Skip to main content
SpringerLink
Log in

Combining adaptive time-series feature window and stacked bidirectional LSTM for predicting tool remaining useful life without failure data

  • ORIGINAL ARTICLE
  • Published:
The International Journal of Advanced Manufacturing Technology Aims and scope Submit manuscript

Abstract

Tool failures have a great effect on workpiece quality and even damage machine tools. The accurate prediction of remaining useful life (RUL) is an effective way to prevent tools from sudden failure. Most existing tool RUL prediction methods require extensively historical health and failure data. However, for new or recently deployed tools, the health and failure data are limited or even unavailable, making RUL prediction a challenge when using existing methods. To deal with this problem, this study proposes a novel tool RUL prediction method without failure data. Firstly, the tool wear factor is derived mathematically to describe the varied trend of the sensitive feature. Then, the time-series feature window is adaptively constructed and compressed to accurately track the tool wear process. Based on this, a stacked bidirectional long short-term memory is developed to model the sequential characteristics of tool conditions. Subsequently, a multi-step ahead prediction method is utilized to predict the value of the sensitive feature and then obtain RUL. Finally, several experiments are carried out, and the mean absolute percentage error of RUL prediction of the proposed method for three tools are 9.87%, 14.36%, and 11.69%, respectively, which verifies the effectiveness and superiority of the proposed method with failure data unavailability.

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

Similar content being viewed by others

Data availability

Not applicable.

Code availability

Not applicable.

References

  1. Zhou Y, Xue W (2018) Review of tool condition monitoring methods in milling processes. Int J Adv Manuf Tech 96(5–8):2509–2523. https://doi.org/10.1007/s00170-018-1768-5

    Article  Google Scholar 

  2. Wang Y, Zheng L, Wang Y (2021) Event-driven tool condition monitoring methodology considering tool life prediction based on industrial internet. J Manuf Syst 58:205–222. https://doi.org/10.1016/j.jmsy.2020.11.019

    Article  Google Scholar 

  3. Li W, Liu T (2019) Time varying and condition adaptive hidden Markov model for tool wear state estimation and remaining useful life prediction in micro-milling. Mech Syst Signal Process 131:689–702. https://doi.org/10.1016/j.ymssp.2019.06.021

    Article  Google Scholar 

  4. Zhou JT, Zhao X, Gao J (2019) Tool remaining useful life prediction method based on LSTM under variable working conditions. Int J Adv Manuf Tech 104(9):4715–4726. https://doi.org/10.1007/s00170-019-04349-y

    Article  Google Scholar 

  5. Mathew P (1989) Use of predicted cutting temperatures in determining tool performance. Int J Mach Tool Manu 29(4):481–497. https://doi.org/10.1016/0890-6955(89)90066-7

    Article  Google Scholar 

  6. Usui E, Hirota A, Masuko M (1978) Analytical prediction of three dimensional cutting process-Part 1: basic cutting model and energy approach. J Eng Industry 100(2):222–322. https://doi.org/10.1115/1.3439413

    Article  Google Scholar 

  7. Takeyama H, Murata R (1963) Basic investigation of tool wear. J Eng Industry 85(1):33–37. https://doi.org/10.1115/1.3667575

    Article  Google Scholar 

  8. Taylor FW (1906) On the art of cutting metals. American Society of Mechanical Engineers

  9. Colding BN (1959) A wear relationship for turning, milling and grinding: machining economics, H Ohlsson

  10. Gilbert W (1950) Machining theory and practice. American Sociaty for Metals, Cleveland, Ohio 465

  11. Wang J, Wang P, Gao RX (2015) Enhanced particle filter for tool wear prediction. J Manuf Syst 36:35–45. https://doi.org/10.1016/j.jmsy.2015.03.005

    Article  Google Scholar 

  12. Si SX, Wang W, Hu CH, Dong HZ (2011) Remaining useful life estimation–a review on the statistical data driven approaches. Eur J Oper Res 213(1):1–14. https://doi.org/10.1016/j.ejor.2010.11.018

