품질경영학회지 (Journal of Korean Society for Quality Management)

  • 제51권1호
  • /
  • Pages.55-65
  • /
  • 2023
  • /
  • 1229-1889(pISSN)
  • /
  • 2287-9005(eISSN)
한국품질경영학회 (Korean Society for Quality Management)
권호 표지
DOI QR코드

DOI QR Code

XAI(eXplainable Artificial Intelligence) 알고리즘 기반 사출 공정 수율 개선 방법론

Injection Process Yield Improvement Methodology Based on eXplainable Artificial Intelligence (XAI) Algorithm

  • 홍지수 (인하대학교 산업경영공학과) ;
  • 홍용민 (인하대학교 산업경영공학과) ;
  • 오승용 (인하대학교 산업경영공학과) ;
  • 강태호 (인하대학교 산업경영공학과) ;
  • 이현정 (인하대학교 신소재공학과) ;
  • 강성우 (인하대학교 산업경영공학과)
  • Ji-Soo Hong (Department of Industrial Engineering, INHA University) ;
  • Yong-Min Hong (Department of Industrial Engineering, INHA University) ;
  • Seung-Yong Oh (Department of Industrial Engineering, INHA University) ;
  • Tae-Ho Kang (Department of Industrial Engineering, INHA University) ;
  • Hyeon-Jeong Lee (Materials Science and Engineering, INHA University) ;
  • Sung-Woo Kang (Department of Industrial Engineering, INHA University)
  • 투고 : 2023.02.01
  • 심사 : 2023.02.17
  • 발행 : 2023.03.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Purpose: The purpose of this study is to propose an optimization process to improve product yield in the process using process data. Recently, research for low-cost and high-efficiency production in the manufacturing process using machine learning or deep learning has continued. Therefore, this study derives major variables that affect product defects in the manufacturing process using eXplainable Artificial Intelligence(XAI) method. After that, the optimal range of the variables is presented to propose a methodology for improving product yield. Methods: This study is conducted using the injection molding machine AI dataset released on the Korea AI Manufacturing Platform(KAMP) organized by KAIST. Using the XAI-based SHAP method, major variables affecting product defects are extracted from each process data. XGBoost and LightGBM were used as learning algorithms, 5-6 variables are extracted as the main process variables for the injection process. Subsequently, the optimal control range of each process variable is presented using the ICE method. Finally, the product yield improvement methodology of this study is proposed through a validation process using Test Data. Results: The results of this study are as follows. In the injection process data, it was confirmed that XGBoost had an improvement defect rate of 0.21% and LightGBM had an improvement defect rate of 0.29%, which were improved by 0.79%p and 0.71%p, respectively, compared to the existing defect rate of 1.00%. Conclusion: This study is a case study. A research methodology was proposed in the injection process, and it was confirmed that the product yield was improved through verification.

키워드

과제정보

이 성과는 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2022H1D8A3037396).

참고문헌

  1. An, Y., and Jo, H. 2021. A Study on XAI-based Clinical Decision Support System. The Journal of the Korea Contents Association 21(12):13-22. https://doi.org/10.5392/JKCA.2021.21.12.013
  2. Arrieta, A. B., Daz-Rodrguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., and Herrera, F. 2020. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion 58:82-115. https://doi.org/10.1016/j.inffus.2019.12.012
  3. Chen.T., and Guestrin. C. 2016. XGBoost: A Scalable Tree Boosting System, KDD 2016: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningAugust 2016, 785-794.
  4. Chung, J., and Kim, D. 2008. Study on the design optimization of injection-molded DVD-Tray parts using CAE Simulation: Korea Academia-Industrial Cooperation Society 9(6):1726-1732. https://doi.org/10.5762/KAIS.2008.9.6.1726
  5. Goldstein, A., Kapelner, A., Bleich, J., and Pitkin, E. 2015. Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation. Journal of Computational and Graphical Statistics 24(1):44-65. https://doi.org/10.1080/10618600.2014.907095
  6. 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
  7. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q., and Liu, T. 2017. Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 30.
  8. Kim, G., Park, J., and Ahn, H., 2001. Direct Search-Based Robust Design of Warpage in Injection Molded Parts: J Korean Soc Qual Manag. 29(3):87.
  9. Korea AI Manufacturing Platform (KAMP), Injection Molding Machine AI Dataset, KAIST (UNIST, EPM Solutions), December 14, 2020, https://www.kamp-ai.kr/front/main/MAIN.01.01.jsp.
  10. Lee, H., Hong, Y., and Kang, S. 2021., Identifying Process Capability Index for Electricity Distribution System through Thermal Image Analysis: J Korean Soc Qual Manag. 49(3):327-340.
  11. Lee, H., and Kim, Y. 2022., A Pre-processing Process Using TadGAN-based Time-series Anomaly Detection: J Korean Soc Qual Manag. 50(3):459-471.
  12. Lee, K., Lee, K., and Ko, T. 2021. SMOTE Using Border-points and Expectation-maximization Algorithm for Imbalanced Data Classification: Journal of the Korean Institute of Industrial Engineers 47(3):232-241. https://doi.org/10.7232/JKIIE.2021.47.3.232
  13. Lundberg, S. M., and Lee, S. 2017. A unified approach to interpreting model predictions: Advances in neural information processing systems, 30.
  14. Mohammed. R., Rawashdeh. J., and Abdullah. M. 2020. Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results: International Conference on Information and Communication Systems.
  15. Oh, H., Son, A., and Lee, Z. 2021. Occupational accident prediction modeling and analysis using SHAP: Journal of Digital Contents Society 22(7):1115-1123. https://doi.org/10.9728/dcs.2021.22.7.1115
  16. Thiriez, A., and Gutowski, T. 2006. An environmental analysis of injection molding: In Proceedings of the 2006 IEEE International Symposium on Electronics and the Environment, 195-200.
  17. Wu, H., Ruan, W., Wang, J., Zheng, D., Liu, B., Geng, Y., Chai, X., Chen, J., Li, S., and Helal, S. 2021. Interpretable machine learning for covid-19: An empirical study on severity prediction task. IEEE Transactions on Artificial Intelligence.
  18. 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). https://doi.org/10.5228/KSTP.2020.29.4.218
  19. Zhao, P., Zhou, H., He, Y., Cai, K., and Fu, J. 2014. A nondestructive online method for monitoring the injection molding process by collecting and analyzing machine running data. The International Journal of Advanced Manufacturing Technology 72(5):765-777. https://doi.org/10.1007/s00170-014-5711-0