A smart tool wear prediction model in drilling of woven composites


Undetected tool wear during drilling of woven composites can cause laminate damage and fiber pull-out and fuzzing, causing subsurface damage. This diminishes the life of the produced part under fatigue loads. Thus, the producing of proper and reliable holes in woven composites requires accurate monitoring of the cutting tool wear level to safeguard the machined parts and increase process productivity and profitability. Available tool condition monitoring (TCM) systems mainly require long development lead time and extensive experimental efforts to predict the tool wear within predefined values of cutting conditions. The changes in these values require system relearning. Therefore, developing of a smart generalized TCM system that can accurately predict tool wear based on unlearned data during drilling of woven composite plates is crucial. In this work, an attempt was presented and discussed to predict the tool wear in drilling of woven composite plates at different and wide range of cutting conditions based on the drilling forces using biased learning data. A generalized heuristic model was proposed to accurately predict tool wear value. The performance of the proposed model was benchmarked with respect to four machine learning techniques namely regression tree, support vector machine (SVM), Gaussian process regression (GPR), and artificial neural network (ANN). Extensive experimental validation tests have showed that the GPR model has offered the lowest prediction error based on a reduced biased learning dataset, which represents 50% reduction in learning efforts compared with available literature. However, the developed heuristic model showed a comparable accuracy using significantly less learning efforts.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11



Flank tool wear


Carbon fiber–reinforced polymer


Glass fiber–reinforced polymer


Adaptive network–fuzzy systems


Support vector machine


Gaussian process regression


Artificial neural network


Thrust force


Cutting force

ΔFzi :

The change in the thrust force at fresh tool (i = 0) and after number of cuts i

ΔFci :

The change in the cutting force at fresh tool (i = 0) and after number of cuts i

a and b:

Trained constants

a’ and b’:

Predicted constants


Weighted mean squared error


Multilayer perceptron


Root mean square error

R 2 :

R squared


Mean absolute error


  1. 1.

    Vigneshwaran S, Uthayakumar M, Arumugaprabu V (2018) Review on machinability of fiber reinforced polymers: a drilling approach. Silicon 10(5):2295–2305

    Article  Google Scholar 

  2. 2.

    Krishnaraj V, Zitoune R, Davim JP (2013) Drilling of polymer-matrix composites. Springer

  3. 3.

    Davim JP Machining composites materials. Wiley

  4. 4.

    Sheikh-Ahmad (2009) Machining of polymer composites, vol 387355391. Springer

  5. 5.

    Abrao AM et al (2007) Drilling of fiber reinforced plastics: a review. J Mater Process Technol 186(1-3):1–7

    Article  Google Scholar 

  6. 6.

    Sadek A, Shi B, Meshreki M, Duquesne J, Attia MH (2015) Prediction and control of drilling-induced damage in fibre-reinforced polymers using a new hybrid force and temperature modelling approach. CIRP Ann 64(1):89–92

    Article  Google Scholar 

  7. 7.

    Hintze W, Clausen R, Schütte C, Kroll K (2018) Evaluation of the total cutting force in drilling of CFRP: a novel experimental method for the analysis of the cutting mechanism. Prod Eng 12(3-4):431–440

    Article  Google Scholar 

  8. 8.

    Davim JP, Reis P (2003) Drilling carbon fiber reinforced plastics manufactured by autoclave—experimental and statistical study. Mater Des 24(5):315–324

    Article  Google Scholar 

  9. 9.

    Geier N, Szalay T (2017) Optimisation of process parameters for the orbital and conventional drilling of uni-directional carbon fibre-reinforced polymers (UD-CFRP). Measurement. 110:319–334

    Article  Google Scholar 

  10. 10.

    Xu J, An Q, Cai X, Chen M (2013) Drilling machinability evaluation on new developed high-strength T800S/250F CFRP laminates. Int J Precis Eng Manuf 14(10):1687–1696

    Google Scholar 

  11. 11.