    Article  MathSciNet  Google Scholar 

  13. Kumar A, Chinnam RB, Tseng F (2019) An HMM and polynomial regression based approach for remaining useful life and health state estimation of cutting tools. Comput Ind Eng 128:1008–1014. https://doi.org/10.1016/j.cie.2018.05.017

    Article  Google Scholar 

  14. Li W, Liu T (2019) Time varying and condition adaptive hidden Markov model for tool wear state estimation and remaining useful life prediction in micromilling. Mech Syst Signal Process 131:689–702. https://doi.org/10.1016/j.ymssp.2019.06.021

    Article  Google Scholar 

  15. Kong D, Chen Y, Li N (2018) Gaussian process regression for tool wear prediction. Mech Syst Signal Process 104:556–574. https://doi.org/10.1016/j.ymssp.2017.11.021

    Article  Google Scholar 

  16. Wang P, Gao RX (2015) Adaptive resampling-based particle filtering for tool life prediction. J Manuf Syst 37:528–534. https://doi.org/10.1016/j.jmsy.2015.04.006

    Article  Google Scholar 

  17. Sun H, Cao D, Zhao Z, Kang X (2018) A hybrid approach to cutting tool remaining useful life prediction based on the Wiener process. IEEE Trans Reliab 67(3):1294–1303. https://doi.org/10.1109/TR.2018.2831256

    Article  Google Scholar 

  18. Hanachi H, Yu W, Kim IY, Liu J, Mechefske CK (2019) Hybrid data-driven physics-based model fusion framework for tool wear prediction. Int J Adv Manuf Tech 101(9–12):2861–2872. https://doi.org/10.1007/s00170-018-3157-5

    Article  Google Scholar 

  19. Venkata RK, Murthy BSN, Mohan RN (2014) Prediction of cutting tool wear, surface roughness and vibration of work piece in boring of AISI 316 steel with artificial neural network. Measurement 51:63–70. https://doi.org/10.1016/j.measurement.2014.01.024

    Article  Google Scholar 

  20. D’Addona DM, Ullah AMMS, Matarazzo D (2017) Tool-wear prediction and pattern-recognition using artificial neural network and DNA-based computing. J Intell Manuf 28(6):1285–1301. https://doi.org/10.1007/s10845-015-1155-0

    Article  Google Scholar 

  21. Mikołajczyk T, Nowicki K, Bustillo A, Pimenov DY (2018) Predicting tool life in turning operations using neural networks and image processing. Mech Syst Signal Process 104:503–513. https://doi.org/10.1016/j.ymssp.2017.11.022

    Article  Google Scholar 

  22. Yang Y, Guo Y, Huang Z, Chen N, Li L, Jiang Y, He N (2019) Research on the milling tool wear and life prediction by establishing an integrated predictive model. Measurement 145:178–189. https://doi.org/10.1016/j.measurement.2019.05.009

    Article  Google Scholar 

  23. Zhang C, Zhang H (2016) Modelling and prediction of tool wear using LS-SVM in milling operation. Int J Comput Integ Manuf 29(1):76–91. https://doi.org/10.1080/0951192X.2014.1003408

    Article  MathSciNet  Google Scholar 

  24. Marani M, Zeinali M, Songmene V, Mechefske CK (2021) Tool wear prediction in high-speed turning of a steel alloy using long short-term memory modelling. Measurement 177:109329. https://doi.org/10.1016/j.measurement.2021.109329

    Article  Google Scholar 

  25. Zhu Y, Wu J, Wu J, Liu S (2022) Dimensionality reduce-based for remaining useful life prediction of machining tools with multisensor fusion. Reliab Eng Syst Safe 218:108179. https://doi.org/10.1016/j.ress.2021.108179

    Article  Google Scholar 

  26. Wu J, Su Y, Cheng Y, Shao X, Deng C, Liu C (2018) Multi-sensor information fusion for remaining useful life prediction of machining tools by adaptive network based fuzzy inference system. Appl Soft Comput 68:13–23. https://doi.org/10.1016/j.asoc.2018.03.043

    Article  Google Scholar 

  27. Zhang J, Jiang Y, Wu S, Li X, Luo H, Yin S (2022) Prediction of remaining useful life based on bidirectional gated recurrent unit with temporal self-attention mechanism. Reliab Eng Syst Safe 221:108297. https://doi.org/10.1016/j.ress.2021.108297

