Design & Manufacturing

Korean Society of Die & Mold Engineering (한국금형공학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on Detecting Changes in Injection Molding Process through Similarity Analysis of Mold Vibration Signal Patterns

금형 기반 진동 신호 패턴의 유사도 분석을 통한 사출성형공정 변화 감지에 대한 연구

  • Jong-Sun Kim (Research Institute of Advanced Manufacturing&Materials Technology Shape Manufacturing R&D Department. Korea Institute of Industrial Technology)
  • 김종선 (한국생산기술연구원 금형성형연구부문)
  • Received : 2023.09.08
  • Accepted : 2023.09.30
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, real-time collection of mold vibration signals during injection molding processes was achieved through IoT devices installed on the mold surface. To analyze changes in the collected vibration signals, injection molding was performed under six different process conditions. Analysis of the mold vibration signals according to process conditions revealed distinct trends and patterns. Based on this result, cosine similarity was applied to compare pattern changes in the mold vibration signals. The similarity in time and acceleration vector space between the collected data was analyzed. The results showed that under identical conditions for all six process settings, the cosine similarity remained around 0.92±0.07. However, when different process conditions were applied, the cosine similarity decreased to the range of 0.47±0.07. Based on these results, a cosine similarity threshold of 0.60~0.70 was established. When applied to the analysis of mold vibration signals, it was possible to determine whether the molding process was stable or whether variations had occurred due to changes in process conditions. This establishes the potential use of cosine similarity based on mold vibration signals in future applications for real-time monitoring of molding process changes and anomaly detection.

Keywords

Acknowledgement

본 연구는 중소기업벤처부의 스마트제조혁신기술개발사업(Project No. SE230069)의 지원으로 진행되었습니다.

References

  1. Mok, S. L., Kwong, C. K., Grasser, F., D'Arrigo, A., and Colombi, S., "Application of artificial neural network and fuzzy logic in a case-based system for initial process parameter setting of injection molding", J. Intell. Manuf., Vol. 13, No. 3, pp. 165-176, 2002. https://doi.org/10.1023/A:1015730705078
  2. Moon, Y. D., "Process optimization for the steam injection molding", Design & Manufacturing, Vol. 9, No. 2, pp. 10-15, 2015.
  3. Chen, J. Y., Yang, K. J., and Huang, S. M., "online quality monitoring of molten resin in injection molding", Int. J. Heat Mass Transfer, Vol. 122, pp. 681-693, 2018. https://doi.org/10.1016/j.ijheatmasstransfer.2018.02.019
  4. Lee, S. H., and Lee, H. S., "Rapid cooling of injection mold for high-curvature parts using CO2 cooling module", Design & Manufacturing, Vol. 16, No. 4, pp. 67-74, 2022.
  5. Lee, J. H., and Kim, J. S., "A study on monitoring for process time and process properties by measuring vibration signals transmitted to the mold during injection molding", Design & Manufacturing, Vol. 14, No. 3, pp. 8-16, 2020.
  6. Lee, J. H., and Kim, J. S., "Development and evaluation of edge devices for injection molding monitoring", Design & Manufacturing, Vol. 14, No. 4, pp. 35-39, 2020.
  7. Chris, Y., and Kim, J. S., "A study on the monitoring of cooling time using the change in the magnitude of mold vibration in injection molding", Design & Manufacturing, Vol. 15, No. 3, pp. 45-49, 2021.
  8. Lee, J. H., and Kim, J. S., "A Study on Process Characterization based on Vibration Signals Transmitted to the Mold in the Press Molding Process", Design & Manufacturing, Vol. 17, No. 1, pp. 56-63, 2023.
  9. Xia, P., and Zhang, L., "Learning similarity with cosine similarity ensemble", Inf. Sci., Vol. 307, No. 20, pp. 39-52, 2015. https://doi.org/10.1016/j.ins.2015.02.024
  10. Kalhori, H., Alamadari, M. M., and Ye, L., "Automated algorithm for impact force identification using cosine similarity searching", Meas., Vol. 122, pp. 648-657, 2018. https://doi.org/10.1016/j.measurement.2018.01.016