Abstract
Data-based process monitoring in injection molding plays an important role in compensating disturbances in the process and the associated impairment of part quality. Selecting appropriate features for a successful online quality prediction based on machine learning methods is crucial. Time series such as the injection pressure and injection flow curve are particularly suitable for this purpose. Predicting quality as early as possible during a cycle has many advantages. In this paper it is shown how the recording length of the time series affects the prediction performance when using machine learning algorithms. For this purpose, two successful molding quality prediction algorithms (k Nearest Neighbors and Ridge Regression) are trained with time series of different lengths on extensive data sets. Their prediction performances for part weight and a geometric dimension are evaluated. The evaluations show that recording time series until the end of a cycle is not necessary to obtain good prediction results. These findings indicate that early reliable quality prediction is possible within a cycle, which speeds up prediction, allows timely part handling at the end of the cycle and provides the basis for automated corrective interventions within the same cycle.
-
Research ethics: Not applicable.
-
Informed consent: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: Parts of this project (HA project no. 864/20–21) were financed with funds of LOEWE – Landes-Offensive zur Entwicklung Wissenschaftlich-ökonomischer Exzellenz, Förderlinie 3: KMU-Verbundvorhaben (State Offensive for the Development of Scientific and Economic Excellence).
-
Data availability: The used datasets are publicly available. https://github.com/sc4t1m/scatimdata (Referenced in the text).
References
Bibow, P., Dalibor, M., Hopmann, C., Mainz, B., Rumpe, B., Schmalzing, D., Schmitz, M., and Wortmann, A. (2020). Model- driven development of a digital model-driven develop ment of a digital twin for injection molding. In: Advanced information systems engineering. Springer, Cham.10.1007/978-3-030-49435-3_6Search in Google Scholar
Bogedale, L., Doerfel, S., Schrodt, A., and Heim, H.-P. (2023a). Online prediction of molded part quality in the injection molding process using high-resolution time series. Polymers 15: 4, https://doi.org/10.3390/polym15040978.Search in Google Scholar PubMed PubMed Central
Bogedale, L., Schrodt, A., and Heim, H.-P. (2023b). Time series data for process monitoring in injection molding: a quantitative study of the benefits of a high sampling rate. Int. Polym. Process. 38: 167–174, https://doi.org/10.1515/ipp-2022-4258.Search in Google Scholar
Chen, W.-C., Tai, P.-H., Wang, M.-W., Deng, W.-J., and Chen, C.-T. (2008). A neural network-based approach for dynamic quality prediction in a plastic injection molding process. Expert Syst. Appl. 35: 843–849, https://doi.org/10.1016/j.eswa.2007.07.037.Search in Google Scholar
Developers, scikit-learn (2023a). sklearn.linear_model.Ridge, Available at: https://scikit-learn.org/stable/modules/generated/sklearn.linear_model.Ridge.html (Accessed 02 October 2023).Search in Google Scholar
Developers, scikit-learn (2023b). sklearn.neighbors.KNeighborsRegressor, Available at: https://scikit-learn.org/stable/modules/generated/sklearn.neighbors.KNeighborsRegressor.html (Accessed 02 October 2023).Search in Google Scholar
Eben, J. (2014). Identifikation und Reduzierung realer Schwankungen durch praxistaugliche Prozessführungsmethoden beim Spritzgießen, Ph.D. thesis. Chemnitz.Search in Google Scholar
Heim, H.-P. (2002). Quality assurance in plastics injection moulding – process monitoring and process control. In: Business briefing: medical device manufacturing & technology. Business Briefings Ltd., London.Search in Google Scholar
Heinzler, F.A. (2014). Modellgestützte Qualitätsregelung durch eine adaptive, druckgeregelte Prozessführung beim Spritzgießen, Ph.D. thesis. Duisburg, Universität Duisburg- Essen.10.3139/O999.02032015Search in Google Scholar
Huang, M.-S., Cheng, K.K., and Wu, P.W. (2022). A machine learning method for predicting part weight, dimensions, and residual stress during InjectionMolding. In: 2022 25th international conference on mechatronics technology (ICMT), pp. 1–4.10.1109/ICMT56556.2022.9997777Search in Google Scholar
Ke, K.-C. and Huang, M.-S. (2020). Quality prediction for injection molding by using a multilayer perceptron neural network. Polymers 12: 1–22, https://doi.org/10.3390/polym12081812.Search in Google Scholar PubMed PubMed Central
Klocke, F., Abel, D., Hopmann, C., Auerbach, T., Keitzel, G., Reiter, M., Reßmann, A., Stemmler, S., and Veselovac, D. (2015). Approaches of self-optimising systems in manufacturing. In: Brecher, C. (Ed.). Advances in production technology. Lecture notes in pro duction engineering. Springer Open, Cham, Heidelberg, New York, Dordrecht, London, pp. 161–171.10.1007/978-3-319-12304-2_12Search in Google Scholar
Kruppa, S. (2015). Adaptive Prozessführung und alternative Einspritzkonzepte beim Spritzgießen von Thermoplasten: Dissertation, Ph.D. thesis. Shaker Verlag GmbH.Search in Google Scholar
Nagorny, P., Pillet, M., Pairel, E., Le Goff, R., Loureaux, J., Wali, M., and Kiener, P. (2017). Quality prediction in injection molding. In: 2017 IEEE international conference on computational intelligence and virtual environments for measurement systems and applications (CIVEMSA), pp. 141–146.10.1109/CIVEMSA.2017.7995316Search in Google Scholar
Osswald, T.A. (2017). Understanding polymer processing: processes and governing equations. Hanser, Munich, Cincinnati, pp. 119–120.10.3139/9781569906484.006Search in Google Scholar
Párizs, R.D., Török, D., Ageyeva, T., and Kovács, J.G. (2022). Machine learning in injection molding: an industry 4.0 method of quality prediction. Sensors 22: 7, https://doi.org/10.3390/s22072704.Search in Google Scholar PubMed PubMed Central
Schiffers, R. (2009). Modellgestätzte Qualitätsregelung durcheine Adaptive, Druckgeregelte Prozessführung beim Spritz gießen, Ph.D. thesis. Duisburg, Universität Duisburg-Essen, pp. 52–99.Search in Google Scholar
Schiffers, R., Morik, K., Schulze Struchtrup, A., Honysz, P.-J., and Wortberg, J. (2018). Anomaly detection in injection molding process data based on unsupervised learning. J. Plast. Technol. 14: 302–347, https://doi.org/10.3139/O999.02052018.Search in Google Scholar
Schulze Struchtrup, A. (2021). Ganzheitliche Formteil- Qualitätsprognose für das Spritzgießen thermoplastischer Kunststoffe auf der Basis maschineller Lernverfahren: Dissertation, Ph.D. thesis. Universität Duisburg-Essen.Search in Google Scholar
Wick, C., Ehrig, F., and Schuster, G. (2020). Data driven injection moulding. In: Hopmann, C. and Dahlmann, R. (Eds.), Advances in polymer processing 2020: proceedings of the international symposiumon plastics tech nology, pp. 128–136.10.1007/978-3-662-60809-8_11Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston