Skip to main content
SpringerLink
Log in

An intelligent milling chatter detection method based on VMD-synchro-squeeze wavelet and transfer learning via deep CNN with vibration signals

  • Original Article
  • Published:
The International Journal of Advanced Manufacturing Technology Aims and scope Submit manuscript

Abstract

Chatter is an undesirable vibration that reduces the surface quality and dimensional accuracy of the workpieces, as well as reduction tool life. In the rapid milling process, this phenomenon can cause a reduction in the surface quality of the workpiece that is difficult to detect and control. It means early identification of chatter is needed to improve the surface quality of the workpiece, but this is still an obstacle for manufacturers. Intelligent real-time chatter monitoring is becoming a major trend in the present manufacturing industry, which is increasingly adopting digital technology and artificial intelligence to improve the quality, speed, efficiency, and safety of production processes. Therefore, this study aimed to develop an intelligent chatter detection model for real-time monitoring based on an optimized variational mode decomposition (VMD) by using a Bayesian optimization algorithm (VMD-BOA), wavelet-based synchro-squeeze transform (WSST), and transfer learning (TL) applications of modified pre-trained deep convolution neural networks (DCNNs). Through the VMD-BOA process, a measured vibration signal is automatically decomposed into appropriate intrinsic mode components (IMFs). To select IMFs with chatter-rich information, the maximum energy ratio is calculated, and the IMFs with chatter-rich information are reconstructed for the next signal-to-image conversion stage. The reconstructed one-dimensional IMF signal is segmented, and then, a wavelet-based synchro-squeeze transform (WSST) is performed to generate vibration signal feature indicators. TL through a modified Squeeze-Net pre-trained network for generating automatic feature extraction and state recognition of machining condition processes is carried out. The results show that a high-performance model was obtained with a maximum classification accuracy of 98.21% and a good recognition time of ±4.2 s for detecting the chatter occurrence. Therefore, this new method could be a solution to the challenge of realizing real-time chatter monitoring for the manufacturing industry, especially in machining.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

Data availability

The authors declare that all data presented in this article are available.

References

  1. Tao F, Xiao B, Qi Q, Cheng J, Ji P (2022) Digital twin modeling. J Manuf Syst 64:372–389. https://doi.org/10.1016/j.jmsy.2022.06.015

    Article  Google Scholar 

  2. Armendia M, Cugnon F, Berglind L, Ozturk E, Gil G, Selmi J (2019) Evaluation of machine tool digital twin for machining operations in industrial environment. Procedia CIRP 82:231–236. https://doi.org/10.1016/j.procir.2019.04.040

    Article  Google Scholar 

  3. Hänel A, Schnellhardt T, Wenkler E, Nestler A, Brosius A, Corinth C et al (2020) The development of a digital twin for machining processes for the application in aerospace industry. Procedia CIRP 93:1399–1404. https://doi.org/10.1016/j.procir.2020.04.017

    Article  Google Scholar 

  4. Wenkler E, Arnold F, Hänel A, Nestler A, Brosius A (2019) Intelligent characteristic value determination for cutting processes based on machine learning. Procedia CIRP 79:9–14. https://doi.org/10.1016/j.procir.2019.02.003

    Article  Google Scholar 

  5. Tong X, Liu Q, Pi S, Xiao Y (2020) Real-time machining data application and service based on IMT digital twin. J Intell Manuf 31:1113–1132. https://doi.org/10.1007/s10845-019-01500-0

    Article  Google Scholar 

  6. Stavropoulos P, Souflas T, Papaioannou C, Bikas H, Mourtzis D (2023) An adaptive, artificial intelligence-based chatter detection method for milling operations. Int J Adv Manuf Technol 124(7-8):2037–2058. https://doi.org/10.1007/s00170-022-09920-8

    Article  Google Scholar 

  7. Quintana G, Ciurana J (2011) Chatter in machining processes: a review. Int J Mach Tools Manuf 51(5):363–376. https://doi.org/10.1016/j.ijmachtools.2011.01.001

    Article  Google Scholar 

  8. Tao F, Meng Z, Nee AYC (2019) Chapter 3 - five-dimension digital twin modeling and its key technologies. In: Tao F, Zhang M, Nee AYC (eds) Five-dimension digital twin modeling and its key technologies. Digital Twin Driven Smart Manufacturing, pp 63–81. https://doi.org/10.1016/B978-0-12-817630-6.00003-5