    Anand RS, Patra K, Steiner M (2014) Size effects in micro drilling of carbon fiber reinforced plastic composite. Prod Eng 8(3):301–307

    Google Scholar 

  12. 12.

    Tsao C (2008) Prediction of thrust force of step drill in drilling composite material by Taguchi method and radial basis function network. Int J Adv Manuf Technol 36(1-2):11–18

    Google Scholar 

  13. 13.

    Xu J, An Q, Chen M (2014) A comparative evaluation of polycrystalline diamond drills in drilling high-strength T800S/250F CFRP. Compos Struct 117:71–82

    Google Scholar 

  14. 14.

    Merino-Pérez JL, Royer R, Merson E, Lockwood A, Ayvar-Soberanis S, Marshall MB (2016) Influence of workpiece constituents and cutting speed on the cutting forces developed in the conventional drilling of CFRP composites. Compos Struct 140:621–629

    Google Scholar 

  15. 15.

    Bhuiyan M, Choudhury I (2014) 13.22—Review of sensor applications in tool condition monitoring in machining. Comprehen Mater Process 13:539–569

    Article  Google Scholar 

  16. 16.

    Brophy B, Kelly K, Byrne G (2002) AI-based condition monitoring of the drilling process. J Mater Process Technol 124(3):305–310

    Article  Google Scholar 

  17. 17.

    Azmi A (2015) Monitoring of tool wear using measured machining forces and neuro-fuzzy modelling approaches during machining of GFRP composites. Adv Eng Softw 82:53–64

    Article  Google Scholar 

  18. 18.

    Slamani M, Chatelain JF, Hamedanianpour H (2015) Comparison of two models for predicting tool wear and cutting force components during high speed trimming of CFRP. Int J Mater Form 8(2):305–316

    Article  Google Scholar 

  19. 19.

    Patra K, Jha AK, Szalay T, Ranjan J, Monostori L (2017) Artificial neural network based tool condition monitoring in micro mechanical peck drilling using thrust force signals. Precis Eng 48:279–291

    Article  Google Scholar 

  20. 20.

    Caggiano A, Rimpault X, Teti R, Balazinski M, Chatelain JF, Nele L (2018) Machine learning approach based on fractal analysis for optimal tool life exploitation in CFRP composite drilling for aeronautical assembly. CIRP Ann 67(1):483–486

    Google Scholar 

  21. 21.

    Hassan M, Damir A, Attia H, Thomson V (2018) Benchmarking of pattern recognition techniques for online tool wear detection. Procedia CIRP 72:1451–1456

    Google Scholar 

  22. 22.

    Loh WY, Shih YS (1997) Split selection methods for classification trees. Stat Sin:815–840

  23. 23.

    Qu J, Zuo MJ (2010) Support vector machine based data processing algorithm for wear degree classification of slurry pump systems. Measurement 43(6):781–791

    Google Scholar 

  24. 24.

    Rasmussen CE (2003) Gaussian processes in machine learning. In: Summer School on Machine Learning. Springer

  25. 25.

    Işık B, Ekici E (2010) Experimental investigations of damage analysis in drilling of woven glass fiber-reinforced plastic composites. Int J Adv Manuf Technol 49(9-12):861–869

    Google Scholar 

  26. 26.

    Xu J, Li C, Chen, El Mansori M, Ren F (2019) An investigation of drilling high-strength CFRP composites using specialized drills. Int J Adv Manuf Technol 103(9-12):3425–3442

    Article  Google Scholar 

Download references

Author information



Corresponding author

Correspondence to H. Hegab.

Additional information

Publisher’s note

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



Table 3 Tool wear prediction results (training and validation stages) using fine tree, ANN, GPR, SVM, HA and measured data

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Hegab, H., Hassan, M., Rawat, S. et al. A smart tool wear prediction model in drilling of woven composites. Int J Adv Manuf Technol (2020). https://doi.org/10.1007/s00170-020-06049-4

Download citation


  • Woven composites
  • Tool wear
  • Drilling
  • Modeling
  • Machine learning