Advertisement

Journal of Intelligent Manufacturing

, Volume 25, Issue 6, pp 1403–1411 | Cite as

Online incremental learning for tool condition classification using modified Fuzzy ARTMAP network

  • Guofeng Wang
  • Zhiwei Guo
  • Lei Qian
Article

Abstract

Condition monitoring of tool wear is paramount for guaranteeing the quality of workpiece and improving the lifetime of the cutter. To improve the training speed and the flexibility of the incremental learning, a modified Fuzzy ARTMAP classifier is developed in which the resonance layer is linked with the category node directly by many to one mapping. Therefore, the weight value and model structure can be updated simultaneously during the online incremental learning process. To testify the effectiveness of the presented method, experiments of tool condition classification in the process of end milling of Titanium alloy are carried out and two incremental learning cases are simulated. The analysis of online learning process in both cases shows that the structure and parameters of the model can be adjusted automatically without requiring access to the previous training data. At the same time, the accuracy analysis demonstrates that the presented method has strong ability to learn the new knowledge without forgetting the previous knowledge.

Keywords

Incremental learning Tool condition monitoring Online Modified Fuzzy ARTMAP 

List of Symbols

\(a=\{x_{1}, x_{2}, x_{3},{\ldots } x_{M}\}\)

Original feature vectors

\(a^{c}\)

Complement code of \(a\)

\(A\)

Input vectors

\(C\)

Index of chosen class label

\(j\)

Index of ART node

\(J\)

Index of chosen ART node

\(k\)

Index of class label

\(K\)

Number of categories

\(K\!(j)\)

Class prediction function

\(M\)

Length of feature vectors

\(N\)

Number of ART node

\(T_{j}\)

Activity function

\(w_{j}\)

Weight value of ART node \(j\)

\(w_J^{new} \)

New weight value of the committed node

\(w_J^{old} \)

Original weight value of the committed node

\(W_{jk}\)

Binary weight value of mapping layer

\(\alpha \)

Choice parameter

\(\beta \)

Learning rate

\(\rho \)

Vigilance parameter

\({\bar{\rho }}\)

Baseline vigilance parameter

Notes

Acknowledgments

This project is supported by National Natural Science Foundation of China (51175371).

References

  1. Abellan-Nebot, J. V., & Subirón, F. R. (2010). A review of machining monitoring systems based on artificial intelligence process models. The International Journal of Advanced Manufacturing Technology, 47(1–4), 237–257.CrossRefGoogle Scholar
  2. Boutros, T., & Liang, M. (2011). Detection and diagnosis of bearing and cutting tool faults using hidden Markov models. Mechanical System and Signal Processing, 25(6), 2102–2124.CrossRefGoogle Scholar
  3. Brezak, D., Majetic, D., Udiljak, T., & Kasac, J. (2012). Tool wear estimation using an analytic fuzzy classifier and support vector machines. Journal of Intelligent Manufacturing, 23(3), 797–809.CrossRefGoogle Scholar
  4. Burke, L., & Rangwala, S. (1991). Tool condition monitoring in metal cutting: A neural network approach. Journal of Intelligent Manufacturing, 2(5), 269–280.CrossRefGoogle Scholar
  5. Carpenter, G. A., Grossberg, S., Markuzon, N., Reynolds, J. H., & Rosen, D. B. (1992). Fuzzy ARTMAP: An adaptive resonance architecture for incremental learning of analog maps. International Joint Conference on Neural Networks, 3, 309–314.Google Scholar
  6. Connolly, J. F., Granger, E., & Sabourin, R. (2008). Supervised incremental learning with the fuzzy ARTMAP neural network. ANNPR ’08 Proceedings of the 3rd IAPR workshop on artificial neural networks in pattern recognition (pp. 66–77). Berlin. Google Scholar
  7. Dimla, D. E., Jr., Lister, P. M., & Leighton, N. J. (1997). Neural network solutions to the tool condition monitoring problem in metal cutting—a critical review of methods. International Journal of Machine Tools and Manufacture, 37(9), 1219–1241.Google Scholar
  8. Jemielniak, K., Kwiatkowski, L., & Wrzosek, P. (1998). Diagnosis of tool wear based on cutting forces and acoustic emission measures as inputs to a neural network. Journal of Intelligent Manufacturing, 9(5), 447–455.CrossRefGoogle Scholar
  9. Kuo, R. J., & Cohen, P. H. (1999). Multi-sensor integration for on-line toolwear estimation through radialbasisfunction networks and fuzzy neural network. Neural Networks, 12(2), 355–370.CrossRefGoogle Scholar
  10. Marungsri, B., & Boonpoke, S. (2011). Applications of simplified fuzzy ARTMAP to partial discharge classification and pattern recognition. Wseas Transactions on Systems, 10(3), 69–80.Google Scholar
  11. Orhan, S., Er, A. O., Camuscu, N., & Aslan, E. (2007). Tool wear evaluation by vibration analysis during end milling of AISI D3 cold work tool steel with 35 HRC hardness. NDT & E International, 40(2), 121–126.CrossRefGoogle Scholar
  12. Polikar, R., Udpa, L., Udpa, S. S., & Honavar, V. (2001). Learn++: An incremental learning algorithm for supervised neural networks. IEEE Transactions on Systems, Man and Cybernetics-Part C: Applications and Reviews, 31(4), 497–508.CrossRefGoogle Scholar
  13. Purushothaman, S. (2010). Tool wear monitoring using artificial neural network based on extended Kalman filter weight updation with transformed input patterns. Journal of Intelligent Manufacturing, 21(6), 717–730.CrossRefGoogle Scholar
  14. Rehorn, A. G., Jiang, J., & Orban, P. E. (2005). State-of-the-art methods and results in tool condition monitoring: A review. The International Journal of Advanced Manufacturing Technology, 26(7–8), 693–710.CrossRefGoogle Scholar
  15. Silva, R. G. (2010). Condition monitoring of the cutting process using a self-organizing spiking neural network map. Journal of Intelligent Manufacturing, 21(6), 823–829.CrossRefGoogle Scholar
  16. Tian, Z. G. (2012). An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring. Journal of Intelligent Manufacturing, 23(2), 227–237.CrossRefGoogle Scholar
  17. Venkatesh, K., Zhou, M., & Caudill, R. J. (1997). Design of artificial neural networks for tool wear monitoring. Journal of Intelligent Manufacturing, 8(3), 215–226.CrossRefGoogle Scholar
  18. Wang, G. F., & Cui, Y. H. (2012). On line tool wear monitoring based on auto associative neural network. Journal of Intelligent Manufacturing,. doi: 10.1007/s10845-012-0636-7.Google Scholar
  19. Xu, Z., Shi, X. J., Wang, L. Y., Luo, J., Zhong, C. J., & Lu, S. (2009). Pattern recognition for sensor array signals using fuzzy ARTMAP. Sensors and Actuators B-Chemical, 141(2), 458–464.CrossRefGoogle Scholar
  20. Yan, W., Wong, Y. S., Lee, K. S., & Ning, T. (1999). An investigation of indices based on milling force for tool wear in milling. Journal of Materials Processing Technology, 89–90, 245–253.CrossRefGoogle Scholar
  21. Zhu, K. P., Wong, Y. S., & Hong, G. S. (2009). Wavelet analysis of sensor signals for tool condition monitoring: A review and some new results. International Journal of Machine Tools & Manufacture, 49(7–8), 537–553.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2013

Authors and Affiliations

  1. 1.Key Laboratory of Mechanism Theory and Equipment Design of Ministry of EducationTianjin UniversityTianjinChina

Personalised recommendations