한국기계가공학회지 (Journal of the Korean Society of Manufacturing Process Engineers)

  • 제21권6호
  • /
  • Pages.89-97
  • /
  • 2022
  • /
  • 1598-6721(pISSN)
  • /
  • 2288-0771(eISSN)
한국기계가공학회 (The Korean Society of Manufacturing Process Engineers)
권호 표지
DOI QR코드

DOI QR Code

초음파 금속용접 시 다층 퍼셉트론 뉴럴 네트워크를 이용한 용접품질의 In-process 모니터링

In-process Weld Quality Monitoring by the Multi-layer Perceptron Neural Network in Ultrasonic Metal Welding

  • ;
  • 박동삼 (인천대학교 기계공학과)
  • 투고 : 2022.04.25
  • 심사 : 2022.05.19
  • 발행 : 2022.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Ultrasonic metal welding has been widely used for joining lithium-ion battery tabs. Weld quality monitoring has been an important issue in lithium-ion battery manufacturing. This study focuses on the weld quality monitoring in ultrasonic metal welding with the longitudinal-torsional vibration mode horn developed newly. As the quality of ultrasonic welding depends on welding parameters like pressure, time, and amplitude, the suitable values of these parameters were selected for experimentation. The welds were tested via tensile testing machine and weld strengths were investigated. The dataset collected for performance test was used to train the multi-layer perceptron neural network. The three layer neural network was used for the study and the optimum number of neurons in the first and second hidden layers were selected based on performances of each models. The best models were selected for the horn and then tested to see their performances on an unseen dataset. The neural network models for the longitudinal-torsional mode horn attained test accuracy of 90%. This result implies that proposed models has potential for the weld quality monitoring.

키워드

과제정보

This work was supported by Incheon National University Research Grant in 2020.

참고문헌

  1. Shahid, M. B., Han. S.-C., Jun, T. S., Park, D. S., "Effect of process parameters on the joint strength in ultrasonic welding of Cu and Ni foils," Materials Manufacturing Processes, Vol. 34, pp. 1217-1224, 2019. https://doi.org/10.1080/10426914.2019.1643474
  2. Shahid, M. B., Jung, J. Y., Park, D. S., "Finite element analysis coupled artificial neural network approach to design the longitudinal-torsional mode ultrasonic welding horn," International Journal of Advanced Manufacturing Technology, Vol. 107, pp. 2731-2743, 2020. https://doi.org/10.1007/s00170-020-05200-5
  3. Lin, S., "Sandwiched piezoelectric ultrasonic transducers of longitudinal-torsional compound vibrational modes," IEEE Transaction on Ultrasonics, Ferroelectrics, and Frequency Control, Vol. 44, No. 6, pp. 1189-1197, 1997. https://doi.org/10.1109/58.656619
  4. Tsujino, J., Ueoka, T., Hasegawa, K., et al., "New Methods of Ultrasonic Welding of Metal and Plastic Materials," Ultrasonics, Vol. 34, pp. 177-185, 1996. https://doi.org/10.1016/0041-624X(96)81780-X
  5. Tsujino, J., "Recent Developments of Ultrasonic Welding," Proc. of 1995 IEEE Ultrasonics Symposium, pp. 1051-1060, 1995.
  6. Lee, S. S., Kim, T. H., Hu, S. J., Cai, W. W., Abell, J. A., Li, J., "Characterization of Joint Quality in Ultrasonic Welding of Battery Tabs," Journal of Manufacturing Science and Engineering, Vol. 135, No. 2, pp. 021004, 2013. https://doi.org/10.1115/1.4023364
  7. Chang, U. I., Frisch, J., "On optimization of some parameters in ultrasonic metal welding," Welding Journal, Vol. 1, pp. 24-35, 1974.
  8. Wan, X., Wang, Y., Zhao, D., Huang, Y., Yin, Z., "Weld quality monitoring research in small scale resistance spot welding by dynamic resistance and neural network," Measurement, Vol. 99, pp. 120-127, 2017. https://doi.org/10.1016/j.measurement.2016.12.010
  9. Lei, Z., Shen, J., Wang, Q., Chen, Y.,"Real-time weld geometry prediction based on multi- information using neural network optimized by PCA and GA during thin-plate laser welding," Journal of Manufacturing Processes, Vol. 43, pp. 207-217, 2019. https://doi.org/10.1016/j.jmapro.2019.05.013
  10. Nwankpa, C. E., Ijomah, W. I., Gachagan, A., Marshall, S., "Activation Functions: Comparison of Trends in Practice and Research for Deep Learning," 2nd International Conf. on INCCST, Jamshoro, Pakistan, 2020.
  11. Han, J., Moraga, C., "The influence of the sigmoid function parameters on the speed of backpropagation learning," Lecture Notes in Computer Science, Springer, pp. 195-201, 1995.
  12. Neal, R. M., "Connectionist learning of belief networks," Artificial Intelligence, Vol. 56, pp. 71-113, 1992. https://doi.org/10.1016/0004-3702(92)90065-6
  13. LeCun, Y., Bengio, Y., Hinton, G., "Deep learning," Nature, Vol. 521, pp. 436-444, 2015. https://doi.org/10.1038/nature14539
  14. Karlik, B., Olgac, A. V., "Performance Analysis of Various Activation Functions in Generalized MLP Architectures of Neural Networks," International Journal of Artificial Intelligence And Expert Systems(IJAE), Vol. 1, Issue 4, pp. 111-122, 2011.
  15. Nair, V., Hinton, G. E., "Rectified Linear Units Improve Restricted Boltzmann Machines," Proc. of the 27th International Conference on Machine Learning, Israel, pp. 807-814, 2010.
  16. Pedregosa, F., Varoquaux, G., Gramfort, A., et al., "Scikit-learn: Machine Learning in Python," Journal of Machine Learning Research, Vol. 12, pp. 2825-2830, 2011.