    Chapter  Google Scholar 

  9. Smith S, Tlusty J (1993) Efficient simulation programs for chatter in milling. CIRP Ann 42(1):463–466. https://doi.org/10.1016/S0007-8506(07)62486-X

    Article  Google Scholar 

  10. Altintaş Y, Budak E (1995) Analytical prediction of stability lobes in milling. CIRP Ann 44(1):357–362. https://doi.org/10.1016/S0007-8506(07)62342-7

    Article  Google Scholar 

  11. Insperger T, Stépán G (2002) Semi-discretization method for delayed systems. Int J Numer Methods Eng 55(5):503–518. https://doi.org/10.1002/nme.505

    Article  MathSciNet  MATH  Google Scholar 

  12. Ding Y, Zhu L, Zhang X, Ding H (2010) A full-discretization method for prediction of milling stability. Int J Mach Tools Manuf 50(5):502–509. https://doi.org/10.1016/j.ijmachtools.2010.01.003

    Article  Google Scholar 

  13. Abele E, Fiedler U (2004) Creating stability lobe diagrams during milling. CIRP Ann 53(1):309–312. https://doi.org/10.1016/S0007-8506(07)60704-5

    Article  Google Scholar 

  14. Elbestawi MA, Papazafiriou TA, Du RX (1991) In-process monitoring of tool wear in milling using cutting force signature. Int J Mach Tools Manuf 31(1):55–73. https://doi.org/10.1016/0890-6955(91)90051-4

    Article  Google Scholar 

  15. Zhang P, Gao D, Lu Y, Kong L, Ma Z (2022) Online chatter detection in milling process based on fast iterative VMD and energy ratio difference. Measurement 194:111060. https://doi.org/10.1016/j.measurement.2022.111060

    Article  Google Scholar 

  16. Berger BS, Minis I, Harley J, Rokni M, Papadopoulos M (1998) Wavelet based cutting state identification. J Sound Vib 213(5):813–827. https://doi.org/10.1006/jsvi.1997.1495

    Article  Google Scholar 

  17. Tangjitsitcharoen S, Saksri T, Ratanakuakangwan S (2015) Advance in chatter detection in ball end milling process by utilizing wavelet transform. J Intell Manuf 26:485–499. https://doi.org/10.1007/s10845-013-0805-3

    Article  Google Scholar 

  18. Wu HT, Flandrin P, Daubechies I (2011) One or two frequencies? The synchrosqueezing answers. Adv Adapt Data Analysis 3(01n02):29–39. https://doi.org/10.1142/S179353691100074X

    Article  MathSciNet  MATH  Google Scholar 

  19. Gaurav T, Eugene B, Neven SF, Wu HT (2013) The synchrosqueezing algorithm for time-varying spectral analysis. Signal Process 93(5):1079–1094. https://doi.org/10.1016/j.sigpro.2012.11.029

    Article  Google Scholar 

  20. Herrera RH, Han J, van der Baan M (2014) Applications of the synchrosqueezing transform in seismic time-frequency analysis. Geophysics 79(3):V55–V64

    Article  Google Scholar 

  21. Auger F, Flandrin P (1995) Improving the readability of time-frequency and time-scale representations by the reassignment method. IEEE Trans Signal Process 43(5):1068–1089. https://doi.org/10.1109/78.382394

    Article  Google Scholar 

  22. Auger F, Flandrin P, Lin YT, McLaughlin S, Meignen S, Oberlin T, Wu HT (2013) Time-frequency reassignment and synchrosqueezing: an overview. IEEE Signal Process Mag 30(6):32–41. https://doi.org/10.1109/MSP.2013.2265316

    Article  Google Scholar 

  23. Daubechies I, Lu J, Wu HT (2011) Synchro-squeezed wavelet transforms: an empirical mode decomposition-like tool. Appl Comput Harmon Anal 30(2):243–261. https://doi.org/10.1016/j.acha.2010.08.002

    Article  MathSciNet  MATH  Google Scholar 

  24. Huang ZL, Zhang J, Zhao TH, Sun Y (2015) Synchrosqueezing S-transform and its application in seismic spectral decomposition. IEEE Trans Geosci Remote Sens 54(2):817–825. https://doi.org/10.1109/TGRS.2015.2466660

