数控机床多变量关联热误差组合模型及其实验验证

doi:10.12068/j.issn.1005-3026.2017.05.019

东北大学学报:自然科学版 ›› 2017, Vol. 38 ›› Issue (5): 700-705.DOI: 10.12068/j.issn.1005-3026.2017.05.019

数控机床多变量关联热误差组合模型及其实验验证

马跃¹，王洪福^1,2，孙伟¹，黄余彬¹

(1.大连理工大学机械工程学院，辽宁大连116024; 2.首都航天机械公司，北京100076)

收稿日期:2015-12-16 修回日期:2015-12-16 出版日期:2017-05-15 发布日期:2017-05-11
通讯作者: 马跃
作者简介:马跃(1960-)，男，辽宁大连人，大连理工大学副教授；孙伟(1967-)，男，黑龙江哈尔滨人，大连理工大学教授.
基金资助:
辽宁省科技创新重大专项(201301002); 辽宁省科学技术计划重大项目(2015106016).

Multivariate Correlative and Combined Thermal Error Model for the CNC Machine Tool with Experimental Validation

MA Yue¹， WANG Hong-fu^1,2， SUN Wei¹， HUANG Yu-bin¹

1.School of Mechanical Engineering， Dalian University of Technology， Dalian 116024，China; 2. Capital Aerospace Machinery Company， Beijing 100076， China.

Received:2015-12-16 Revised:2015-12-16 Online:2017-05-15 Published:2017-05-11
Contact: SUN Wei
About author:-
Supported by:
-

摘要/Abstract

摘要：

针对主要基于受综合因素影响的机床本体温度所建立的热误差模型鲁棒性较差的问题.综合考虑机床本体温度、动力源转速、冷却液温度及环境温度提出了多变量关联热误差组合模型.将最小二乘支持向量机(LS-SVM)的方法运用到热误差建模中，并利用偏最小二乘(PLS)方法提取输入变量的主成分作为LS-SVM的输入，形成PLS-LSSVM组合热误差模型.此外根据数控加工过程及材料热变形原理，将相对起始温度的差温值作为温度输入，使热误差补偿更加准确.在某型号精密加工中心进行实验验证，结果表明:PLS-LSSVM模型比LS-SVM更稳定，比PLSR预测精度高;考虑差温多变量的PLS-LSSVM模型较单纯考虑机床本体测量温度值的PLS-LSSVM*模型，热误差预测值的均方根误差(RMSE)平均减少了5.5μm.

关键词: 数控机床, 热误差模型, 热误差影响因素, 偏最小二乘, 最小二乘支持向量机

Abstract:

To solve the problem that based on machine tool temperature that is comprehensively influenced by other factors， and thus the thermal error models had poor robustness， a multivariate correlative and combined thermal error model was put forward， which overall considers machine tool temperature， speed of power source， and temperature of coolant and environment. Least squares support vector (LS-SVM) method was applied to the thermal error model， and partial least squares (PLS) method was applied to extract the principal components as the input of LS-SVM， and the PLS-LSSVM thermal error combined model was then formulated. In addition， this model set the differential temperatures， relatively with initial temperatures， as the temperature variable， which is based on the process of numerical control machining and the principle of material thermal deformation， to make the thermal error compensation more accurate. It was tested on a precision machining center， whose results showed that the PLS-LSSVM thermal error model is more stable than the LS-SVM model， and more accurate than the partial least squares regression (PLSR) model. Besides， the root mean square error (RMSE) of the predictive thermal error with the PLS-LSSVM model is 5.5μm on average less than that with the PLS-LSSVM* model， which only takes into account the temperature measurements of the machine tool.

Key words: CNC machine tool, thermal error model, influence factor of thermal error, partial least squares, least squares support vector machine

中图分类号:

TH161.4

马跃，王洪福，孙伟，黄余彬. 数控机床多变量关联热误差组合模型及其实验验证[J]. 东北大学学报:自然科学版, 2017, 38(5): 700-705.

MA Yue， WANG Hong-fu， SUN Wei， HUANG Yu-bin. Multivariate Correlative and Combined Thermal Error Model for the CNC Machine Tool with Experimental Validation[J]. Journal of Northeastern University:Natural Science, 2017, 38(5): 700-705.