    Article  Google Scholar 

  28. Lei Y, Li N, Guo L, Li N, Yan T, Lin J (2018) Machinery health prognostics: a systematic review from data acquisition to RUL prediction. Mech Syst Signal Process 104:799–834. https://doi.org/10.1016/j.ymssp.2017.11.016

    Article  Google Scholar 

  29. Hu C, Youn BD, Wang P, Yoon JT (2012) Ensemble of data-driven prognostic algorithms for robust prediction of remaining useful life. Reliab Eng Syst Safe 103:120–135. https://doi.org/10.1016/j.ress.2012.03.008

    Article  Google Scholar 

  30. Nazir R (2017) Taylor series expansion based repetitive controllers for power converters, subject to fractional delays. Control Eng Pract 64:140–147. https://doi.org/10.1016/j.conengprac.2017.03.013

    Article  Google Scholar 

  31. Tian Z, Wong L, Safaei N (2010) A neural network approach for remaining useful life prediction utilizing both failure and suspension histories. Mech Syst Sig Process 24(5):1542–1555. https://doi.org/10.1016/j.ymssp.2009.11.005

    Article  Google Scholar 

  32. Tran VT, Yang BS, Tan A (2009) Multi-step ahead direct prediction for the machine condition prognosis using regression trees and neuro-fuzzy systems. Expert Syst Appl 36(5):9378–9387. https://doi.org/10.1016/j.eswa.2009.01.007

    Article  Google Scholar 

  33. The Prognostics and Health Management Society (2010) 2010 Conference Data Challenge. Electronic Bulletin Board Online. https://www.phmsociety.org/competition/phm/10. Accessed 18 May 2010

  34. Upase R, Ambhore N (2020) Experimental investigation of tool wear using vibration signals: an ANN approach. Materials Today: Proceedings 24:1365–1375

    Google Scholar 

  35. Alonso FJ, Salgado DR (2008) Analysis of the structure of vibration signals for tool wear detection. Mech Syst Signal Process 22(3):735–748. https://doi.org/10.1016/j.ymssp.2007.09.012

    Article  Google Scholar 

  36. He Z, Shi T, Xuan J (2022) Milling tool wear prediction using multi-sensor feature fusion based on stacked sparse autoencoders. Measurement 190:110719. https://doi.org/10.1016/j.measurement.2022.110719

    Article  Google Scholar 

  37. Yang Z, Chen YX, Li YF, Zio E, Kang R (2014) Smart electricity meter reliability prediction based on accelerated degradation testing and modeling. Int J Elec Power Ener Syst 56:209–219. https://doi.org/10.1016/j.ijepes.2013.11.023

    Article  Google Scholar 

Download references

Funding

This work was supported by the Major Project of National Science and Technology (No. 2017ZX04002001).

Author information

Authors and Affiliations

  1. West China Hospital, Sichuan University, Chengdu, 610041, China

    Weili Kong

  2. School of Mechanical and Electrical Engineering, University of Electronic Science and Technology of China, Chengdu, 611731, China

    Hai Li

Authors
  1. Weili Kong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hai Li
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Weili Kong: conceptualization, methodology, software, validation, writing-original manuscript; Hai Li: conceptualization, resources, writing-review & editing, funding acquisition.

Corresponding author

Correspondence to Hai Li.

Ethics declarations

Competing interests

Not applicable.

Additional information

Publisher's Note

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

Highlights

• A novel method for predicting tool remaining useful life (RUL) with failure data unavailability is proposed.

• Tool wear factor is derived mathematically and the adaptive time-series feature window is developed to accurately track tool wear process.

• A multi-step ahead rolling prediction method with a stacked bidirectional LSTM is developed to predict the future trend of tool and then obtain RUL.

• The effectiveness of proposed method is verified by several experiments.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kong, W., Li, H. Combining adaptive time-series feature window and stacked bidirectional LSTM for predicting tool remaining useful life without failure data. Int J Adv Manuf Technol 121, 7509–7526 (2022). https://doi.org/10.1007/s00170-022-09771-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-022-09771-3

Keywords

Search

Navigation