Research on thermal error modeling of machine tool based on bayesian neural network
-
摘要: 热误差严重影响着机床的加工精度，对机床关键部件进行热特性分析是开发精密机床的重要环节。通过测量包括数控机床的特殊位置温度和定位误差在内的热特性，研究了温升与定位误差之间的关系，提出了一种基于贝叶斯神经网络的热误差建模方法。通过K-means聚类和相关系数法来选择温度敏感点，可以有效地抑制温度测量点之间的多重共线性问题。结果表明：通过使用贝叶斯神经网络能提高机床88.015 9%的精度，比BP神经网络高出15.763 8%，与BP神经网络模型相比，贝叶斯神经网络具有更加优良预测性能。贝叶斯神经网络模型为降低机床热误差的影响提供了新思路。Abstract: Thermal error seriously affects the machining accuracy of the machine tool. The thermal characteristic analysis of the key parts of the machine tool is an important link in the development of precision machine tool. Therefore, this paper studies the relationship between temperature rise and positioning error by measuring the thermal characteristics including the temperature and positioning error of special position of CNC machine tool, and proposes a thermal error modeling method based on Bayesian neural network. Using K-means clustering and correlation coefficient method to select temperature sensitive points can effectively suppress multicollinearity between temperature measurement points. The results show that the accuracy of machine tool can be improved by 88.015 9% by using bayesian neural network, which is 15.763 8% higher than BP neural network. Compared with BP neural network model, bayesian neural network has better prediction performance. Bayesian neural network model provides a new idea to reduce the influence of thermal error of machine tool.
-
Key words:
- machine tool /
- thermal error /
- BP neural network /
- bayesian neural network
-
表 1 各温度传感器具体位置
位置 传感器 主轴电机 T1 主轴轴承 T2 X轴导轨滑块 T3 Y轴导轨滑块 T4 Z轴导轨滑块 T5 X轴丝杠螺母 T6 Z轴丝杠螺母 T7 Y轴丝杠螺母 T8 
下载: 导出CSV
表 3 温度变量相关系数
温度传感器 相关系数 T1 0.917 8 T2 0.834 2 T3 0.726 9 T4 0.699 7 T5 0.892 1 T6 0.775 8 T7 0.814 5 T8 0.763 7
下载: 导出CSV
表 4 模型性能指标
模型 ΔEmax/μm ΔE/μm MSE/μm η BP 1.430 1 0.644 3 0.592 7 89.292 1% BNN 1.732 8 0.474 5 0.400 4 91.269 6%
下载: 导出CSV
表 5 模型性能指标
模型 ΔEmax/μm ΔE/μm MSE/μm η BP 2.297 1 1.266 6 2.100 4 72.252 1% BNN 1.473 9 0.705 2 0.625 1 88.015 9%
下载: 导出CSV
-
[1] Ramesh R, Mannan M A, Poo A N. Error compensation in machine tools-a review[J]. International Journal of Machine Tools and Manufacture, 2000, 40(9): 12-19. [2] Josef M, Jerzy J, Eckart U, et al. Thermal issues in machine tools[J]. CIRP Annals-Manufacturing Technology, 2012, 61(2): 43-58. [3] 余文利, 姚鑫骅. 改进混沌粒子群优化的灰色系统模型在机床热误差建模中的应用[J]. 现代制造工程, 2018, 21(6): 101-107, 22. [4] 张毅, 杨建国. 基于灰色理论预处理的神经网络机床热误差建模[J]. 机械工程学报, 2011, 47(7): 134-139. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201107021.htm [5] 张毅, 杨建国. 基于灰色神经网络的机床热误差建模[J]. 上海交通大学学报, 2011, 45(11): 1581-1586. https://www.cnki.com.cn/Article/CJFDTOTAL-SHJT201111003.htm [6] 郑金勇, 刘保国, 冯伟. 基于遗传算法优化灰色神经网络的机床主轴热误差建模研究[J]. 机电工程, 2019, 36(6): 602-607. doi: 10.3969/j.issn.1001-4551.2019.06.009 [7] 谭峰, 殷国富, 殷勤, 等. 基于GM-LS-SVM层级模型的数控机床热误差建模[J]. 中南大学学报: 自然科学版, 2016, 47(12): 4028-4034. https://www.cnki.com.cn/Article/CJFDTOTAL-ZNGD201612010.htm [8] 李彬, 张云, 王立平, 等. 基于遗传算法优化小波神经网络数控机床热误差建模[J]. 机械工程学报, 2019, 55(21): 215-220. https://www.cnki.com.cn/Article/CJFDTOTAL-JXXB201921023.htm [9] Shi H, Jiang C, Yan Z, et al. Bayesian neural network-based thermal error modeling of feed drive system of CNC machine tool[J]. The International Journal of Advanced Manufacturing Technology, 2020, 108(9): 3031-3044. [10] Blundell C, Cornebise J, Kavukcuoglu K, et al. Weight uncertainty in neural network[C]//International Conference on Machine Learning. PMLR, 2015, 23(7): 1613-1622. [11] Kingma D P, Salimans T, Welling M. Variational dropout and the local reparameterization trick[J]. IEICE Transactions on Fundamantals of Electronics, Communications and Computer Sciences, 2015, 34(2): 2575-2583. [12] Kingma D P, Welling M. Auto-encoding variational bayes[J]. arxiv: Machine Learning, 2013. [13] Mater M, Zwicker R, Akbari M, et al, Wegener K Bayesian optimization for autonomous process set-up in turning[J]. CIRP Journal of Manufacturing Science and Technology, 2019, 26: 81-87. [14] Ticknor J L. A Bayesian regularized artificial neural networkfor stock market forecasting[J]. Expert Systems with Application, 2013, 40(14): 5501-5506. [15] 余文利, 姚鑫骅, 傅建中, 等. 贝叶斯证据框架下的LS-SVM多工况数控机床热误差建模[J]. 中国机械工程, 2014, 25(17): 2361-2368. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJX201417017.htm [16] 吴雄彪, 姚鑫骅, 傅建中. 基于贝叶斯网络的数控机床热误差建模[J]. 中国机械工程, 2009, 20(3): 293-296. https://www.cnki.com.cn/Article/CJFDTOTAL-ZGJX200903010.htm [17] 徐洋. 基于动态贝叶斯网络的精密机床热误差研究与应用[D]. 上海: 上海工程技术大学, 2016. [18] 王承辉. 基于深度学习的大型龙门五面加工中心热误差建模方法与补偿[D]. 重庆: 重庆理工大学, 2019. [19] 杜柳青, 李仁杰. 基于优化模糊神经网络的高速数控机床热误差建模方法[J]. 组合机床与自动化加工技术, 2020(8): 8-11. https://www.cnki.com.cn/Article/CJFDTOTAL-ZHJC202008003.htm [20] 马雨萌. 立式加工中心热误差的测量与分析研究[D]. 济南: 济南大学, 2019. [21] 陈维范, 薛丹. 数控车床热误差建模与补偿研究[J]. 机床与液压, 2020, 48(14): 171-175. https://www.cnki.com.cn/Article/CJFDTOTAL-JCYY202014039.htm -
下载:
点击查看大图
图(6) / 表(5)
计量
- 文章访问数: 127
- HTML全文浏览量: 24
- PDF下载量: 36
- 被引次数: 0
