[ Special Issue : Application of Sensor Technology in Polymer Processing ]

Journal of the Korean Society of Manufacturing Technology Engineers - Vol. 33, No. 5, pp.251-261

ISSN: 2508-5107 (Online)

Print publication date 15 Oct 2024

Received 29 Aug 2024 Revised 20 Sep 2024 Accepted 23 Sep 2024

DOI: https://doi.org/10.7735/ksmte.2024.33.5.251

설명가능 인공지능(XAI) 기반 사출금형 내 성형조건(IMC)의 품질 영향도 분석 방법론

김진수^a^{, *} ; 린청윈^b^{, c} ; 텅리솅^b^{, c}

Analysis Methodology for Effect of In-Mold Condition (IMC) on Quality based on Explainable Artificial Intelligence (XAI) in Injection Molding

Jinsu Gim^a^{, *} ; Chung-Yin Lin^b^{, c} ; Lih-Sheng Turng^b^{, c}

aDongnam Technology Application Division, Korea Institute of Industrial Technology (KITECH)
bDepartment of Mechanical Engineering, University of Wisconsin–Madison
cWisconsin Institute for Discovery, University of Wisconsin–Madison

Correspondence to: ^*Tel.: +82-55-924-0134 E-mail address: jgim@kitech.re.kr (Jinsu Gim).

Abstract

This paper proposes a methodology to analyze the effect of in-mold conditions (IMCs) on part quality for autonomous manufacturing in injection molding. The IMC is the most important information affecting part quality in injection molding because it presents detailed molding conditions in the cavity. To utilize IMCs for monitoring, optimization, and control, the relationship between IMC and quality should be analyzed. The main goal of the proposed method is to use explainable artificial intelligence (XAI) to automate analysis tasks and yield more objective and quantitative results than conventional knowledge-driven methods based on previous knowledge and understanding. The contributions of IMC features to the quality of a specific part quality and the overall effect of IMC features on molding processes are analyzed by applying XAI to IMC–Quality AI models. The analysis results can be further utilized for specific quality-targeted monitoring and intelligent process optimization based on IMCs.

Keywords:

Autonomous manufacturing, Explainable artificial intelligence (XAI), Injection molding, In-mold condition, Process analysis

Acknowledgments

본 연구는 한국생산기술연구원 기본사업 “펨토초 레이저를 활용한 20 um 급 위치 제어 기반 고정밀 렌즈 사출성형 기술 개발(KITECH UR240031)”의 지원으로 수행한 연구입니다.

