A review on transfer learning in spindle thermal error compensation of spindle

Yue Zheng; Guoqiang Fu; Sen Mu; Sipei Zhu; Kunlong Lin; Long Yang

doi:10.55092/am20240012

Review

Open Access

A review on transfer learning in spindle thermal error compensation of spindle

Yue Zheng^1,²Guoqiang Fu^1,^2,^3,⁴^,∗Sen Mu^1,²Sipei Zhu^1,²Kunlong Lin^1,²Long Yang^1,²

¹ School of Mechanical Engineering, Southwest Jiaotong University, Chengdu 610031, China

² The Intelligent Manufacturing Longcheng Laboratory, Changzhou 213164, China

³ The State Key Laboratory of Mechanical Transmissions, Chongqing University, Chongqing 400044, China

⁴ Technology and Equipment of Rail Transit Operation and Maintenance Key Laboratory of Sichuan Province, Chengdu 610031, China

* fuguoqiang@swjtu.edu.cn

Volume
Volume 1 Issue 3, 2024
Citation
Zheng Y, Fu G, Mu S, Zhu S, Lin K, et al. A review on transfer learning in spindle thermal error compensation of spindle. Adv. Manuf. 2024(3):0012, https://doi.org/10.55092/am20240012.
DOI
10.55092/am20240012
Copyright
Copyright2024 by the authors. Published by ELSP.

Abstract

Data-driven approaches offer unprecedented opportunities for smart manufacturing to facilitate the transition to Industry 4.0-based production. One of the key factors affecting the accuracy of machine tools is the thermal error caused by thermal deformation. A major heat source among those that cause thermal deformation in machine tools is the spindle. Transfer learning plays a key role in developing intelligent systems for thermal error prediction in machine tools. In this paper, the opportunities and challenges of migration learning for thermal error modeling of spindles are reviewed. The main models of transfer learning are discussed, including, and their application to spindle thermal error modeling is overviewed. The purpose of this paper is to provide a basic introduction to the whole process of thermal error compensation in spindles and to give an overview of the different topics of thermal error modeling methods.

Keywords

Transfer learning; domain adaption; machine tools; subspace metric; thermal error prediction

