基于红外成像与卷积神经网络的滚珠丝杠进给系统热误差动态补偿方法
Dynamic Compensation Method for Thermal Error in Ball Screw Feed System Based on Infrared Imaging and Convolutional Neural Network
摘要: 滚珠丝杠作为机床进给系统的直线进给传动装置，由于受到非均匀热场的影响，其热误差成为影响机床加工精度的重要因素。为了降低非均匀热场产生的影响，本文提出一种基于红外成像与卷积神经网络的滚珠丝杠进给系统热误差动态补偿方法。给出了一套基于多模型集合的滚珠丝杠分段补偿方法，建立了基于红外成像与卷积神经网络的热误差模型。结果表明，相对于无补偿、选取特征点的Back Propagation (BP)神经网络模型补偿和全图层BP (ABP)神经网络模型补偿，定位误差的均方根分别减少了90.3%、53.4%、55.3%。
Abstract: As a linear feed transmission device in the machine tool feed system, the ball screw is affected by the non-uniform thermal field, and its thermal error has become an important factor affecting the machining accuracy of the machine tool. In order to reduce the influence of non-uniform thermal field, this paper proposes a dynamic compensation method for thermal error of ball screw feed sys-tem based on infrared imaging and convolutional neural network. A multi-model ensemble based ball screw segment compensation method is provided, and a thermal error model based on infrared imaging and convolutional neural network is established. The results show that compared with the no compensation method, the Back Propagation (BP) neural network model compensation method with selected feature points, and the full layer BP (ABP) neural network model compensation method, the root mean square error of positioning is reduced by 90.3%, 53.4%, and 55.3%, respec-tively.
文章引用：吴宇航. 基于红外成像与卷积神经网络的滚珠丝杠进给系统热误差动态补偿方法[J]. 建模与仿真, 2023, 12(3): 2173-2181. https://doi.org/10.12677/MOS.2023.123199

参考文献

[1] Altintas, Y., Verl, A., Brecher, C., Uriarte, L. and Pritschow, G. (2011) Machine Tool Feed Drives. CIRP Annals, 60, 779-796. [Google Scholar] [CrossRef] 
[2] Sun, W., Cao, X., Chen, B., Zhou, Y., Shen, Z. and Xiang, J. (2020) A Two-Stage Vision-Based Method for Measuring the Key Parameters of Ball Screws. Precision Engineering, 66, 76-86. [Google Scholar] [CrossRef] 
[3] Huang, S.-C. (1995) Analysis of a Model to Forecast Thermal Deformation of Ball Screw Feed Drive Systems. International Journal of Machine Tools & Manufacture, 35, 1099-1104. [Google Scholar] [CrossRef] 
[4] Ma, C., Liu, J. and Wang, S. (2020) Thermal Error Compensation of Linear Axis with Fixed-Fixed Installation. International Journal of Mechanical Sciences, 175, Article ID: 105531. [Google Scholar] [CrossRef] 
[5] Li, Y.X., Yang, J.G., Gelvis, T. and Li, Y.Y. (2008) Optimization of Measuring Points for Machine Tool Thermal Error Based on Grey System Theory. International Journal of Advanced Manu-facturing Technology, 35, 745-750. [Google Scholar] [CrossRef] 
[6] Shi, H., Jiang, C., Yan, Z., Tao, T. and Mei, X. (2020) Bayesian Neural Network-Based Thermal Error Modeling of Feed Drive System of CNC Machine Tool. The International Journal of Advanced Manufacturing Technology, 108, 3031-3044. [Google Scholar] [CrossRef] 
[7] Xu, Z.Z., Liu, X.J., Kim, H.K., Shin, J.H. and Lyu, S.K. (2011) Thermal Error Forecast and Performance Evaluation for an Air-Cooling Ball Screw Sys-tem. International Journal of Machine Tools & Manufacture, 51, 605-611. [Google Scholar] [CrossRef] 
[8] Ma, C., Zhao, L., Mei, X., Shi, H. and Yang, J. (2017) Thermal Error Compensation of High-Speed Spindle System Based on a Modified BP Neural Network. International Journal of Ad-vanced Manufacturing Technology, 89, 3071-3085. [Google Scholar] [CrossRef] 
[9] Jin, C., Wu, B. and Hu, Y. (2015) Temperature Distribution and Thermal Error Prediction of a CNC Feed System under Varying Operating Condi-tions. The International Journal of Advanced Manufacturing Technology, 77, 1979-1992. [Google Scholar] [CrossRef] 
[10] Wang, H., Li, F., Cai, Y., Liu, Y. and Yang, Y. (2020) Experimental and Theoretical Analysis of Ball Screw under Thermal Effect. Tribology International, 152, Article ID: 106503. [Google Scholar] [CrossRef] 
[11] Heisel, U., Koscsák, G. and Stehle, T. (2006) Thermography-Based Investigation into Thermally Induced Positioning Errors of Feed Drives by Example of a Ball Screw. CIRP Annals, 55, 423-426. [Google Scholar] [CrossRef] 
[12] 王全宝, 肖宁, 余光怀, 等. 滚珠丝杠进给系统热变形研究[J]. 制造技术与机床, 2015(8): 154-157.
[13] Zapata, J. (2017) Measurements of Temperature of CNC Machine Tool Ball Screw Utilising IR Method. International Journal of Applied Mechanics & Engineering, 22, 769-777. [Google Scholar] [CrossRef] 
[14] Li, J., Wu, R., Zhao, J. and Ma, Y. (2017) Convolutional Neural Networks (CNN) for Indoor Human Activity Recognition Using Ubisense System. 2017 29th Chinese Control And Decision Conference (CCDC), Chongqing, 28-30 May 2017, 2068-2072. [Google Scholar] [CrossRef] 
[15] Helbing, G. and Ritter, M. (2017) Power Curve Monitoring with Flexible EWMA Control Charts. 2017 International Conference on Promising Electronic Technologies (ICPET), Deir El-Balah, 16-17 October 2017, 124-128. [Google Scholar] [CrossRef] 
[16] Li, X., Fu, X.M., Xiong, F.R. and Bai, X.M. (2020) Deep Learning-Based Unsupervised Representation Clustering Methodology for Automatic Nuclear Reactor Operating Transient Identification. Knowledge-Based Systems, 204, Article ID: 106178. [Google Scholar] [CrossRef] 
[17] Al-Antari, M.A., Han, S.-M. and Kim, T.-S. (2020) Evaluation of Deep Learning Detection and Classification towards Computer-Aided Diagno-sis of Breast Lesions in Digital X-Ray Mammograms. Computer Methods and Programs in Biomedicine, 196, Article ID: 105584. [Google Scholar] [CrossRef] [PubMed]
[18] Ornek, A.H., Ceylan, M. and Ervural, S. (2019) Health Status Detection of Neonates Using Infrared Thermography and Deep Convolutional Neural Networks. Infrared Physics & Technolo-gy, 103, Article ID: 103044. [Google Scholar] [CrossRef] 
[19] Akram, M.W., Li, G., Jin, Y., et al. (2020) Automatic Detection of Photovoltaic Module Defects in Infrared Images with Isolated and Develop-Model Transfer Deep Learning. Solar Energy, 198, 175-186. [Google Scholar] [CrossRef] 
[20] Mayr, J., Jedrzejewski, J., Uhlmann, E., et al. (2012) Thermal Issues in Machine Tools. CIRP Annals, 61, 771-791. [Google Scholar] [CrossRef] 

为你推荐