Machine learning models for predicting volumetric errors based on scale and master balls artefact probing data

被引:0
作者
Zeng, Min [1 ]
Feng, Miao [2 ]
Mayer, J. R. R. [1 ]
Bitar-Nehme, Elie [1 ]
Duong, Xuan Truong [3 ]
机构
[1] Polytech Montreal, Dept Mech Engn, 2500 Chemin Polytech, Montreal, PQ H3T 1J4, Canada
[2] Univ Montreal, Dept Comp Sci & Operat Res, 2900 Boul Edouard Montpetit, Montreal, PQ H3T 1J4, Canada
[3] Dawson Coll, Dept Mech Engn, 3040 Rue Sherbrooke, Montreal, PQ H3Z 1A4, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Volumetric errors; Five-axis machine tool; Machine learning; SAMBA; COMPENSATION;
D O I
10.1016/j.cirpj.2025.03.003
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The volumetric accuracy of machine tools is important to both machine tool manufacturers and users. Predicting volumetric errors (VEs) is a pre-requisite for their compensation yielding increased dimensional quality of machined parts. However, predicting VEs in five-axis machine tools is challenging due to the complexity of error sources and their associated physics-based model. Machine learning (ML) is used to predict VEs under no load and stable thermal conditions. Data is acquired using a scale and master ball artefact (SAMBA) and on-machine touch probing. A general process for determining the minimum number of balls required to generate data to satisfactorily train an ML model is proposed. The VEs prediction is verified using synthetic data for inter-axis and some intra-axis geometric errors, and then validated using only experimental data. Different datasets based on decreasing number of balls are tested to train either a Neural Networks (NN) or an eXtreme Gradient Boosting (XGBoost) algorithm to compare their performances. The results show that, both NN and XGBoost are effective to predict VEs of a five-axis machine tool with wCBXfZY(S)t topology regardless of the geometric error parameter values. By using only experimental data of twenty balls to train the models, XGBoost outperforms NN in all four error metrics and processing time. A time efficient scheme was tested whereby only two master balls plus one scale bar dataset and an additional master ball (when only the spindle rotates) were used for training NN.
引用
收藏
页码:135 / 157
页数:23
相关论文
共 27 条
  • [1] Araie I, 1996, Google Pat
  • [2] Limitations of lager diagonal measurements
    Chapman, MA
    [J]. PRECISION ENGINEERING-JOURNAL OF THE INTERNATIONAL SOCIETIES FOR PRECISION ENGINEERING AND NANOTECHNOLOGY, 2003, 27 (04): : 401 - 406
  • [3] Chen T., 2015, NIPS 2014 WORKSH HIG, P69
  • [4] XGBoost: A Scalable Tree Boosting System
    Chen, Tianqi
    Guestrin, Carlos
    [J]. KDD'16: PROCEEDINGS OF THE 22ND ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, 2016, : 785 - 794
  • [5] The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation
    Chicco, Davide
    Warrens, Matthijs J.
    Jurman, Giuseppe
    [J]. PEERJ COMPUTER SCIENCE, 2021,
  • [6] Volumetric Error Model for Multi-Axis Machine Tools
    Cong, Dang Chi
    Chinh, Bui Ba
    Jooho, Hwang
    [J]. 43RD NORTH AMERICAN MANUFACTURING RESEARCH CONFERENCE, NAMRC 43, 2015, 1 : 1 - 11
  • [7] Propagation of assembly errors in multitasking machines by the homogenous matrix method
    Diaz-Tena, E.
    Ugalde, U.
    Lopez de Lacalle, L. N.
    de la Iglesia, A.
    Calleja, A.
    Campa, F. J.
    [J]. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2013, 68 (1-4) : 149 - 164
  • [8] A GENERAL METHODOLOGY FOR MACHINE-TOOL ACCURACY ENHANCEMENT BY ERROR COMPENSATION
    DONMEZ, MA
    BLOMQUIST, DS
    HOCKEN, RJ
    LIU, CR
    BARASH, MM
    [J]. PRECISION ENGINEERING-JOURNAL OF THE AMERICAN SOCIETY FOR PRECISION ENGINEERING, 1986, 8 (04): : 187 - 196
  • [9] Machine tool positioning error compensation using artificial neural networks
    Fines, John M.
    Agah, Arvin
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2008, 21 (07) : 1013 - 1026
  • [10] Machine tool calibration: Measurement, modeling, and compensation of machine tool errors
    Gao, Wei
    Ibaraki, Soichi
    Donmez, M. Alkan
    Kono, Daisuke
    Mayer, J. R. R.
    Chen, Yuan -Liu
    Szipka, Karoly
    Archenti, Andreas
    Linares, Jean-Marc
    Suzuki, Norikazu
    [J]. INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE, 2023, 187