Skip to main content
SpringerLink
Log in

Detection of tool wear during machining by designing a novel 12-way 2-shot learning model by applying L2-regularization and image augmentation

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

Abstract

Tool wear monitoring is regarded as an incredibly important aspect of improving the surface integrity of machined components in the manufacturing sector. This research study performed operations using twelve different types of drilling and milling tools. The worn tools ranging from grade-1 to grade-5 were categorized based on tool wear severity by measuring the flank wear land width of each tool. Advanced algorithms were designed based on short-time Fourier transform and continuous wavelet transform to convert time-series force signals’ data into spectrogram and scalogram images, respectively, to increase the number of shots with which the model can work based on the methodology of 2-shot learning. An algorithm for image augmentation was developed to increase the number of images to improve the training and overall performance of the model. L2 regularization along with the optimal hyper-parameters were utilized to avoid overfitting and to improve the model’s efficiency. Hyper-parameters were optimized by using the grid-search methodology. The milling and drilling data was collated into 12 classes which resulted in a 12-way learning model. Therefore, it will work for both milling and drilling operations. The model will determine whether the test tool is normal or worn. And if worn, it will determine the severity level of tool wear ranging from grade-1 to grade-5. The final results have shown that the model has worked efficiently during CNC machining and achieved 87.83% accuracy.

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

Availability of data

Complete data based on the force signals in Excel files are available which are already plotted in Figs. 8 and 9 in graphical representation.

Availability of code

The separate flow chart is designed for the explanation of the code given in Fig. 3.

Abbreviations

ML:

Machine learning

ANN:

Artificial Neural network

SVM:

Support vector machine

CNN:

Convolutional NN

RUL:

Remaining useful life

KNN:

K-nearest neighbors algorithm

RUL:

Remaining useful life

AE:

Auto-encoder

MCLSTM:

Multiscale Convolutional LSTM

RNN:

Recurrent NN

RF:

Random forest

NB:

Naïve Bayes

LSTM:

Long short-term memory network

BLSTM:

Bidirectional long short-term memory network

MCLSTM:

Convolutional bidirectional LSTM

XGBOOST:

Extreme gradient boosting

STFT:

Short-time fast Fourier transform

DBN:

Deep belief network

References

  1. Shankar S, Mohanraj T, Rajasekar R (2019) Prediction of cutting tool wear during milling process using artificial intelligence methodology. Int J Comput Integr Manuf 32:174–182. https://doi.org/10.1080/0951192x.2018.1550681

    Article  Google Scholar 

  2. Chen G, Li Y, Liu X (2019) Pose-dependent tool tip dynamics prediction using transfer learning. Int J Mach Tools Manuf 137:30–41. https://doi.org/10.1016/j.ijmachtools.2018.10.003

    Article  Google Scholar 

  3. Kurek J, Wieczorek G, Kruk BSM, Jegorowa A, Osowski S (2017) Transfer learning in recognition of drill wear using convolutional NN. 2017 18th International Conference on Computational Problems of Electrical Engineering (CPEE): IEEE; p 1–4. https://doi.org/10.1109/cpee.2017.8093087

  4. Sun C, Ma M, Zhao Z, Tian S, Yan R, Chen X (2018) Deep transfer learning based on sparse autoencoder for remaining useful life prediction of the tool in manufacturing. IEEE Trans Industr Inf 15:2416–2425. https://doi.org/10.1109/tii.2018.2881543

    Article  Google Scholar 

  5. Kim Y-M, Shin S-J, Cho H-W (2021) Predictive modeling for machining power based on multi-source transfer learning in metal cutting. Int J Precis Eng Manuf-Green Technol 1–19. https://doi.org/10.1007/s40684-021-00327-6

  6. Huang S, Guo Y, Liu D, Zha S, Fang W (2019) A two-stage transfer learning-based deep learning approach for production progress prediction in IoT-enabled manufacturing. IEEE Internet Things J 6:10627–10638. https://doi.org/10.1109/jiot.2019.2940131

    Article  Google Scholar 

  7. Li J, Lu J, Chen C, Ma J, Liao X (2021) Tool wear state prediction based on feature-based transfer learning. Int J Adv Manuf Technol 113:3283–3301. https://doi.org/10.1007/s00170-021-06780-6

