Hybrid data-driven physics-based model fusion framework for tool wear prediction

  • Houman Hanachi
  • Wennian YuEmail author
  • Il Yong Kim
  • Jie Liu
  • Chris K. Mechefske


An integral part of modern manufacturing process management is to acquire useful information from machining processes to monitor machine and tool condition. Various models have been introduced to detect, classify, and predict tool wear, as a key parameter of the machining process. In more recent developments, sensor-based approaches have been attempted to infer the tool wear condition from real-time processing of the measurement data. Experiments show that the physics-based prediction models can include large uncertainties. Likewise, the measurement-based (or sensor-based) inference techniques are affected by sensor noise and measurement model uncertainties. To manage uncertainties and noise of both methods, a hybrid framework is proposed to fuse together the results of the prediction model and the measurement-based inference data in a stepwise manner. The fusion framework is an extension to the regularized particle filtering technique, used to facilitate updating the state prediction with a numerical inference model, when measurement models alone are not satisfactory. The results show significant improvement in tool wear state estimation, reducing the prediction errors by almost half, compared to the prediction model and sensor-based monitoring method used independently.


Tool wear Sensor-based monitoring Particle filter Fusion framework 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.



This project was financially supported by the Natural Sciences and Engineering Research Council of Canada (Grant number: RGPIN/05922-2014).


