Skip to main content
SpringerLink
Log in

Bayesian-inference-based neural networks for tool wear estimation

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

Abstract

This paper introduces the application of neural networks based on Bayesian inference, the automatic relevance determination algorithm for selecting relevant features and designing neural estimators for tool wear estimation in face-milling processes. Two types of neural networks are studied: Bayesian support vector machines for regression (BSVR) and Bayesian multilayer perceptrons (BMLP). Sixteen well-known features derived from pre-processing of the milling force signal are considered. The force signal samples are collected from 20 milling experiments under various machining conditions. The feature extraction and selection procedure is then applied to the sampled force signal. The feature selection results from the two neural networks are found to be quite similar. The average force has been proven to be the most relevant feature for tool wear estimation in both cases, among a set of six other features in each case, with each set differing by only one feature. The comparison among the generalization capabilities of the entire, selected, and rejected features shows that the selected features are relatively more relevant to tool wear processes in both cases. The comparison between the estimation results from the two neural networks using the corresponding relevant feature set shows that the BSVR method is more accurate in estimating flank wear than BMLP, but at the cost of a higher computing load.

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

Similar content being viewed by others

References

  1. Altintas Y, Yellowley I (1989) In-process detection of tool failure in milling using cutting force models. J Eng Ind 111:149–157

    Article  Google Scholar 

  2. Altintas Y (1988) In-process detection of tool breakages using time series monitoring of cutting forces. Int J Mach Tools Manuf 28(2):157–172

    Article  MathSciNet  Google Scholar 

  3. Tansel IN, McLaughlin C (1993) Detection of tool breakage in milling operations. I. The time series analysis approach. Int J Mach Tools Manuf 33(4):531–544

    Article  Google Scholar 

  4. Yan D, El-Wardany TI, Elbestawi MA (1995) A multi-sensor strategy for tool failure detection in milling. Int J Mach Tools Manuf 35(3):383–398

    Article  Google Scholar 

  5. Tarn JH, Tomizuka M (1989) On-line monitoring of tool and cutting conditions in milling. J Eng Ind 111:206–212

    Google Scholar 

  6. Leem CS, Dornfeld DA, Dreyfus SE (1995) A customized neural network for sensor fusion in on-line monitoring of cutting tool wear. J Eng Ind 117:152–159

    Google Scholar 

  7. Neal RM (1996) Bayesian learning for neural networks. Lecture notes in statistics. Springer, Berlin Heidelberg New York

    Google Scholar 

  8. Altintas Y (1988) In-process detection of tool breakages using time series monitoring of cutting forces. Int J Mach Tools Manuf 28(2):157–172

    Article  MathSciNet  Google Scholar 

  9. Tarng YS (1990) Study of milling cutting force pulsation applied to the detection of tool breakage. Int J Mach Tools Manuf 30(4):651–660

    Article  Google Scholar 

  10. Zhang DY, Han YT, Chen DC (1995) On-line detection of tool breakages using telemetering of cutting forces in milling. Int J Mach Tools Manuf 35(1):19–27

    Article  Google Scholar 

  11. Elbestawi MA, Marks J, Papazafiriou TA (1989) Process monitoring in milling by pattern recognition. Mech Syst Signal Process 3(3):305–315

    Article  Google Scholar 

  12. Tarng YS, Hseih YW, Hwang ST (1994) Sensing tool breakage in face milling with a neural network. Int J Mach Tools Manuf 34(3):341–350

    Article  Google Scholar 

  13. Lin SC, Lin RJ (1996) Tool wear monitoring in face milling using force signals. Wear 198:136–142

    Article  Google Scholar 

  14. Santanu D, Chattopadhyay AB, Murthy ASR (1996) Force parameters for on-line tool wear estimation: a neural network approach. Neural Netw 9(9):1639–1645

    Article  PubMed  Google Scholar 

  15. Mackay DJC (1995) Bayesian methods for neural networks: theory and application. Lecture notes for neural network summer school. Springer, Berlin Heidelberg New York

    Google Scholar 

  16. Buntine WL, Weigend AS (1991) Bayesian back-propagation. Complex Syst 5(6):603–643

    MATH  Google Scholar 

  17. Vapnik VN (1995) The nature of statistical learning theory. Springer, Berlin Heidelberg New York

    MATH  Google Scholar 

  18. Tipping ME (1999) The relevance vector machine. Adv Neural Inf Process Syst 12:652–658

    Google Scholar 

  19. MacKay DJC (1992) A practical Bayesian framework for backpropagation networks. Neural Comput 4(3):448–472

    Google Scholar 

  20. Chu W, Keerthi SS, Ong CJ (2001) A unified loss function in Bayesian framework for support vector regression. In: Proceedings of the 18th International Conference on Machine Learning (ICML 2001), Williamstown, Massachusetts, June/July 2001, pp 51–58

  21. Kim JD, Choi IH (1996) Development of a tool failure detection system using multi-sensors. Int J Mach Tools Manuf 36(8):861–870

    Article  MathSciNet  Google Scholar 

  22. International Organization for Standardization (ISO) (1989) ISO 8688-1, first edition. Tool life testing in milling—part 1: face milling, p 14

  23. Nabney IT (2003) Bayesian Techniques. In: NETLAB: algorithms for pattern recognition. Springer, London, pp 325–364

Download references

Author information

Authors and Affiliations

  1. Department of Mechanical Engineering, National University of Singapore, 119260, Singapore, Singapore

    Jianfei Dong, Yoke San Wong & Geok Soon Hong

  2. Department of Mechanical Engineering, Indian Institute of Technology, Kharagpur, 721302, India

    K. V. R. Subrahmanyam & A. R. Mohanty

Authors
  1. Jianfei Dong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. K. V. R. Subrahmanyam
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yoke San Wong
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Geok Soon Hong
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. A. R. Mohanty
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yoke San Wong.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Dong, J., Subrahmanyam, K.V.R., Wong, Y.S. et al. Bayesian-inference-based neural networks for tool wear estimation. Int J Adv Manuf Technol 30, 797–807 (2006). https://doi.org/10.1007/s00170-005-0124-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00170-005-0124-8

Keywords

Search

Navigation