품질경영학회지 (Journal of Korean Society for Quality Management)

  • 제52권1호
  • /
  • Pages.43-56
  • /
  • 2024
  • /
  • 1229-1889(pISSN)
  • /
  • 2287-9005(eISSN)
한국품질경영학회 (Korean Society for Quality Management)
권호 표지
DOI QR코드

DOI QR Code

사출 성형 공정에서의 변수 최적화 방법론

Methodology for Variable Optimization in Injection Molding Process

  • 정영진 (인하대학교 산업경영공학과) ;
  • 강태호 (인하대학교 산업경영공학과) ;
  • 박정인 (인하대학교 산업경영공학과) ;
  • 조중연 (인하대학교 산업경영공학과) ;
  • 홍지수 (인하대학교 산업경영공학과) ;
  • 강성우 (인하대학교 산업경영공학과)
  • Jung, Young Jin (Department of Industrial Engineering, Inha University) ;
  • Kang, Tae Ho (Department of Industrial Engineering, Inha University) ;
  • Park, Jeong In (Department of Industrial Engineering, Inha University) ;
  • Cho, Joong Yeon (Department of Industrial Engineering, Inha University) ;
  • Hong, Ji Soo (Department of Industrial Engineering, Inha University) ;
  • Kang, Sung Woo (Department of Industrial Engineering, Inha University)
  • 투고 : 2024.01.22
  • 심사 : 2024.02.14
  • 발행 : 2024.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Purpose: The injection molding process, crucial for plastic shaping, encounters difficulties in sustaining product quality when replacing injection machines. Variations in machine types and outputs between different production lines or factories increase the risk of quality deterioration. In response, the study aims to develop a system that optimally adjusts conditions during the replacement of injection machines linked to molds. Methods: Utilizing a dataset of 12 injection process variables and 52 corresponding sensor variables, a predictive model is crafted using Decision Tree, Random Forest, and XGBoost. Model evaluation is conducted using an 80% training data and a 20% test data split. The dependent variable, classified into five characteristics based on temperature and pressure, guides the prediction model. Bayesian optimization, integrated into the selected model, determines optimal values for process variables during the replacement of injection machines. The iterative convergence of sensor prediction values to the optimum range is visually confirmed, aligning them with the target range. Experimental results validate the proposed approach. Results: Post-experiment analysis indicates the superiority of the XGBoost model across all five characteristics, achieving a combined high performance of 0.81 and a Mean Absolute Error (MAE) of 0.77. The study introduces a method for optimizing initial conditions in the injection process during machine replacement, utilizing Bayesian optimization. This streamlined approach reduces both time and costs, thereby enhancing process efficiency. Conclusion: This research contributes practical insights to the optimization literature, offering valuable guidance for industries seeking streamlined and cost-effective methods for machine replacement in injection molding.

키워드

과제정보

본 논문은 인하대학교의 지원에 의해 연구되었습니다.