  1. 1.
    Kalpakjian S, Schmid S (2006) Manufacturing, engineering and technology, 6th edn. Peason, HobokenGoogle Scholar
  2. 2.
    Yen YC, Söhner J, Lilly B, Altan T (2004) Estimation of tool wear in orthogonal cutting using the finite element analysis. J Mater Process Technol 146:82–91. CrossRefGoogle Scholar
  3. 3.
    Pálmai Z (2013) Proposal for a new theoretical model of the cutting tool’s flank wear. Wear 303:437–445. CrossRefGoogle Scholar
  4. 4.
    Bhattacharyya A, Ham I (1969) Analysis of tool wear—part I: theoretical models of flank wear. J Eng Ind 91:790. CrossRefGoogle Scholar
  5. 5.
    Danai K, Ulsoy AG (1987) A dynamic state model for on-line tool wear estimation in turning. J Eng Ind 109(4):396–399Google Scholar
  6. 6.
    Chen XQ, Li HZ (2009) Development of a tool wear observer model for online tool condition monitoring and control in machining nickel-based alloys. Int J Adv Manuf Technol 45:786–800. CrossRefGoogle Scholar
  7. 7.
    Liu J, Shao Y (2018) An improved analytical model for a lubricated roller bearing including a localized defect with different edge shapes. J Vib Control 24(17):3894–3907.
  8. 8.
    Attanasio A, Ceretti E, Rizzuti S, Umbrello D, Micari F (2008) 3D finite element analysis of tool wear in machining. CIRP Ann - Manuf Technol 57:61–64. CrossRefGoogle Scholar
  9. 9.
    Colbaugh R, Glass K (1995) Real time tool wear estimation using recurrent neural networks. In: Proc of the 1995 IEEE Int Symp on Intelligent Contr, Monterey, USA, pp 357–362Google Scholar
  10. 10.
    Eker Ö, Camci F, Jennions I (2012) Major challenges in prognostics: study on benchmarking prognostic datasets. In: 1st European conference of the prognostics and health management Society pp 1–8Google Scholar
  11. 11.
    Müller E (1962) Der Verschleiss von Hartmetallwerkzeugen und seine kurzzeitige Ermittlung. Eidgenössischen Technischen Hochschule in ZürichGoogle Scholar
  12. 12.
    Zorev NN, Granovskij GI, Loladze TN, Tretyakov IP (1967) Razvitie nauki o rezanii metallov. In: Mashinostroenije. MoskowGoogle Scholar
  13. 13.
    Sipos Z (1986) Investigation of cutting performance of coated HSS tools made in Hungary. NME, MiskocGoogle Scholar
  14. 14.
    Sick B (2002) On-line and indirect tool wear monitoring in turning with artificial neural networks: a review of more than a decade of research. Mech Syst Signal Process 16:487–546. CrossRefGoogle Scholar
  15. 15.
    Benkedjouh T, Medjaher K, Zerhouni N, Rechak S (2015) Health assessment and life prediction of cutting tools based on support vector regression. J Intell Manuf 26:213–223. CrossRefGoogle Scholar
  16. 16.
    Li S, Elbestawi MA (1996) Tool condition monitoring in machining by fuzzy neural networks. J Dyn Syst Meas Control 118:665–672. CrossRefzbMATHGoogle Scholar
  17. 17.
    Kuo RJ (2000) Multi-sensor integration for on-line tool wear estimation through artificial neural networks and fuzzy neural network. Eng Appl Artif Intell 13:249–261. CrossRefGoogle Scholar
  18. 18.
    Gajate A, Haber R, Del TR et al (2012) Tool wear monitoring using neuro-fuzzy techniques: a comparative study in a turning process. J Intell Manuf 23:869–882. CrossRefGoogle Scholar
  19. 19.
    Dutta RK, Paul S, Chattopadhyay AB (2000) Fuzzy controlled backpropagation neural network for tool condition monitoring in face milling. Int J Prod Res 38:2989–3010. CrossRefGoogle Scholar
  20. 20.
    Cao H, Zhang X, Chen X (2017) The concept and progress of intelligent spindles: a review. Int J Mach Tools Manuf 112:21–52. CrossRefGoogle Scholar
  21. 21.
    Zhao R, Yan R, Chen Z et al (2016) Deep learning and its applications to machine health monitoring: a survey. Prepr arXiv 161207640:1–14. Google Scholar
  22. 22.
    Malhotra P, TV V, Ramakrishnan A, et al (2016) Multi-sensor prognostics using an unsupervised health index based on LSTM encoder-decoder. 1st ACM SIGKDD work Mach learn Progn heal Manag san Fransisco, CA, USAGoogle Scholar
  23. 23.
    Simon D (2006) Optimal state estimation: Kalman, H [infinity] and nonlinear approaches. Wiley-InterscienceGoogle Scholar
  24. 24.
    Wang J, Wang P, Gao RX (2013) Tool life prediction for sustainable manufacturing. In: 11th global conference on sustainable manufacturing innovative solutions. Univ.-Verl. der TU, Berlin, pp 230–234Google Scholar
  25. 25.
    Wang J, Wang P, Gao R et al (2015) Enhanced particle filter for tool wear prediction. J Manuf Syst 36:35–45CrossRefGoogle Scholar
  26. 26.
    Wang P, Gao RX (2016) Stochastic tool wear prediction for sustainable manufacturing. Procedia CIRP 48:236–241. CrossRefGoogle Scholar
  27. 27.
    Wang P, Gao RX (2015) Adaptive resampling-based particle filtering for tool life prediction. J Manuf Syst 37:528–534. CrossRefGoogle Scholar
  28. 28.
    Gordon NJ, Salmond DJ, Smith AFM (1989) Novel approach to nonlinear/non-Gaussian Bayesian state estimation. In: IEE Proceedings (Radar and Signal Processing). Institution of Electrical Engineers, pp 107–113Google Scholar
  29. 29.
    Agogino A, Goebel K (2007) Milling Data Set. In: BEST lab, UC Berkeley, NASA Ames Progn. Data Repos.
  30. 30.
    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. CrossRefGoogle Scholar
  31. 31.
    Rad JS, Zhang Y, Chen C (2014) A novel local time-frequency domain feature extraction method for tool condition monitoring using S-transform and genetic algorithm. IFAC Proc 47(3):3516–3521Google Scholar
  32. 32.
    Ghosh N, Ravi YB, Patra A, Mukhopadhyay S, Paul S, Mohanty AR, Chattopadhyay AB (2007) Estimation of tool wear during CNC milling using neural network-based sensor fusion. Mech Syst Signal Process 21:466–479. CrossRefGoogle Scholar
  33. 33.
    Jain V, Raj T (2017) Tool life management of unmanned production system based on surface roughness by ANFIS. Int J Syst Assur Eng Manag 8:458–467. CrossRefGoogle Scholar
  34. 34.
    Whitehouse DJ (1978) BETA functions for surface typologie? CIRP Ann 27:491–497Google Scholar
  35. 35.
    Kannatey-Asibu E, Dornfeld DA (1982) A study of tool wear using statistical analysis of metal-cutting acoustic emission. Wear 76:247–261. CrossRefGoogle Scholar
  36. 36.
    Jang JSR (1993) ANFIS: adaptive-network-based fuzzy inference system. IEEE Trans Syst Man Cybern 23:665–685. CrossRefGoogle Scholar
  37. 37.
    Hanachi H, Liu J (2016) State estimation for general class of dynamical systems: an extension to particle filters. In: the 3rd international conference on control, dynamic systems, and robotics (CDSR’16). Ottawa, pp 1–9Google Scholar
  38. 38.
    Hanachi H, Liu J, Banerjee A, Chen Y (2016) Sequential state estimation of nonlinear/non-Gaussian systems with stochastic input for turbine degradation estimation. Mech Syst Signal Process 72–73:32–45. CrossRefGoogle Scholar
  39. 39.
    Silverman BW (2018) Density estimation for statistics and data analysis. RoutledgeGoogle Scholar
  40. 40.
    Musso C, Oudjane N, Gland F (2001) Improving regularised particle filters. In: Sequential Monte Carlo methods in practice. Springer, New York, pp 247–271Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.Life Prediction Technologies Inc. (LPTi)OttawaCanada
  2. 2.Department of Mechanical and Materials EngineeringQueen’s UniversityKingstonCanada
  3. 3.National Research Base of Intelligent Manufacturing ServiceChongqing Technology and Business UniversityChongqingChina
  4. 4.Department of Mechanical and Aerospace EngineeringCarleton UniversityOttawaCanada

Personalised recommendations