INDIRECT DRILL CONDITION MONITORING BASED ON MACHINE TOOL CONTROL SYSTEM DATA

被引:2
|
作者
Kolar, Petr [1 ]
Burian, David [1 ]
Fojtu, Petr [2 ]
Masek, Petr [2 ]
Fiala, Stepan [1 ]
Chladek, Stepan [1 ]
Petracek, Petr [1 ]
Sveda, Jiri [1 ]
Rytir, Michal [1 ,2 ]
机构
[1] Czech Tech Univ, Czech Inst Informat Robot & Cybernet, Dept Ind Prod & Automation, Prague, Czech Republic
[2] Czech Tech Univ, Fac Mech Engn, Res Ctr Mfg Technol, Dept Prod Machines & Equipment, Prague, Czech Republic
来源
MM SCIENCE JOURNAL | 2022年 / 2022卷
关键词
tool wear monitoring; edge computing; spiral drill wear; smart machine tools; correlation analysis; CUTTING FORCE; SIGNAL; VIBRATION;
D O I
10.17973/MMSJ.2022_10_2022119
中图分类号
TH [机械、仪表工业];
学科分类号
0802 ;
摘要
Automatic process monitoring, including tool wear monitoring, is a key aspect of improving the energy efficiency and cost of the machining process. The tool flank wear continuously increases during drilling operations. The intensity of tool wear may vary depending on the local properties of the material and the process settings. This paper shows the potential of drill condition monitoring based on machine tool control system data, namely spindle drive current and Z slide current. The workpiece vibration measurement is used as a reference method. Correlations of various features of monitored signals are evaluated. These features are shown to depend, in general, on the instantaneous drilling depth. Among the features investigated, the RMS signal has been shown to exhibit a significant correlation with tool wear. The results were compared for two values of cutting speed. The correlation of selected features is shown to be independent of the total lifetime of the tool, thus demonstrating the attractiveness of these features for tool wear prediction. Specifically, the root mean square of the vibration and spindle torque signals strongly correlate with flank wear near the bottom of the hole while the root mean square of the drive current of the drilling axis strongly correlates with flank wear near the middle of the hole.
引用
收藏
页码:5905 / 5912
页数:8
相关论文
共 50 条
  • [41] Tool wear classification in precision machining using distance metrics and unsupervised machine learning: Unsupervised ML for tool condition monitoring
    Mishra, Debasish
    Awasthi, Utsav
    Pattipati, Krishna R.
    Bollas, George M.
    JOURNAL OF INTELLIGENT MANUFACTURING, 2025, 36 (01) : 331 - 355
  • [42] A tool wear condition monitoring approach for end milling based on numerical simulation
    Zhu, Qinsong
    Sun, Weifang
    Zhou, Yuqing
    Gao, Chen
    EKSPLOATACJA I NIEZAWODNOSC-MAINTENANCE AND RELIABILITY, 2021, 23 (02): : 371 - 380
  • [43] A tool wear condition monitoring approach for end milling based on numerical simulation
    Zhu Q.
    Sun W.
    Zhou Y.
    Gao C.
    Eksploatacja i Niezawodnosc, 2021, 23 (02): : 371 - 380
  • [44] A tool condition monitoring method based on two-layer angle kernel extreme learning machine and binary differential evolution for milling
    Zhou, Yuqing
    Sun, Bintao
    Sun, Weifang
    MEASUREMENT, 2020, 166
  • [45] Tool condition monitoring of diamond-coated burrs with acoustic emission utilising machine learning methods
    Jessel, Thomas
    Byrne, Carl
    Eaton, Mark
    Merrifield, Ben
    Harris, Stuart
    Pullin, Rhys
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2024, 130 (3-4): : 1107 - 1124
  • [46] Ultra low power wireless multi-sensor platform dedicated to machine tool condition monitoring
    Caroff, Tristan
    Brulais, Sebastien
    Faucon, Adrien
    Boness, Axel
    Arrizabalaga, Anne Sanz
    Ellinger, Johannes
    30TH INTERNATIONAL CONFERENCE ON FLEXIBLE AUTOMATION AND INTELLIGENT MANUFACTURING (FAIM2021), 2020, 51 : 296 - 301
  • [47] Machine condition monitoring in FDM based on electret microphone, SVM, and neural networks
    Lopes, Thiago Glissoi
    Aguiar, Paulo Roberto
    Monson, Paulo Monteiro de Carvalho
    D'Addona, Doriana Marilena
    Conceicao Junior, Pedro de Oliveira
    de Oliveira Junior, Reinaldo Goetz
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2023, 129 (3-4): : 1769 - 1786
  • [48] Condition Monitoring of Single Point Cutting Tools Based on Machine Learning Approach
    Gangadhar, N.
    Kumar, Hemantha
    Narendranath, S.
    Sugumaran, V.
    INTERNATIONAL JOURNAL OF ACOUSTICS AND VIBRATION, 2018, 23 (02): : 131 - 137
  • [49] Unsupervised Tool Wear Monitoring in the Corner Milling of a Titanium Alloy Based on a Cutting Condition-Independent Method
    Li, Zhimeng
    Zhong, Wen
    Shi, Yonggang
    Yu, Ming
    Zhao, Jian
    Wang, Guofeng
    MACHINES, 2022, 10 (08)
  • [50] Image-based tool condition monitoring based on convolution neural network in turning process
    Kou, Rui
    Lian, Shi-wei
    Xie, Nan
    Lu, Bei-er
    Liu, Xue-mei
    INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY, 2022, 119 (5-6): : 3279 - 3291