Preview

view pdf

References

[1] Jia GJ, Zhang X, Shen YJ, Huang ND. Intermittent multivariate time series spindle thermal error prediction under wide environmental temperature ranges and diverse scenario conditions. Int. J. Adv. Manuf. Technol. 2024, 132:4625–4643.
[2] Tian Y, Pan GY. An unsupervised regularization and dropout based deep neural network and its application for thermal error prediction. Appl. Sci. 2020, 10(8):2870.
[3] Wu CY, Xiang ST, Xiang WS. Spindle thermal error prediction approach based on thermal infrared images: a deep learning method. J. Manuf. Syst. 2021, 59:67–80.
[4] Makoto F, Koichiro N, Naruhiro I, Masahiko M, Soichi I. Adaptive thermal displacement compensation method based on deep learning. CIRP Ann. Manuf. Technol. 2019, 25:22–25.
[5] Li Y, Yu ML, Bai YM, Hou ZY, Wu WW. A review of thermal error modeling methods for machine tools. Appl. Sci. 2021, 11(11):5216.
[6] Li ZL, Zhu WM, Zhu B, Wang BD, Wang QH, et al. Simulation analysis model of high-speed motorized spindle structure based on thermal load optimization. Case Stud. Therm. Eng. 2023, 44:102871.
[7] Shi H, Zhang B, Mei X, Wang H, Zhao F, et al. Thermal error modelling and compensation of CNC lathe feed system based on positioning error measurement and decoupling. Measurement 2024, 231:114633.
[8] Liang YC, Li WD, Lou P, Hu JM. Thermal error prediction for heavy-duty CNC machines enabled by long short-term memory networks and fog-cloud architecture. J. Manuf. Syst. 2022, 62:950–963.
[9] Fabian S, Josef M, Clemens S, Petr Ka, Friedrich B, et al. Cloud-based thermal error compensation with a federated learning approach. Precis. Eng. 2023, 79:135–145.
[10] Li TJ, Sun TY, Zhang YM, Cui SY, Zhao CY. Dynamic memory intelligent algorithm used for prediction of thermal error reliability of ball screw system. Appl. Soft. Comput. 2022, 125:109183.
[11] Li PW, Lou P, Yan JW, Liu NY. The thermal error modeling with deep transfer learning, J. Phys. Conf. Ser. 2020, 1576:012003.
[12] Mori M, Mizuguchi H, Fujishima M, Ido Y, Mingkai N, et al. Design optimization and development of CNC lathe headstock to minimize thermal deformation. CIRP Ann. 2009, 58(1):331–334.
[13] Ye Z, Yu JB. State-of-health estimation for lithium-ion batteries using domain adversarial transfer learning. IEEE Trans. Power Electr. 2022, 37(3):3528–3543.
[14] Xia M, Shao HD, Williams D, Lu S, Shu L, et al. Intelligent fault diagnosis of machinery using digital twin-assisted deep transfer learning. Reliab. Eng. Sys. Saf. 2021, 215:107938.
[15] Xiao YM, Shao HD, Han SY, Huo ZQ, Wan JF. Novel joint transfer network for unsupervised bearing fault diagnosis from simulation domain to experimental domain. IEEE ASME Trans. Mechatron. 2022, 27(6):5254–5263.
[16] Liu HY, Deng HG, Feng XY, Liu YD, Li YF, et al. Data-driven thermal error modeling based on a novel method of temperature measuring point selection. Int. J. Adv. Manuf. Technol. 2024, 131(3):1823–1848.
[17] Kuo PH, Tu TL, Chen YW, Jywe WY, Yau HT. Thermal displacement prediction model with a structural optimized transfer learning technique. Case Stud. Therm. Eng. 2023, 49:103323.
[18] Zhu MR, Yang Y, Feng XB, Du CZ, Yang JG. Robust modeling method for thermal error of CNC machine tools based on random forest algorithm. J. Intell. Manuf. 2022, 34(3):2013–2026.
[19] Tan F, Deng CY, Xiao H, Luo JF, Zhao S. A wrapper approach-based key temperature point selection and thermal error modeling method. Int. J. Adv. Manuf. Technol. 2019, 106:907–920.
[20] Zhang L, Ma C, Liu JL, Totis G, Weng SB. Multi-layer parallel-perceptual-fusion spatiotemporal graph convolutional network for cross-domain, poor thermal information prediction in cloud-edge control services. Adv. Eng. Inform. 2024, 59:102358.
[21] Soori M, Arezoo B. Dimensional, geometrical, thermal and tool deflection errors compensation in 5-Axis CNC milling operations. Aust. J. Mech. Eng. 2023:1–15.
[22] Li Y, Zhao WH, Lan SH, Ni J, Wu WW, et al. A review on spindle thermal error compensation in machine tools. Int. J. Mach. Tool Manu. 2015, 95:20–38.
[23] Zhuang FZ, Qi ZY, Duan KY, Xi DB, Zhu YC, et al. A comprehensive survey on transfer learning. Proc. IEEE. 2021, 109(1):43–76.
[24] Subramaniam V, Dbouk T, Harion JL. Topology optimization of conductive heat transfer devices: an experimental investigation. Appl. Therm. Eng. 2018, 131:390–411.
[25] Li C, Zhang SH, Qin Y, Estupinan E. A systematic review of deep transfer learning for machinery fault diagnosis. Neurocomputing 2020, 407:121–135.
[26] Lei MH, Jiang GD, Yang J, Mei XS, Xia P, et al. Improvement of the regression model for spindle thermal elongation by a boosting-based outliers detection approach. Int. J. Adv. Manuf. Technol. 2018, 99:1389–1403.
[27] Miao E, Gong Y, Xu Z, Zhou X. Comparative analysis of thermal error compensation model robustness of CNC machine tools. J Mech Eng. 2015, 51(7):130–135.
[28] Zhao ZY, Huang ND, Shen YJ, Jia GJ, Zhang X, et al. Modeling and prediction of full-term thermal error in linear axis of machine tools based on MSTGCN-A. Int. J. Adv. Manuf. Technol. 2024, 130(9):4805–4819.
[29] Michaleris P. Modeling metal deposition in heat transfer analyses of additive manufacturing processes. Finite Elem. Anal. Des. 2014, 86:51–60.
[30] Wang X, Wang TY, Ming AB, Zhang W, Li AH, et al. Cross-operating condition degradation knowledge learning for remaining useful life estimation of bearings. IEEE Trans. Instrum. Meas. 2021, 70:1–11.
[31] Kang CM, Zhao CY, Zhang JQ. Thermal behavior analysis and experimental study on the vertical machining center spindle. Trans. Can. Soc. Mech. Eng. 2020, 44(3):344–351.
[32] Kuo PH, Lee CH, Yau HT. Stacking ensemble transfer learning based thermal displacement prediction system. Int. J. Optomechatron. 2023, 17(1):2225573.
[33] Sun FS, Cao BH, Fan MB, Ye B, Pan JP. Physics-constrained transfer learning for self-assessment of terahertz thickness measurement of thermal barrier coatings. IEEE Trans. Ind. Inform. 2024, 20(9):11045–11056
[34] Sun C, Ma M, Zhao ZB, Tian SH, Yan RQ, et al. Deep transfer learning based on sparse autoencoder for remaining useful life prediction of tool in manufacturing. IEEE Trans. Ind. Inform. 2019, 15(4):2416–2425.
[35] Liu JL, Ma C, Gui HQ, Wang SL. Transfer learning-based thermal error prediction and control with deep residual LSTM network. Knowl. Based Syst. 2022, 237:107704.
[36] Liu JL, Ma C, Gui HQ, Li MY. Geometric-thermal error control system for gear profile grinding machine. Adv. Eng. Inform. 2022, 52:101618.
[37] Wang Q, Chen X, Chen M, He YF, Guo H. A rapid modelling method for machine tool power consumption using transfer learning. Int. J. Adv. Manuf. Technol. 2024, 131(3):1551–1566.
[38] Liu SG, Yang ZQ, Wei Q, Chen YS, Liu LB. Thermal Error Model of Linear Motor Feed System Based on Bayesian Neural Network. IEEE Access 2021, 9:112561–112572.
[39] Li PW, Lou P, Yan JW, Liu NY. The Thermal error modeling with deep transfer learning. J. Phys. Conf. Ser. 2020, 1576:012003.
[40] Mao HY, Liu ZY, Qiu C, Liu H, Sun JC, et al. Subspace metric-based transfer learning for spindle thermal error prediction under time-varying conditions. IEEE Trans. Instrum. Meas. 2024, 73:1–11.
[41] Ma S, Leng JW, Chen ZY, Li B, Zhang D, et al. A novel adaptive deep transfer learning method towards thermal error modeling of electric spindles under variable conditions. J. Manuf. Syst. 2024, 74:112–128.