    Article  Google Scholar 

  25. Yang H (2015) Synchrosqueezed wave packet transforms and diffeomorphism based spectral analysis for 1D general mode decompositions. Appl Comput Harmon Anal 39(1):33–66

    Article  MathSciNet  MATH  Google Scholar 

  26. Khan S, Yairi T (2018) A review on the application of deep learning in system health management. Mech Syst Signal Process 107:241–265. https://doi.org/10.1016/j.ymssp.2017.11.024

    Article  Google Scholar 

  27. Zhang WJ, Yang G, Lin Y, Ji C, Gupta MM (2018) On definition of deep learning. In: In 2018 World automation congress (WAC). IEEE, pp 1–5. https://doi.org/10.23919/WAC.2018.8430387

    Chapter  Google Scholar 

  28. Tran MQ, Liu MK, Tran QV (2020) Milling chatter detection using scalogram and deep convolutional neural network. Int J Adv Manuf Technol 107:1505–1516. https://doi.org/10.1007/s00170-019-04807-7

    Article  Google Scholar 

  29. Sener B, Gudelek MU, Ozbayoglu AM, Unver HO (2021) A novel chatter detection method for milling using deep convolution neural networks. Measurement 182:109689. https://doi.org/10.1016/j.measurement.2021.109689

    Article  Google Scholar 

  30. Unver HO, Sener B (2021) A novel transfer learning framework for chatter detection using convolutional neural networks. J Intell Manuf 1-20. https://doi.org/10.1007/s10845-021-01839-3

  31. Dragomiretskiy K, Zosso D (2013) Variational mode decomposition. IEEE Trans Signal Process 62(3):531–544. https://doi.org/10.1109/TSP.2013.2288675

    Article  MathSciNet  MATH  Google Scholar 

  32. Chen X, Yang Y, Cui Z, Shen J (2019) Vibration fault diagnosis of wind turbines based on variational mode decomposition and energy entropy. Energy 174:1100–1109. https://doi.org/10.1016/j.energy.2019.03.057

    Article  Google Scholar 

  33. Sharma V, Parey A (2020) Extraction of weak fault transients using variational mode decomposition for fault diagnosis of gearbox under varying speed. Eng Fail Anal 107:104204. https://doi.org/10.1016/j.engfailanal.2019.104204

    Article  Google Scholar 

  34. Jiang F, Zhu Z, Li W (2018) An improved VMD with empirical mode decomposition and its application in incipient fault detection of rolling bearing. IEEE Access 6:44483–44493. https://doi.org/10.1109/ACCESS.2018.2851374

    Article  Google Scholar 

  35. Ali JB, Saidi L, Harrath S, Bechhoefer E, Benbouzid M (2018) Online automatic diagnosis of wind turbine bearings progressive degradations under real experimental conditions based on unsupervised machine learning. Appl Acoust 132:167–181. https://doi.org/10.1016/j.apacoust.2017.11.021

    Article  Google Scholar 

  36. Li Y, Cheng G, Liu C, Chen X (2018) Study on planetary gear fault diagnosis based on variational mode decomposition and deep neural networks. Measurement 130:94–104. https://doi.org/10.1016/j.measurement.2018.08.002

    Article  Google Scholar 

  37. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K (2016) SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size. arXiv preprint arXiv 1602:07360. https://doi.org/10.48550/arXiv.1602.07360

    Article  Google Scholar 

  38. Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22(10):1345–1359. https://doi.org/10.1109/TKDE.2009.191

    Article  Google Scholar 

  39. Zhuang F, Qi Z, Duan K, Xi D, Zhu Y, Zhu H et al (2020) A comprehensive survey on transfer learning. Proc IEEE 109(1):43–76. https://doi.org/10.1109/JPROC.2020.3004555

    Article  Google Scholar 

  40. Weiss K, Khoshgoftaar TM, Wang D (2016) A survey of transfer learning. J Big Data 3(1):1–40. https://doi.org/10.1186/s40537-016-0043-6

    Article  Google Scholar 

  41. Susanto A, Liu CH, Yamada K, Hwang YR, Tanaka R, Sekiya K (2018) Application of Hilbert–Huang transform for vibration signal analysis in end-milling. Precis Eng 53:263–277. https://doi.org/10.1016/j.precisioneng.2018.04.008