    Article  Google Scholar 

  8. Lee J, Kim D, Lee S (1996) Application of NNs to flank wear prediction. Mech Syst Signal Process 10:265–276. https://doi.org/10.1006/mssp.1996.0020

    Article  Google Scholar 

  9. Ghosh N, Ravi Y, Patra A, Mukhopadhyay S, Paul S, Mohanty A et al (2007) Estimation of tool wear during CNC milling using NN-based sensor fusion. Mech Syst Signal Process 21:466–479. https://doi.org/10.1016/j.ymssp.2005.10.010

    Article  Google Scholar 

  10. Kandilli I, Sonmez M, Ertunc HM, Cakir B (2007) Online monitoring of tool wear in drilling and milling by multi-sensor NN fusion. 2007 International Conference on Mechatronics and Automation: IEEE; p. 1388–94. https://doi.org/10.1109/icma.2007.4303752

  11. D’Addona D, Segreto T, Simeone A, Teti R (2011) NN tool wear modelling in the machining of nickel superalloy industrial products. CIRP J Manuf Sci Technol 4:33–37. https://doi.org/10.1016/j.cirpj.2011.07.003

    Article  Google Scholar 

  12. Palanisamy P, Rajendran I, Shanmugasundaram S (2008) Prediction of tool wear using regression and NN models in end-milling operation. Int J Adv Manuf Technol 37:29–41. https://doi.org/10.1007/s00170-007-0948-5

    Article  Google Scholar 

  13. Chen JC, Chen JC (2005) An artificial-neural-networks-based in-process tool wear prediction system in milling operations. Int J Adv Manuf Technol 25:427–434. https://doi.org/10.1007/s00170-003-1848-y

    Article  Google Scholar 

  14. Youneszadeh H, Ardeshir A, Sebt MH (2020) Predicting project success in residential building projects (RBPs) using artificial NNs (NNs). Civil Eng J 6:2203–19. https://doi.org/10.28991/cej-2020-03091612

  15. Hao G, Kunpeng Z (2020) Pyramid LSTM auto-encoder for tool wear monitoring. 2020 IEEE 16th International Conference on Automation Science and Engineering (CASE): IEEE; p 190–5. https://doi.org/10.1109/case48305.2020.9217015

  16. Huang C-G, Yin X, Huang H-Z, Li Y-F (2019) An enhanced deep learning-based fusion prognostic method for RUL prediction. IEEE Trans Reliab 69:1097–1109. https://doi.org/10.1109/tr.2019.2948705

    Article  Google Scholar 

  17. Xu X, Wang J, Ming W, Chen M, An Q (2021) In-process tap tool wear monitoring and prediction using a novel model based on deep learning. Int J Adv Manuf Technol 112:453–466. https://doi.org/10.1007/s00170-020-06354-y

    Article  Google Scholar 

  18. Chen Y, Jin Y, Jiri G (2018) Predicting tool wear with multi-sensor data using deep belief networks. Int J Adv Manuf Technol 99:1917–1926. https://doi.org/10.1007/s00170-018-2571-z

    Article  Google Scholar 

  19. Zhang Z, Lu J, Zhou G, Liao X (2018) Research on tool wear prediction based on LSTM and ARIMA. Proceedings of the 2018 international conference on big data engineering and technology p 73–7. https://doi.org/10.1145/3297730.3297732

  20. Qiao H, Wang T, Wang P (2020) A tool wear monitoring and prediction system based on multiscale deep learning models and fog computing. Int J Adv Manuf Technol 108:2367–2384. https://doi.org/10.1007/s00170-020-05548-8

    Article  Google Scholar 

  21. Karandikar J, McLeay T, Turner S, Schmitz T (2015) Tool wear monitoring using naive Bayes classifiers. Int J Adv Manuf Technol 77:1613–1626. https://doi.org/10.1007/s00170-014-6560-6

    Article  Google Scholar 

  22. Wu D, Jennings C, Terpenny J, Gao RX, Kumara S (2017) A comparative study on machine learning algorithms for smart manufacturing: tool wear prediction using random forests. J Manuf Sci Eng 139. https://doi.org/10.1115/1.4036350