참고문헌

  1. Bae, J., Lee, W., Jee, H., Hong, B., and Lee, J. 2021. Simulation for Injection Molding of Insulation Spacers for Gas-Insulated Switches Using Thermosetting Epoxy Resin. Journal of the Korean Institute of Electrical and Electronic Material Engineers 34(6):426-432.
  2. Breiman, L. 2001. RandomForests. Machine Learning 45:5-32. https://doi.org/10.1023/A:1010933404324
  3. Brochu, E., Cora, V. M., and De Freitas, N. 2010. A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning. arXiv preprint arXiv:1012.2599.
  4. Guo, F., Zhou, X., Liu, J., Zhang, Y., Li, D., and Zhou, H. 2019. A Reinforcement Learning Decision Model For Online Process Parameters Optimization From Offline Data In Injection Molding. Applied Soft Computing 85:105828.
  5. Hong, J., and Jeon, S. 2023. Prediction of Safety Grade of Bridges Using the Classification Models of Decision Tree and Random Forest. Journal of The Korean Society of Civel Engineers 43(3):397-411.
  6. Hwang, H., Cho, Y., Hwang, S., and Kim, S. 2022. Optimal Tire Design Using Machine Learning and Bayesian Optimization. Journal of the Korean Institute of Industrial Engineers 48(4):433-440. https://doi.org/10.7232/JKIIE.2022.48.4.433
  7. Hwang, S., Han, S., and Lee, H. 2021. A Study on the Improvement of Injection Molding Process Using CAE and Decision-tree. Journal of the Korea Academia-Industrial cooperation Society 22(4):580-586. https://doi.org/10.5762/KAIS.2021.22.4.580
  8. Jeon, Y., and Cho, H. 2019. Model Based Hybrid Decision Tree. Journal of the Korean Data And Information Science Society 30(3):515-524. https://doi.org/10.7465/jkdi.2019.30.3.515
  9. Jeong, J. 2022. Predicting Defects of EBM-Based Additive Manufacturing through XGBoost. Journal of the Korea Institute of Information and Communication Engineering 26(5):641-648.
  10. Jones, D. R., Schonlau, M., and Welch, W. J. 1998. Efficient global optimization of expensive black-box functions. Journal of Global Optimization 13:455-492. https://doi.org/10.1023/A:1008306431147
  11. Kim, D. and Hong, J. 2023. Improvement of Plastic Injection Molding Process of Mole Trap Parts using Design of Experiments. Journal of the Korean Society of Manufacturing Technology Engineers 32(2):85-91. https://doi.org/10.7735/ksmte.2023.32.2.85
  12. Kim, K., and Kim, S. 2023. Hot-Rolled Steel Plate Thickness Prediction and Bayesian Optimization-Based Rolling Pattern Derivation. Journal of the Korean Institute of Industrial Engineers 49(2):167-175. https://doi.org/10.7232/JKIIE.2023.49.2.167
  13. Ko, M., and Cho, Y. 2022. Application of Deep Learning Algorithm for Defect Detection and Cause Analysis of Automotive Parts in Injection Process. Journal of the Korean Society of Manufacturing Technology Engineers 31(6):452-459. https://doi.org/10.7735/ksmte.2022.31.6.452
  14. Lee, Y., Joo, J., Lim, S., Lee, J., and Han, S. 2022. Optimization of Molding Conditions for Mobile Lens using Injection Molding CAE and Machine Learning. Journal of the Korean Society of Mechanical Technology 24(4):652-658. https://doi.org/10.17958/KSMT.24.4.202208.652
  15. Lim, S., Seo, H., and Yu, Y. 2023. Bayesian Optimization for 3D Source Localization from Multi-channel Time-series Signals. Journal of the Korean Society for Nondestructive Testing. 43(1):44-51. https://doi.org/10.7779/JKSNT.2023.43.1.44
  16. Wu, J., Chen, X. Y., Zhang, H., Xiong, L. D., Lei, H., and Deng, S. H. 2019. Hyperparameter Optimization for Machine Learning Models Based on Bayesian Optimization. Journal of Electronic Science and Technology 17(1):26-40.
  17. Yang, D., Lee, J., Yoon, K., and Kim, J. 2020. A Study on the Prediction of Optimized Injection Molding Condition using Artificial Neural Network (ANN). Transactions of Materials Processing 29(4):218-228. https://doi.org/10.5228/KSTP.2020.29.4.218
  18. Yang, D., Lee, J., Yoon, K., and Kim, J. 2022. A Study on the Practical Application of the Integrated ANN System for Manufacturing the Target Quality of the Injection Molded Product. Korea-Australia Rheology Journal 34(2):147-157. https://doi.org/10.1007/s13367-022-00026-x
  19. Yoo, J., and Lee, G., 2021. A Study on the Prediction Analysis of Quality Control Components and Control Criteria for Portuguese Red Wine using UCI Dataset: Focusing on the Decision Tree Techniques by CART Algorithm. Korean Journal of Hospitality & Tourism 30(6):239-255. https://doi.org/10.24992/KJHT.2021.8.30.06.239
  20. Zou, M., Jiang, W. G., Qin, Q. H., Liu, Y. C., and Li, M. L. 2022. Optimized XGBoost Model with Small Dataset for Predicting Relative Density of Ti-6Al-4V Parts Manufactured by Selective Laser Melting. Materials 15(15):5298.