Tool wear monitoring in ultrasonic welding using high-order decomposition


Ultrasonic welding has been used for joining lithium-ion battery cells in electric vehicle manufacturing. The geometric profile change of tool shape significantly affects the weld quality and should be monitored during production. In this paper, a high-order decomposition method is suggested for tool wear monitoring. In the proposed monitoring scheme, a low dimensional set of monitoring features is extracted from the high dimensional tool profile measurement data for detecting tool wear at an early stage. Furthermore, the proposed method can be effectively used to analyze the data cross-correlation structure in order to help identify the unusual wear pattern and find the associated assignable cause. The effectiveness of the proposed monitoring method was demonstrated using a simulation and a real-world case study.

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

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 99

This is the net price. Taxes to be calculated in checkout.

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


  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.

  2. de Lathauwer, L., de Moor, B., & Vandewalle, J. (2000). On the best rank-1 and rank-(R1, R2,., Rn) approximation of high order tensors. SIAM Journal of Matrix Analysis and Applications, 21(4), 1324–1342.

  3. He, X., Cai, D., & Niyogi, P. (2005). Tensor subspace analysis, advances in neural information processing systems, 18 (NIPS). Cambridge: MIT Press.

  4. Hotelling, H. (1947). Multivariate quality control. Techniques of Statistical Analysis, 1947, 114–184.

  5. Jolliffe, I. (2005). Principal component analysis. New York: Wiley Online Library.

  6. Kisić, E., Durović, Z., Kovačević, B., & Petrović, V. (2015). Application of \(T^{2}\) control charts and hidden Markov models in condition-based maintenance at thermoelectric power plants. Hindawi corporation, Shock and Vibration, 2015, Article ID 960349.

  7. Kolda, T., & Bader, B. (2009). Tensor decompositions and applications. SIAM Rev, 51(3), 455–500.

  8. Li, X., Dong, S., & Yuan, Z. (1999). Discrete wavelet transform for tool breakage monitoring. International Journal of Machine Tools and Manufacture, 39(12), 1935–1944.

  9. Mason, R. L., Tracy, N. D., & Young, J. C. (1995). Decomposition of T2 for multivariate control chart interpretation. Journal of Quality Technology, 27(2), 109–119.

  10. Paynabar, K., Jin, J. J., & Pacella, M. (2013). Monitoring and diagnosis of multichannel nonlinear profile variations using uncorrelated multilinear principal component analysis. IIE Transactions, 45(11), 1235–1247.

  11. Shao, C., Guo, W., Kim, T. H., Jin, J. J., Hu, S. J., Spicer, J. P., & Abell, J. A. (2014). Characterization and monitoring of tool wear in ultrasonic metal welding. In 9th international workshop on microfactories, Honolulu, Hawaii, October 5–8, (pp. 161–169).

  12. Shao, C., Kim, T. H., Jin, J. J., Hu, S. J., Spicer, J. P., & Abell, J. A. (2016). Tool wear monitoring for ultrasonic metal welding of lithium-ion batteries. ASME Journal of Manufacturing Science and Engineering, 138(5), 051005.

  13. Shao, C., Paynabar, K., Kim, T. H., Jin, J. J., Hu, S. J., Spicer, J. P., et al. (2013). Feature selection for manufacturing process monitoring using cross-validation. Journal of Manufacturing Systems, 32(4), 550–555.

  14. Shi, D., & Gindy, N. N. (2007). Tool wear predictive model based on least squares support vector machines. Mechanical Systems and Signal Processing, 21(4), 1799–1814.

  15. Yan, H., Paynabar, K., & Shi, J. (2015). Image-based process monitoring using low-rank tensor decomposition. IEEE Transactions on Automation Science and Engineering, 99, 1–12.

  16. Zhou, J. H., Pang, C. K., Zhong, Z. W., & Lewis, F. L. (2011). Tool wear monitoring using acoustic emissions by dominant-feature identification. IEEE Transactions on Instrumentation and Measurement, 60(2), 547–559.

Download references

Author information

Correspondence to Yaser Zerehsaz.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zerehsaz, Y., Shao, C. & Jin, J. Tool wear monitoring in ultrasonic welding using high-order decomposition. J Intell Manuf 30, 657–669 (2019).

Download citation


  • Ultrasonic metal welding
  • Tool wear monitoring
  • High-order representation
  • Principal component analysis (PCA)
  • High-order singular value decomposition (HOSVD)