: IEEE 17th international conference on automation science and engineering (CASE), Lyon, France, 23‒27 August, pp 528‒533. https://doi.org/10.1109/CASE49439.2021.9551682

[23] Brillinger M, Wuwer M, Hadi MA, et al. . Energy prediction for CNC machining with machine learning. CIRP J Manuf Sci Technol. 2021, 35: 715-723

[24] Zhao XK, Li CB, Chen XZ, et al. . Data-driven cutting parameters optimization method in multiple configurations machining process for energy consumption and production time saving. Int J Precis Eng Manuf Green Technol. 2021, 9: 709-728

[25] Ghimire S, Bhandari B, Casillas-Perez D, et al. . Hybrid deep CNN-SVR algorithm for solar radiation prediction problems in Queensland, Australia. Eng Appl Artif Intell. 2022, 112: 104860

[26] Yao JT, Shui HF, Li ZK, et al. . Machine learning prediction of pyrolytic sulfur migration based on coal compositions. J Anal Appl Pyrolysis. 2024, 177: 106316

[27] Xiao B, Li SZ, Dou SQ, et al. . Comparison of leaf chlorophyll content retrieval performance of citrus using FOD and CWT methods with field-based full-spectrum hyperspectral reflectance data. Comput Electron Agric. 2024, 217: 108559

[28] Hanifi S, Cammarono A, Zare-Behtash H. Advanced hyperparameter optimization of deep learning models for wind power prediction. Renew Energy. 2024, 221: 119700

[29] Yang Q, Pattipati KR, Awasthi U, et al. . Hybrid data-driven and model-informed online tool wear detection in milling machines. J Manuf Syst. 2022, 63: 329-343

[30] Li W, Li CB, Wang NB, et al. . Energy saving design optimization of CNC machine tool feed system: a data-model hybrid driven approach. IEEE Trans Autom Sci Eng. 2022, 19(4): 3809-3820

[31] Vishnu VS, Varghese KG, Gurumoorthy B. A hybrid approach for predictive modeling of KPIs in CNC machining operations. Procedia CIRP. 2023, 118: 566-571

[32] Xiao QE, Yang ZL, Zhang YF, et al. . Adaptive optimal process control with actor-critic design for energy-efficient batch machining subject to time-varying tool wear. J Manuf Syst. 2023, 67: 80-96

[33] Jiang P, Wang ZX, Li XB, et al. . Energy consumption prediction and optimization of industrial robots based on LSTM. J Manuf Syst. 2023, 70: 137-148

[34] Li W, Kara S. An empirical model for predicting energy consumption of manufacturing processes: a case of turning process. Proc Inst Mech Eng Part B J Eng Manuf. 2011, 225: 1636-1646

[35] Kara S, Li W. Unit process energy consumption models for material removal processes. CIRP Ann Manuf Technol. 2011, 60: 37-40

[36] Razavian AS, Azizpour H, Sullivan J et al (2014) CNN features off-the-shelf: an astounding baseline for recognition. In: 2014 IEEE conference on computer vision and pattern recognition workshops, Columbus, OH, USA, 23‒28 June. https://doi.org/10.1109/CVPRW.2014.131

[37] Korotcov A, Tkachenko V, Russo DP, et al. . Comparison of deep learning with multiple machine learning methods and metrics using diverse drug discovery data sets. Mol Pharm. 2017, 14: 4462-4475

[38] Xu DP, Zhang SD, Zhang HS, et al. . Convergence of the RMSprop deep learning method with penalty for nonconvex optimization. Neural Netw. 2021, 139: 17-23

[39] Gong YD, Zhang XY, Gao DZ, et al. . State-of-health estimation of lithium-ion batteries based on improved long short-term memory algorithm. J Energy Storage. 2022

[40] Roy SK, Mhammedi Z, Harandi M (2018) Geometry aware constrained optimization techniques for deep learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 18‒23 June, Salt Lake City, UT, USA. https://doi.org/10.1109/CVPR.2018.00469

[41] Bergstra J, Komer B, Eliasmith C, et al. . Hyperopt: a Python library for model selection and hyperparameter optimization. Comput Sci Disc. 2015, 8(1): 014008

[42] Ozaki Y, Tanigaki Y, Watanabe S et al (2020) Multiobjective tree-structured Parzen estimator for computationally expensive optimization problems. In: Proceedings of the 2020 genetic and evolutionary computation conference, Cancún Mexico, 8‒12 July. https://doi.org/10.1145/3377930.3389817

[43] Zang J, Wang Q, Shen WF. Hyper-parameter optimization of multiple machine learning algorithms for molecular property prediction using hyperopt library. Chin J Chem Eng. 2022, 52: 115-125

Funding

National Natural Science Foundation of China(U22A20128)

RIGHTS & PERMISSIONS

Shanghai University and Periodicals Agency of Shanghai University and Springer-Verlag GmbH Germany, part of Springer Nature