Thermal error modeling method for machine tool under different working conditions based on transfer learning

被引：0
|
作者：
Wei X. [1 ]
Wang G. [1 ]
Zhou J. [1 ]
Pan Q. [2 ]
Qian M. [1 ]
机构：
[1] School of Electrical and Information Engineering, Anhui University of Technology, Ma'anshan
[2] School of Instrument Science and Opto-Electronics Engineering, Hefei University of Technology, Hefei
来源：
Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument | 2023年 / 44卷 / 07期
关键词：
different working conditions; modeling and compensation; prediction effects; thermal error of machine tools; transfer learning;
D O I：
10.19650/j.cnki.cjsi.J2311375
中图分类号：
学科分类号：
摘要：
The difficulty in maintaining high prediction accuracy of machine tool thermal error prediction models under different working conditions is an important reason for thermal errors' poor actual compensation effect. This article proposes a modeling method for the thermal error of machine tools under different working conditions based on transfer learning. Firstly, the kernel mean matching algorithm is used to obtain the transfer weight between machine tool temperature data under different working conditions. And a thermal error modeling method based on transfer learning is proposed. Furthermore, the significance of differences in thermal error data under different working conditions is tested, and a thermal error prediction model is formulated by using the proposed method to analyze the modeling effect. Then, the actual prediction performance of the proposed modeling method and commonly used modeling methods are compared and analyzed. Finally, the compensation validation experiments are conducted to evaluate the effectiveness of the proposed method. The results show that the modeling method based on transfer learning proposed in this paper can effectively improve the modeling effect. The prediction accuracy and robustness of transfer learning combined with the LASSO algorithm under different working conditions reach 3.73 and 1.14 μm, respectively. After compensation, the thermal errors in the X/Y/Z directions of the machine tool remain within -2.3~3.1 μm, -3.4~3.9 μm, and -3.3~4.6 μm, respectively. © 2023 Science Press. All rights reserved.
引用
收藏
页码：44 / 52
页数：8
相关论文
共 26 条
  • [1] LI Y, ZHAO W H, LAN S H, Et al., A review on spindle thermal error compensation in machine tools, International Journal of Machine Tools and Manufacture, 95, pp. 20-38, (2015)
  • [2] XU K, WANG W H, LI ZH Y, Et al., Temperature-sensitive point selection method of machine tool based on active construction of temperature difference variable, Chinese Journal of Scientific Instrument, 44, 2, pp. 67-74, (2023)
  • [3] LIU K, HAN W, WANG Y Q, Et al., Review on thermal error compensation for feed axes of CNC machine tools, Journal of Mechanical Engineering, 57, 3, pp. 156-173, (2021)
  • [4] MIAO E M, GONG Y Y, NIU P CH, Et al., Robustness of thermal error compensation modeling models of CNC machine tools [J], International Journal of Advanced Manufacturing Technology, 69, 9-12, pp. 2593-2603, (2013)
  • [5] WEI X, YE H, FENG X., Year-round thermal error modeling and compensation for the spindle of machine tools based on ambient temperature intervals, Sensors, 22, 14, (2022)
  • [6] VOLK W, GROCHE P, BROSIUS A, Et al., Models and modelling for process limits in metal forming, CIRP Annals, 68, 2, pp. 775-798, (2019)
  • [7] LIU H, MIAO E M, WEI X Y, Et al., Robust modeling method for thermal error of CNC machine tools based on ridge regression algorithm, International Journal of Machine Tools and Manufacture, 113, pp. 35-48, (2017)
  • [8] TAN F, YIN M, WANG L, Et al., Spindle thermal error robust modeling using LASSO and LS-SVM, The International Journal of Advanced Manufacturing Technology, 94, pp. 2861-2874, (2018)
  • [9] ZHU M, YANG Y, FENG X, Et al., Robust modeling method for thermal error of CNC machine tools based on random forest algorithm, Journal of Intelligent Manufacturing, pp. 1-14, (2022)
  • [10] LIU J, MA C, GUI H, Et al., Transfer learning-based thermal error prediction and control with deep residual LSTM network, Knowledge-Based Systems, 237, (2022)
123