    Article  Google Scholar 

  42. Wang M, Fei R (1999) Chatter suppression based on nonlinear vibration characteristic of electrorheological fluids. Int J Mach Tools Manuf 39(12):1925–1934. https://doi.org/10.1016/S0890-6955(99)00039-5

    Article  Google Scholar 

  43. Liu C, Zhu L, Ni C (2018) Chatter detection in milling process based on VMD and energy entropy. Mech Syst Signal Process 105:169–182. https://doi.org/10.1016/j.ymssp.2017.11.046

    Article  Google Scholar 

  44. Yesilli MC, Khasawneh FA, Otto A (2020) On transfer learning for chatter detection in turning using wavelet packet transform and ensemble empirical mode decomposition. CIRP J Manuf Sci Technol 28:118–135. https://doi.org/10.1016/j.cirpj.2019.11.003/

    Article  Google Scholar 

  45. Postel M, Bugdayci B, Wegener K (2020) Ensemble transfer learning for refining stability predictions in milling using experimental stability states. Int J Adv Manuf Technol 107:4123–4139. https://doi.org/10.1007/s00170-020-05322-w

    Article  Google Scholar 

Download references

Acknowledgements

This paper was funded by research grant RIIM No. 82/II.7/HK/2022 from BRIN, Republic of Indonesia, which the authors gratefully acknowledge.

Code availability

The authors state that no codes are provided in this publication.

Author information

Authors and Affiliations

  1. Mechanical Engineering Department, University of Diponegoro, Tembalang, Semarang, 50275, Indonesia

    Khairul Jauhari, Achmad Zaki Rahman, Achmad Widodo & Toni Prahasto

  2. National Research and Innovation Agency (BRIN), Puspiptek, South Tangerang, 15314, Indonesia

    Khairul Jauhari, Achmad Zaki Rahman & Mahfudz Al Huda

Authors
  1. Khairul Jauhari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Achmad Zaki Rahman
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mahfudz Al Huda
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Achmad Widodo
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Toni Prahasto
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Khairul Jauhari contributed by proposing ideas and all methods, conducting experimental verification, and writing the manuscript. Achmad Zaki Rahman contributed to data collection and writing the manuscript. Mahfudz Al Huda, Achmad Widodo, and Toni Prahasto supervise methods, manuscript checking, and project administration.

Corresponding author

Correspondence to Khairul Jauhari.

Ethics declarations

Ethics approval

Ethics approval is not required.

Consent to participate

Consent to participate is not required.

Consent for publication

The authors approved to publish this article.

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Highlights

1.Proposed a novel method for enabling an intelligent chatter detection model for real-time monitoring.

2.Continuous wavelet transform (CWT) and an expansion technique of CWT such as synchro-squeezing based on wavelet transform (WSST) pre-processing methods are used and compared to realize signal-to-image conversion for increasing accuracy.

3.To obtain appropriate intrinsic mode components (IMFs) of signal decomposition, we proposed a new method that embeds the VMD algorithm in a Bayesian optimization algorithm in order to fine-tune the optimum hyper-parameter. Finally, an optimized VMD algorithm is obtained for the next decomposition process.

4.To increase more accuracy in the learning process, we combine the optimized VMD method with continuous wavelet transform (CWT) and synchro-squeeze based on wavelet transform (WSST) for images fed into the modified pre-trained deep convolutional neural networks (DCNNs)-transfer learning.

5.The comparisons of modified pre-trained network learning methods such as Squeeze-Net with optimized VMD-WSST, optimized VMD-CWT, and without optimized VMD are carried out to strengthen the proposed method.

6.Chatter detection performances are improved by WSST-VMD-transfer learning with an average classification accuracy of 95.83% and a nice recognition time of ±4.2 s, especially in milling machining-sample cases.

Appendix

Appendix

In this appendix, Table 11 shows the detailed structural parameters of the modified Squeeze-Net.

Table 11 Structural parameters of modified Squeeze-Net
Full size table

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Jauhari, K., Rahman, A.Z., Al Huda, M. et al. An intelligent milling chatter detection method based on VMD-synchro-squeeze wavelet and transfer learning via deep CNN with vibration signals. Int J Adv Manuf Technol 129, 629–657 (2023). https://doi.org/10.1007/s00170-023-12249-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-023-12249-5

Keywords

Search

Navigation