An Ensemble Modeling for Thermal Error of CNC Machine Tools
Thermal error caused by the thermal deformation of computer numerical control (CNC) machine tools is one of the main factors to affect the machining accuracy. With monitoring data of the temperature field, establishing data-driven thermal error model is considered as a more convenient, effective and cost-efficient way to reduce the thermal error. As a matter of fact, it is very difficult to develop a thermal error model with perfect generalization adapting to different working conditions of machining tools. In this paper, a method of an ensemble modeling (EM) based on Convolution Neural Network (CNN) and Back Propagation (BP) Neural Network for modeling thermal error is presented. This ensemble model takes full advantages of two different neural networks, namely CNN having self-extracting feature to solve collinear problem in temperature field and BP can process heat source to thermal error by mapping nonlinear function, then combined into a EM. To demonstrate the effectiveness of the proposed model, an experiment platform was set up based on a heavy-duty CNC machine tool. The results show that the proposed model achieves better accuracy and strong robustness in comparison with only with BP network and CNN network respectively.
KeywordsThermal error Ensemble modeling CNC machine Convolution neural network Back propagation network
The authors would like to acknowledge funding support from the National Natural Science Foundation Committee of China under Grant No. 51475347 and the Major Project of Technological Innovation Special Fund of Hubei Province Grant No. 2016AAA016, as well as the contributions from all collaborators within the projects mentioned. We would also like to thank Wuhan University of Technology, People’s Republic of China in supporting this work.
- 3.Postlethwaite, S.R., Allen, J.P., Ford, D.G.: Machine tool thermal error reduction—an appraisal. Proc. Inst. Mech. Eng. 213(213), 1–9 (1999)Google Scholar
- 4.Section I.: An adaptive finite element method for stationary incompressible thermal flow based on projection error estimation. Math. Prob. Eng. 2013(2), 1–14 (2013)Google Scholar
- 5.Kim, J., Zverv, I., Lee, K.: Thermal model of high-speed spindle units. Intell. Inf. Manag. 02(05), 306–315 (2010)Google Scholar
- 8.Pahk, H.J., Lee, S.W.: Thermal error measurement and real time compensation system for the CNC machine tools incorporating the spindle thermal error and the feed axis thermal error. In: Hayhurst, D.R. (ed.) Proceedings of the 33rd International Conference, pp. 249–254. Springer, Heidelberg (2000). https://doi.org/10.1007/978-1-4471-0777-4_39CrossRefGoogle Scholar
- 11.Ren, X., Sun, Y., Zhou, T., Xu, W., Yue, Y.: Real-time thermal error compensation on machine tools using improved BP neural network. In: 2011 International Conference on Electric Information and Control Engineering, Wuhan, pp. 630–632 (2011)Google Scholar
- 12.Wang, J., Qin, B., Liu, Y., Yang, Y.: Thermal error prediction of numerical control machine based on improved particle swarm optimized back propagation neural network. In: 11th International Conference on Natural Computation (ICNC), Zhangjiajie, pp. 820–824 (2015)Google Scholar
- 13.Wang, P., Jin, Z.F., Zheng, Y.l.: Artificial neural network-based thermal error model-ling in ball screw. In: IEEE Symposium on Electrical & Electronics Engineering (EEESYM), Kuala Lumpur, pp. 67–70 (2012)Google Scholar
- 14.Ren, B., Ren, X., Huang, S., Li, G.: The research on thermal error modeling and compensation on machine tools. In: International Conference on Control Engineering and Communication Technology, Liaoning, pp. 444–447 (2012)Google Scholar
- 15.Pani, A.K., Mohanta, H.K.: A hybrid soft sensing approach of a cement mill using principal component analysis and artificial neural networks. In: 3rd IEEE International Advance Computing Conference (IACC), Ghaziabad, pp. 713–718 (2013)Google Scholar
- 16.Zhao, C., Wang, Y.: Optimization of measuring points based on the grey system theory for spindle of CNC machine tool. In: International Conference on Mechatronics and Automation, Changchun, pp. 686–690 (2009)Google Scholar
- 19.Yan, J., Meng, Y., Lu, L., Guo, C.: Big-data-driven based intelligent prognostics scheme in industry 4.0 environment. In: Prognostics and System Health Management Conference (PHM-Harbin), Harbin, pp. 1–5 (2017)Google Scholar
- 22.SU, Y.-F., Yuan, W.X., Liu, D.P., et al.: A thermal errors compensation model for high-speed motorized spindle based on bp neural network. Modul. Mach. Tool Autom. Manuf. Tech. (2013)Google Scholar