Manufacturing Technology 2023, 23(4):392-398 | DOI: 10.21062/mft.2023.055

Identification Method of Vibration Drilling Bit Wear State Based on Signal Im-aging and Deep Learning

Yingyu Du ORCID...1, Zhiyi Lu ORCID...2, Enquan Chang ORCID...2, Qinghua Li ORCID...2, Yaochen Shi ORCID...2
1 College of Mechanical and Electrical, Changchun Polytechnic, Changchun 130022, China
2 College of Mechanical and Vehicular Engineering, Changchun University, Changchun 130022, China

In vibration-assisted drilling, the wear state of the drill bit affects the processing quality of the hole. The traditional method of identifying the wear state of the drill bit adopts the method of packet de-composition, ignoring the timing characteristics of the signal. In this paper, the force and acoustic emission signals in vibration-assisted drilling are used. The Gram angle field converts the one-dimensional time series into a two-dimensional image, while retaining the trajectory of the time se-ries in the high-dimensional space. Based on the Graham difference field (GADF) image of force and AE, the Inception improved convolutional neural network (IN-CNN) is used to identify the wear state. The experiment proves that compared with the traditional convolutional neural network, BP neural network and support vector machine, the recognition rate of IN-CNN drill wear state based on GADF is 93.1 %, which is increased by 2.5 %, 10.6 % and 8.1 % respectively. It provides a reliable condition monitoring method for the state identification of the drill bit in semi-closed vibration-assisted machining, and has practical engineering significance for improving the machining accuracy and efficiency of composite equal-holes.

Keywords: Vibration drilling, State recognition, Convolutional neural network, Gram angle field
Grants and funding:

Jilin Provincial Science and Technology Department Natural Science Foundation Project YDZJ202101ZYTS150 Carbon Fiber Composite Vibration Assisted Drilling Key Technology

Received: April 7, 2023; Revised: July 18, 2023; Accepted: July 19, 2023; Prepublished online: July 24, 2023; Published: September 5, 2023  Show citation

ACS AIP APA ASA Harvard Chicago IEEE ISO690 MLA NLM Turabian Vancouver
Du Y, Lu Z, Chang E, Li Q, Shi Y. Identification Method of Vibration Drilling Bit Wear State Based on Signal Im-aging and Deep Learning. Manufacturing Technology. 2023;23(4):392-398. doi: 10.21062/mft.2023.055.
Share...
Download citation
  • BibTeX (.bib)
  • Bookends (.ris)
  • EasyBib (.ris)
  • EndNote (.enw)
  • EndNote 8 (.xml)
  • ISI WoS (.isi)
  • Medlars (.medlars)
  • Mendeley (.ris)
  • MODS (.xml)
  • Papers (.ris)
  • RefWorks (.txt)
  • RefManager (.ris)
  • RIS (.ris)
  • MS Word (.xml)
  • Zotero (.ris)
    • Open full article

    References

    1. SHI YAOCHEN, LIU HONGYAN, ZHANG XECHEN, YU XUELIAN & ZHANG LONGFEI. Experimental Study on Fault Diagnosis of Vibratory Drilling Bits Based on Acoustic Emission and Vibration Signals. Machine Tools and Hydraulics (10), (2020), 197-200.
    2. PODANÝ, JAN, AND TOMÍČEK JAN. Analysis of small holes manufacturing for optomechanical components. Manufacturing Technology 20, no. 2 (2020): 229-36. Go to original source...
    3. ZHA, CHANGLI, AND ZHA SHENLONG. Theoretical and Experimental Study on The Influence of Ultrasonic Vibration on Contact Friction. Manufacturing Technology 22, no. 3 (2022): 367-76. Go to original source...
    4. NASIR, NUR SYUHADA, AB WAHAB NORFARIZA, BIN SOFIAN BADRI, IZAMSHAH RAJA, AND SASAHARA HIROYUKI. Experimental Investigations Towards Hole Accuracy in Micro-drilling of Carbon Fibre Reinforced Polymer Material. Manufacturing Technology 21, no. 3 (2021): 381-6. Go to original source...
    5. MA, L.J., YU H., MAO X.H., LI C.R., FENG C.Y., AND LI F.N.. Influence of Cutting Tool and Drill-ing Process on the Machinability of Inconel 718. Manufacturing Technology 23, no. 2 (2023): 204-15 Go to original source...
    6. PI©, DOMINIK, POUZAROVÁ HANA, AND HANU©OVÁ KRISTÝNA. Degradation of 3D Printed Polymer Composites with Filler of Cellulose-Based Materials. Manufacturing Technology 22, no. 3 (2022): 327-33. Go to original source...
    7. WANG. Research on drill bit wear monitoring technology based on GA-LVQ network. Shenyang Aerospace University, (2020).
    8. SOUFIANE LADDADA, MED. OUALI SI-CHAIB, TARAK BENKEDJOUH & REDOUANE DRAI. Tool wear condition monitoring based on wavelet transform and improved extreme learning machine. Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science (5), (2020). doi:10.1177/0954406219888544. Go to original source...
    9. DONG XIN, LI GUOLONG, JIA YACHAO & XU KAI. Multiscale feature extraction from the perspective of graph for hob fault diagnosis using spectral graph wavelet transform combined with improved random forest. Measurement. (2021). doi: 10.1016/J.MEASUREMENT. 2021.109178. Go to original source...
    10. CAI L. G., LI H. B., YANG C. B., LIU C. F. & ZHAO Y. S. Tool wear state monitoring method based on improved VMD and adaptive BSA optimized LS-SVM. Journal of Beijing University of Technology (01), (2021), 10-23.
    11. CHENG, X. & YU, J.-B. A machine vision-based method for machining tool wear monitoring. Journal of Zhejiang University (Engineering Edition) (05), (2021), 896-904.
    12. ZHANG BOWEN. Recognition and prediction of milling cutter wear state based on deep learning. Harbin University of Science and Technology, (2022).
    13. GU YINGKUI, WU KUAN, AND LI CHENG. Fault diagnosis of rolling bearings based on Gram angle field and transfer depth residual neural network. Vibration and shock 41.21 (2022): 228-237.doi: 10.13465 / j.cnki.jvs.2022.21.025.
    14. XU, AND WANG. Image classification method based on improved S-ReLU activation function. Science, Technology and Engineering 22.29 (2022): 12963-12968.
    15. YU, WU-LIN. Research on rolling bearing vibration signal analysis method based on deep learning (Master's thesis, Southwest Jiaotong University), (2021).
    16. TANG KESHUANG, CHEN SIQU, CAO YUMIN & ZHANG FENGXIN. Short-time prediction of urban expressway travel speed based on Inception convolutional neural network. Journal of Tongji University (Natural Science Edition) (03), (2021), 370-381.

    This is an open access article distributed under the terms of the Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0), which permits non-comercial use, distribution, and reproduction in any medium, provided the original publication is properly cited. No use, distribution or reproduction is permitted which does not comply with these terms.


    Return to the content