A machine-learning based solution for chatter prediction in heavy-duty milling machines

被引:43
|
作者
Oleaga, Ibone [1 ]
Pardo, Carlos [2 ]
Zulaika, Juan J. [1 ]
Bustillo, Andres [2 ]
机构
[1] Tecnalia, Ind & Transport Div, San Sebastian, Spain
[2] Univ Burgos, Dept Civil Engn, Avda Cantabria S-N, Burgos 09006, Spain
关键词
Random Forest; Regression trees; Milling; Vibrations; Chatter; Polar diagrams; ARTIFICIAL-INTELLIGENCE; SURFACE-ROUGHNESS; STABILITY; QUALITY; WEAR;
D O I
10.1016/j.measurement.2018.06.028
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
The main productivity constraints of milling operations are self-induced vibrations, especially regenerative chatter vibrations. Two key parameters are linked to these vibrations: the depth of cut achievable without vibrations and the chatter frequency. Both parameters are linked to the dynamics of machine component excitation and the milling operation parameters. Their identification in any cutting direction in milling machine operations requires complex analytical models and mechatronic simulations, usually only applied to identify the worst cutting conditions in operating machines. This work proposes the use of machine learning techniques with no need to calculate the two above-mentioned parameters by means of a 3-step strategy. The strategy combines: 1) experimental frequency responses collected at the tool center point; 2) analytical calculations of both parameters; and, 3) different machine learning techniques. The results of these calculations can then be used to predict chatter under different combinations of milling directions and machine positions. This strategy is validated with real experiments on a bridge milling machine performing concordance roughing operations on AISI 1045 steel with a 125mm diameter mill fitted with nine cutters at 45 degrees, the results of which have confirmed the high variability of both parameters along the working volume. The following regression techniques are tested: artificial neural networks, regression trees and Random Forest. The results show that Random Forest ensembles provided the highest accuracy with a statistical advantage over the other machine learning models; they achieved a final accuracy of 0.95mm for the critical depth and 7.3 Hz for the chatter frequency (RMSE) in the whole working volume and in all feed directions, applying a 10x10 cross validation scheme. These RMSE values are acceptable from the industrial point of view, taking into account that the critical depth of this range varies between 0.68mm and 19.20mm and the chatter frequency between 1.14 Hz and 65.25 Hz. Besides, Random Forest ensembles are more easily optimized than artificial neural networks (1 parameter configuration versus 210 MLPs). Additionally, tools that incorporate regression trees are interesting and highly accurate, providing immediately accessible and useful information in visual formats on critical machine performance for the design engineer.
引用
收藏
页码:34 / 44
页数:11
相关论文
共 50 条
  • [1] Chatter prediction based on frequency domain solution in CNC pocket milling
    Ko, Jeong Hoon
    Shaw, Kah Chuan
    INTERNATIONAL JOURNAL OF PRECISION ENGINEERING AND MANUFACTURING, 2009, 10 (04) : 19 - 25
  • [2] Chatter prediction based on frequency domain solution in CNC pocket milling
    Jeong Hoon Ko
    Kah Chuan Shaw
    International Journal of Precision Engineering and Manufacturing, 2009, 10 : 19 - 25
  • [3] Theoretical-experimental modeling of milling machines for the prediction of chatter vibration
    Catania, Giuseppe
    Mancinelli, Nicolo
    INTERNATIONAL JOURNAL OF MACHINE TOOLS & MANUFACTURE, 2011, 51 (04) : 339 - 348
  • [4] Robust prediction of chatter stability in milling based on the analytical chatter stability
    Graham, E.
    Mehrpouya, M.
    Park, S. S.
    JOURNAL OF MANUFACTURING PROCESSES, 2013, 15 (04) : 508 - 517
  • [5] A study on the extreme learning machine based prediction of machining times of the cycloidal gears in CNC milling machines
    Gurgenc, Turan
    Ucar, Ferhat
    Korkmaz, Deniz
    Ozel, Cihan
    Ortac, Yunus
    PRODUCTION ENGINEERING-RESEARCH AND DEVELOPMENT, 2019, 13 (06): : 635 - 647
  • [6] Preventing chatter vibrations in heavy-duty turning operations in large horizontal lathes
    Urbikain, G.
    Campa, F. -J.
    Zulaika, J. -J.
    Lopez de Lacalle, L. -N.
    Alonso, M. -A.
    Collado, V.
    JOURNAL OF SOUND AND VIBRATION, 2015, 340 : 317 - 330
  • [7] Physics-supported Bayesian machine learning for chatter prediction with process damping in milling
    Akbari, Vahid Ostad Ali
    Eichenberger, Andrea
    Wegener, Konrad
    CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY, 2024, 55 : 165 - 173
  • [8] On-line chatter detection in milling with hybrid machine learning and physics-based model
    Rahimi, M. Hossein
    Huynh, Hoai Nam
    Altintas, Yusuf
    CIRP JOURNAL OF MANUFACTURING SCIENCE AND TECHNOLOGY, 2021, 35 : 25 - 40
  • [9] A model-based adaptive controller for chatter mitigation and productivity enhancement in CNC milling machines
    Bort, Carlos Maximiliano Giorgio
    Leonesio, Marco
    Bosetti, Paolo
    ROBOTICS AND COMPUTER-INTEGRATED MANUFACTURING, 2016, 40 : 34 - 43
  • [10] Machine-learning for automatic prediction of flatness deviation considering the wear of the face mill teeth
    Bustillo, Andres
    Pimenov, Danil Yu
    Mia, Mozammel
    Kaplonek, Wojciech
    JOURNAL OF INTELLIGENT MANUFACTURING, 2021, 32 (03) : 895 - 912