参考文献

[1]Ramesh R，Mannan M A，Poo A N.Error compensation in machine tools:a review part I:geometric，cutting-force induced and fixture-dependent errors［J］.International Journal of Machine Tools & Manufacture，2000，40(9):1235-1256.
[2]Creighton E，Honegger A，Tulsian A，et al.Analysis of thermal errors in a high-speed micro-milling spindle［J］.International Journal of Machine Tools & Manufacture，2010，50 (4):386-393.
[3]Eneko G A，Aitor O，Javier O，et al.Methodology for the design of a thermal distortion compensation for large machine tools based in state-space representation with Kalman filter［J］.International Journal of Machine Tools & Manufacture， 2013，75(1):100-108.
[4]Huang Y Q，Zhang J，Li X，et al.Thermal error modeling by integrating GA and BP algorithms for the high-speed spindle［J］.International Journal of Advanced Manufacturing Technology，2014，71:1669-1675.
[5]Li Y，Zhao W H，Wu W W，et al.Thermal error modeling of the spindle based on multiple variables for the precision machine tool［J］.International Journal of Advanced Manufacturing Technology， 2014，72:1415-1427.
[6]Lee E S，Lee C H，Kim S C.Machining accuracy improvement by automatic tool setting and on machine verification［J］.Key Engineering Materials， 2008，381/382:199-202.
[7]ISO 230-3:2007 Test code for machine tools—part3:determination of thermal effects［S］.Sydney:SAI Global，2007:15-19.
[8]邓乃杨，田英杰．支持向量机:理论、算法与拓展［M］.北京:科学出版社，2009:182-189.(Deng Nai-yang，Tian Ying-jie.Support vector machine:theory algorithms and expansion［M］.Beijing:Science Press Publishing，2009:182-189.)
[9]马跃，王洪福，孙伟，等.基于IFCM-GRA的空间多维.热误差温度测点优化［J］.大连理工大学学报，2016，56(3):236-243.(Ma Yue，Wang Hong-fu，Sun Wei，et al.Optimization of temperature measuring points in multi-dimensional space for thermal error based on IFCM-GRA［J］.Journal of Dalian University of Technoloty，2016，5(3):236-243.)

[1]	单鹏，吴缀，何年，刘隆兴. 基于ATR-FTIR光谱的γ-PGA发酵批次分类研究[J]. 东北大学学报（自然科学版）, 2022, 43(10): 1376-1382.
[2]	赵煜辉，芦鹏程，刘晓东，齐天舒. 基于校正分布差异的标定迁移方法研究[J]. 东北大学学报（自然科学版）, 2021, 42(3): 310-317.
[3]	单鹏，何年，李志刚，吴缀. 分数阶微分Whittaker平滑器[J]. 东北大学学报（自然科学版）, 2021, 42(11): 1527-1532.
[4]	黄智，刘永超，廖荣杰，曹旭军. 基于SSO算法优化神经网络的数控机床热误差建模[J]. 东北大学学报（自然科学版）, 2021, 42(11): 1569-1578.
[5]	赵春雨，侯森林，李朕均. 进给系统成对安装的角接触球轴承热分析[J]. 东北大学学报:自然科学版, 2020, 41(5): 700-705.
[6]	李朕均，赵春雨，闻邦椿，卢泽宸. 数控机床进给系统热源发热率辨识与热误差预测[J]. 东北大学学报:自然科学版, 2019, 40(9): 1305-1309.
[7]	李铁军，赵春雨，张义民. 数控机床进给系统热误差自适应解析模型[J]. 东北大学学报:自然科学版, 2018, 39(6): 834-839.
[8]	谭国威，马钦海，孙琦. 服务类企业管理者特征与工作绩效之间的关系[J]. 东北大学学报:自然科学版, 2017, 38(8): 1206-1210.
[9]	陈晔，赵春雨，张义民，闻邦椿. 数控机床进给系统的摩擦力特性[J]. 东北大学学报:自然科学版, 2017, 38(7): 993-997.
[10]	王超，王建辉，顾树生，张宇献. 基于优化支持向量机的带钢延伸量软测量研究[J]. 东北大学学报:自然科学版, 2015, 36(8): 1084-1088.
[11]	盛忠起，徐涛，旋嘉耀，宋均有. 基于遗传算法的数控机床服务模块配置设计[J]. 东北大学学报:自然科学版, 2015, 36(6): 848-852.
[12]	刘卓，柴天佑，汤健. 一种多尺度球磨机筒体振动频谱分析与建模方法[J]. 东北大学学报:自然科学版, 2015, 36(3): 305-308.
[13]	张义民，贾敬存，黄贤振. 基于数控机床故障信息的可靠性模糊分配[J]. 东北大学学报:自然科学版, 2015, 36(2): 245-249.
[14]	佟昕，陈凯，李刚. 中国碳排放影响因素分析和趋势预测——基于STIRPAT 和GM(1，1)模型的实证研究[J]. 东北大学学报:自然科学版, 2015, 36(2): 297-300.
[15]	石松宁，王大志，时统宇. 永磁驱动器偏心磁极的优化设计[J]. 东北大学学报:自然科学版, 2014, 35(8): 1078-1082.

数控机床多变量关联热误差组合模型及其实验验证

Multivariate Correlative and Combined Thermal Error Model for the CNC Machine Tool with Experimental Validation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价