  23. Wang X, Huang Y (2009) Optimized recurrent NN-based tool wear modeling in hard turning. Trans NAMRI/SME 37:213–220

    Google Scholar 

  24. Qian Y, Tian J, Liu L, Zhang Y, Chen Y (2010) A tool wear predictive model based on SVM. 2010 Chinese control and decision conference: IEEE; p 1213–7. https://doi.org/10.1109/ccdc.2010.5498161

  25. Penedo F, Haber RE, Gajate A, del Toro RM (2012) Hybrid incremental modeling based on least squares and fuzzy $ K $-NN for monitoring tool wear in turning processes. IEEE Trans Industr Inf 8:811–818. https://doi.org/10.1109/tii.2012.2205699

  26. Alajmi MS, Almeshal AM (2020) Predicting the tool wear of a drilling process using novel machine learning XGBoost-SDA. Materials 13:4952. https://doi.org/10.3390/ma13214952

    Article  Google Scholar 

  27. Socher R, Ganjoo M, Sridhar H, Bastani O, MNNing CD, Ng AY (2013) Zero-shot learning through cross-modal transfer. arXiv preprint arXiv:13013666

  28. Xu Y, Li Y, Wang Y, Zhong D, Zhang G (2021) Improved few-shot learning method for transformer fault diagnosis based on approximation space and belief functions. Exp Syst Appl 167:114105. https://doi.org/10.1016/j.eswa.2020.114105

    Article  Google Scholar 

  29. Ou X, Yan P, Zhang Y, Tu B, Zhang G, Wu J et al (2019) Moving object detection method via ResNet-18 with encoder-decoder structure in complex scenes. IEEE Access 7:108152–108160. https://doi.org/10.1109/access.2019.2931922

    Article  Google Scholar 

  30. Vinyals O, Blundell C, Lillicrap T, Wierstra D (2016) Matching networks for one-shot learning. Adv Neural Inf Process Syst 29:3630–3638

    Google Scholar 

  31. Han C, Luo M, Zhang D (2020) Optimization of varying-parameter drilling for multi-hole parts using metaheuristic algorithm coupled with self-adaptive penalty method. Appl Soft Comput 95:106489. https://doi.org/10.1016/j.asoc.2020.106489

    Article  Google Scholar 

Download references

Acknowledgements

All authors are extremely thankful to Professor Ming Luo of Northwestern Polytechnical University for his kind contribution regarding novel ideas of experimentation as well as for supervision.

Funding

This research was funded by the Technological University Transfer Fund (TUTF) of the Higher Education Authority (HEA), Ireland.

Author information

Authors and Affiliations

  1. Regulated Software Research Center (RSRC), Dundalk Institute of Technology, Dundalk, A91K584, Co. Louth, Ireland

    Jawad Mahmood, Muhammad Adil Raja & John Loane

  2. School of Mechanical Engineering, Northwestern Polytechnical University, Xi’an, 710072, People’s Republic of China

    Mudassar Rehman

  3. Department of Industrial and Manufacturing Engineering, University of Engineering and Technology Lahore, Lahore, 54890, Pakistan

    Sadaf Zahoor

Authors
  1. Jawad Mahmood
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Muhammad Adil Raja
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mudassar Rehman
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. John Loane
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Sadaf Zahoor
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

J. Mahmood: conceptualization, writing – original draft, investigation, methodology, formal analysis, software, visualization, writing – review and editing. M. Adil Raja: software, project administration, investigation, supervision, software, methodology. M. Rehman: writing – review and editing, methodology, formal analysis. J. Loane: writing – review and editing, methodology, formal analysis. S. Zahoor: writing – review and editing, methodology, formal analysis.

Corresponding author

Correspondence to Muhammad Adil Raja.

Ethics declarations

Ethics approval

The research had been conducted following the rules of ethics.

Consent to participate

All authors are willing to participate in the review of IJAMT articles.

Consent for publication

All authors are willing to publish the manuscript of this research study.

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.

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

Mahmood, J., Raja, M.A., Rehman, M. et al. Detection of tool wear during machining by designing a novel 12-way 2-shot learning model by applying L2-regularization and image augmentation. Int J Adv Manuf Technol 126, 1121–1142 (2023). https://doi.org/10.1007/s00170-023-11040-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-023-11040-w

Keywords

Search

Navigation