References

Collins, C., 1999, Monitoring Cavity Pressure Perfects Injection Molding, Assem. Autom., 19:3 197-202. [https://doi.org/10.1108/01445159910280056]
Menges, G., Michaeli, W., Mohren, P., 2001, How to Make Injection Molds(3rd edition), Carl Hanser Verlag, USA.
Kazmer, D. O., 1995, Dynamic Feed Control: A New Method for Injection Molding of High Quality Plastic Parts, Doctorate Thesis, Stanford University, USA.
Huang, M.-S., Ke, K.-C., Liu, C.-Y., 2021, Cavity Pressure Based Holding Pressure Adjustment for Enhancing the Consistency of Injection Molding Quality, J. Appl. Polym. Sci., 138:18 50357. [https://doi.org/10.1002/app.50357]
Hassan, H., 2013, An Experimental Work on the Effect of Injection Molding Parameters on the Cavity Pressure and Product Weight, Int. J. Adv. Manuf. Technol., 67 675-686. [https://doi.org/10.1007/s00170-012-4514-4]
Gim, J.-S., Tae, J.-S., Jeon, J.-H., Choi, J.-H., Rhee, B.-O., 2015, Detection Method of Filling Imbalance in a Multi-cavity Mold for Small Lens, Int. J. Precis. Eng. Manuf., 16:3 531-535. [https://doi.org/10.1007/s12541-015-0072-7]
Kim, B., Gim, J., Han, E., Rhee, B., 2021, Development of the Vent Clogging Monitoring Methods for Injection Molding, CIRP J. Manuf. Sci. Technol., 32 277-286. [https://doi.org/10.1016/j.cirpj.2021.01.009]
Guan, W.-S., Huang, H.-X., 2013, A Proposed Technique to Acquire Cavity Pressure Using a Surface Strain Sensor During Injection-Compression Molding, J. Manuf. Sci. Eng., 135:2 021003. [https://doi.org/10.1115/1.4023376]
Román, A. J., Qin, S., Zavala, V. M., Osswald, T. A., 2021, Neural Network Feature and Architecture Optimization for Injection Molding Surface Defect Prediction of Model Polypropylene, Polym. Eng. Sci., 61:9 2376-2387. [https://doi.org/10.1002/pen.25765]
Lockner, Y., Hopmann, C., Zhao, W., 2022, Transfer Learning with Artificial Neural Networks Between Injection Molding Processes and Different Polymer Materials, J. Manuf. Process., 73 395-408. [https://doi.org/10.1016/j.jmapro.2021.11.014]
Jeon, J., Rhee, B., Gim, J., 2022, Melt Temperature Estimation by Machine Learning Model Based on Energy Flow in Injection Molding, Polymers, 14:24 5548. [https://doi.org/10.3390/polym14245548]
Lin, C. Y., Gim, J., Shotwell, D., Lin, M.-T., Liu, J.-H., Turng, L.-S., 2024, Explainable artificial intelligence and multi-stage transfer learning for injection molding quality prediction, J. Intell. Manuf., 1-20. [https://doi.org/10.1007/s10845-024-02436-w]
Farahani, S., Xu, B., Filipi, Z., Pilla, S., 2021, A Machine Learning Approach to Quality Monitoring of Injection Molding Process using Regression Models, Int. J. Comput. Integr. Manuf., 34:11 1223-1236. [https://doi.org/10.1080/0951192X.2021.1963485]
Wang, Z. H., Wen, F. C., Li, Y. T., Tsou, H. H., 2023, A Novel Sensing Feature Extraction Based on Mold Temperature and Melt Pressure for Plastic Injection Molding Quality Assessment, IEEE Sensors Journal, 23:7 7451-7459. [https://doi.org/10.1109/JSEN.2023.3247597]
Rønsch, G. Ø., Kulahci, M., Dybdahl, M., 2021, An Investigation of the Utilisation of Different data Sources in Manufacturing with Application in Injection Moulding, Int. J. Prod. Res., 59:16 4851-4868. [https://doi.org/10.1080/00207543.2021.1893853]
Kramschuster, A., Cavitt, R., Ermer, D., Chen, Z., Turng, L.-S., 2005, Quantitative Study of Shrinkage and Warpage Behavior for Microcellular and Conventional Injection Molding, Polym. Eng. Sci., 45:10 1408-1418. [https://doi.org/10.1002/pen.20410]
Fu, T.-C., Hung, Y.-K., Chung, F.-I., 2017, Improvement Algorithms of Perceptually Important Point Identification for Time Series Data Mining, IEEE 4th International Conference on Soft Computing & Machine Intelligence (ISCMI), 11-15. [https://doi.org/10.1109/ISCMI.2017.8279589]
Gim, J, Rhee, B., 2021, Novel Analysis Methodology of Cavity Pressure Profiles in Injection-molding Processes using Interpretation of Machine Learning Model, Polymers, 13:19 3297. [https://doi.org/10.3390/polym13193297]
Gim, J., Turng, L.-S., 2023, Interpretation of the Effect of Transient Process Data on Part Quality of Injection Molding based on Explainable Artificial Intelligence, Int. J. Prod. Res., 61:23 8192-8212. [https://doi.org/10.1080/00207543.2023.2216310]
Colas, C., Sigaud, O., Oudeyer, P.-Y., 2018, How Many Random Seeds? Statistical Power Analysis in Deep Reinforcement Learning Experiments, arXiv preprint arXiv:1806.08295. [https://doi.org/10.48550/arXiv.1806.08295]
Lundberg, S. M., Erion, G., Chen, H., DeGrave, A., Prutkin, J. M., Nair, B., Katz, R., Himmelfarb, J., Bansal, N., Lee, S.-I., 2020, From Local Explanations to Global Understanding with Explainable AI for Trees, Nat. Mach. Intell., 2 56-67. [https://doi.org/10.1038/s42256-019-0138-9]
Chang, H., Su, Z., Lu, S., Zhang, G., 2022, Application of Deep Learning Network in Bumper Warpage Quality Improvement, Processes, 10:5 1006. [https://doi.org/10.3390/pr10051006]
Chen, J.-Y., Tseng, C.-C., Huang, M.-S., 2019, Quality Indexes Design for Online Monitoring Polymer Injection Molding, Adv. Polym. Technol., 2019:1 3720127. [https://doi.org/10.1155/2019/3720127]
Ke, K.-C., Huang, M.-S., 2020, Quality Prediction for Injection Molding by Using a Multilayer Perceptron Neural Network, Polymers, 12:8 1812. [https://doi.org/10.3390/polym12081812]
Párizs, R. D., Török, D., Ageyeva, T., Kovács, J. G., 2022, Machine Learning in Injection Molding: An Industry 4.0 Method of Quality Prediction, Sensors, 22:7 2704. [https://doi.org/10.3390/s22072704]
Rhee, B., Gim, J, 2023, Monitoring Apparatus using Sensor Signal in Injection Mold and Method Thereof, KR Patent: 10-2500376.

Jinsu Gim

Senior Researcher, Korea Institute of Industrial Technology (KITECH).His research interests are Autonomous Manufacturing for Polymer/Plastic Industry, Rheology, and Mold Technology.

E-mail:

Chung-Yin Lin

Research Assistant (Ph.D. Candidate), Department of Mechanical Engineering, University of Wisconsin–Madison.His research interests are Artificial Intelligence for Polymer Processing, Polymer Composites, and CAE.

E-mail:

Lih-Sheng (Tom) Turng

Professor, Department of Mechanical Engineering, University of Wisconsin–Madison.His research interests are Injection Molding, Microcellular Injection Molding, Nanocomposites, Multi-functional Materials, Bio-based Polymers, Tissue Engineering, and Bio-manufacturing.

E-mail: turng@engr.wisc.edu