Abstract
The temperature rise of key internal components and ambient temperature changes during machining processes are the main causes of thermal displacement in machine tool spindle. This wastes materials and reduces working efficiency. A highly accurate and robust thermal spindle displacement estimation scheme is proposed in this paper which is based on the convolutional neural network (CNN) technique. Several key signals of specific dimensions related to spindle thermal displacement were first collected as two-dimensional (2D) signal maps. A multi-level feature expression for these 2D signal maps was extracted using convolution and pooling. A relationship between the extracted features and spindle thermal displacement was then learned using the neural architecture of the full connection layer. Optimized hyperparameter settings were determined by design of experiments (DoE) applied to the proposed CNN model. Experimental results showed that the proposed method had better performance than the multiple regression analysis (MLR) or back propagation neural network (BPNN) methods in terms of estimation accuracy and robustness at different spindle speeds.
Similar content being viewed by others
References
J. Bryan, International status of thermal error research, CIRP Annals, 39(2) (1990) 645–656.
J. Mayr, J. Jedrzejewski, E. Uhlmann, M. A. Donmez, W. Knapp, F. Hartig, K. Webdt, T. Moriwaki, P. Shore, R. Schmitt, C. Brecher, T. Wurz and K. Wegener, Thermal issues in machine tools, CIRP Annals, 61(2) (2012) 771–791.
S. R. Postlethwaite, J. P. Allen and D. G. Ford, The use of thermal imaging, temperature and distortion models for machine tool thermal error reduction, Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, 212(8) (1998) 671–679.
T. J. Ko, T. W. Gim and J. Y. Ha, Particular behavior of spindle thermal deformation by thermal bending, Int. J. Mach. Tools Manuf., 43(1) (2003) 17–23.
L. Sun, M. Ren, H. Hong and Y. Yin, Thermal error reduction based on thermodynamics structure optimization method for an ultra-precision machine tool, Int. J. Adv Manuf. Technol., 88 (2017) 1267–1277.
C. H. Chien and J. Y. Jang, 3-D numerical and experimental analysis of a built-in motorized high-speed spindle with helical water-cooling channel, Appl. Therm. Eng., 28(17–18) (2008) 2327–2336.
K. M. Ganesh, N. V. Kamalesh, A. K. Dawood and M. Karthikeyan, CFD analysis of cooling channels in built-in motorized highspeed spindle, Eng. Sci. Technol. Int. J., 2(2) (2012) 2250–3498.
S. Yang, X. Luo, X. Chen and Z. Luo, Self-adaptive compensation method of thermal error for hobbing machine tool, Int. J. Innov. Comput. Inf. Control., 17(6) (2021) 2045–2055.
H. Liu, E. M. Miao, X. Y. Wei and X. D. Zhuang, Robust modeling method for thermal error of CNC machine tools based on ridge regression algorithm, Int. J. Mach. Tools Manu., 113 (2017) 35–48.
B. Li, X. Tian and M. Zhang, Thermal error modeling of machine tool spindle based on the improved algorithm optimized BP neural network, Int. J. Adv. Manuf. Technol., 105 (2019) 1497–1505.
Y. C. Liang, W. D. Li, P. Lou and J. M. Hu, Thermal error estimation for heavy-duty CNC machines enabled by long short-term memory networks and fog-cloud architecture, J. Manuf. Syst., 62 (2020) 950–963.
A. M. Abdulshahed, A. P. Longstaff and S. Fletcher, The application of ANFIS estimation models for thermal error compensation on CNC machine tools, App. Soft. Comput., 27 (2015) 158–168.
P. L. Liu, Z. C. Du, H. M. Li, M. Deng, X. B. Feng and J. G. Yan, Thermal error modeling based on BiLSTM deep learning for CNC machine tool, Adv Manuf., 9 (2021) 235–249.
Y. Chen, H. Zhou, J. Chen and G. Xu, Spindle thermal error modeling method considering the operating condition based on long short-term memory, Eng. Res. Express, 3(3) (2021) 035019.
C. Y. Wu, S. Xiang and W. H. Xiang, Spindle thermal error estimation approach based on thermal infrared images: A deep learning method, J. Manuf. Syst., 59 (2021) 67–80.
X. Zhang, L. Yang, P. Lou, X. Jiang and Z. Li, Thermal error modeling for heavy duty CNC machine tool based on convolution neural network, 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chengdu, China (2019) 272–276.
H. Yang and J. Ni, Dynamic neural network modeling for nonlinear, nonstationary machine tool thermally induced error, Int. J. Mach. Tools Manuf., 45(4–5) (2005) 455–465.
Y. Lecun, L. Bottou, Y. Bengio and P. Haffner, Gradient-based learning applied to document recognition, Proceedings of the IEEE, 86(11) (1998) 2278–2324.
H. Atil and Y. Unver, A different approach of experimental design: taguchi method, Pak J. Biol Sci., 3(9) (2000) 1538–1540.
B. Xu, N. Wang, T. Chen and M. Li, Empirical evaluation of rectified activations in convolutional network, arXiv:1505.00853 (2015).
P. C. Lee, T. P. Loa, H. Sunb and I. Wenc, An efficient method for determining the optimal convolutional neural network structure based on taguchi method, J. Intell. Fuzzy Syst., 39(3) (2020) 2611–2625.
Y. Y. Hong and T. Satriani, Day-ahead spatiotemporal wind speed forecasting using robust design-based deep learning neural network, Energy, 209 (2020) 118441.
C. J. Lin and Y. C. Li, Lung nodule classification using Taguchi-based convolutional neural networks for computer tomography images, Electronics, 9(7) (2020) 1066.
Y. C. Liu, K. Y. Li and Y. C. Tsai, Spindle thermal error estimation based on LSTM deep learning for a CNC machine tool, Appl. Sci., 11(12) (2021) 5444.
Acknowledgments
This study was supported in part by grants from the Ministry of Science and Technology of the Republic of China (Taiwan) (Grant No. MOST 111-2221-E-167-020).
Author information
Authors and Affiliations
Corresponding author
Additional information
Chien-Wei Liao is a Master of the Department of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung, Taiwan. His research interests are deep learning and thermal error compensation of machine tools.
Ming-Tsang Lee is currently a faculty member in Power Mechanical Engineering, National Tsing Hua University, Hsinchu, Taiwan. He received his Ph.D. in Mechanical Engineering from the University of California, Berkeley. His research interests encompass advanced heat transfer, laser-assisted manufacturing, intelligent machine tools, and green energy.
Yu-Chi Liu is an Assistant Professor of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung, Taiwan. His research interests include the application of artificial intelligence, image processing, software engineering, as well as the visualization, manufacturing accuracy and control of smart manufacturing.
Rights and permissions
About this article
Cite this article
Liao, CW., Lee, MT. & Liu, YC. A thermal deformation estimation method for high precision machine tool spindles based on the convolutional neural network. J Mech Sci Technol 37, 3151–3162 (2023). https://doi.org/10.1007/s12206-023-0539-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12206-023-0539-x