Visual quality prediction of plastic product based on thermographic images

Visual quality prediction of plastic product based on thermographic images


download PDF

Abstract. The main purpose of this study is to control the visual quality in plastic injection moulding using an infrared camera after the ejection of the plastic part. Quality indicators have been extracted from the thermal image and from the data recorded by the sensors in the plastic injection machine and in the mould. After cooling, visual quality has been labelled by plastic experts based on 3 aesthetic defects: spot, flow line and streak mark. Three methods of reducing the dimension of the thermal image were studied: Quantiles, Principal Component Analysis (PCA), and Linear Discriminant Analysis (LDA). The visual quality can be predicted efficiently using dimension reduction of the image and Partial Least Square (PLS) regression. The PLS results allow to identify the root causes that explain the apparition of visual defects.

Injection Moulding, Quality Prediction, Thermography

Published online 4/19/2023, 10 pages
Copyright © 2023 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA

Citation: LE GOFF Ronan, MARCHAL Nils, AGAZZI Alban, Visual quality prediction of plastic product based on thermographic images, Materials Research Proceedings, Vol. 28, pp 1565-1574, 2023


The article was published as article 169 of the book Material Forming

Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.

[1] S. Kumar, H. Park, C.M. Lee, Data-driven smart control of injection molding process, CIRP-JMST 31 (2020) 439-449.
[2] F. Finkeldey, J. Volke, J.-C. Zarges, H.-P. Heim, P. Wiederkehr, Learning quality characteristics for plastic injection molding processes using a combination of simulated and measured data, J. Manuf. Process. 60 (2020) 134-143.
[3] D. Kazmer, S. Westerdale, D. Hazen, A comparison of statistical process control (SPC) and on-line multivariate analyses (MVA) for injection modling, Int.. Polym. Process. 23 (2008) 5.
[4] R. Gao, X. Tang, G. Gordon, D. Kazmer, Online product quality monitoring through in-process measurement, CIRP Annals 63 (2014) 493-496.
[5] D.O. Kazmer, L. Hutson, D. Hazen, Machine learning and multi-objective optimization of industrial extrusion, SPE ANTEC (2020).
[6] H. Lau, T. Wong, K. Pun, Neural-fuzzy modeling of plastic injection molding machine for intelligent control, Expert. Syst. Appl. 17 (1999) 33-43.
[7] B.H.M. Sadeghi, A BP-neural network predictor model for plastic injection molding process, J. Mater. Process. Technol. 103 (2000) 411-416.
[8] P. Yarlagadda, C. Khong, Development of hybrid neural system for prediction of process parameters in injection moulding, J. Mater. Process. Technol. 118 (2001) 110-116.
[9] E. Li, L. Jia, J. Yu, A genetic neural fuzzy system-based quality prediction model for injection process, Comput. Chem. Eng. 26 (2002) 1253-63.
[10] W.-C. Chen, P.-H. Tai, M.-W. Wang, W.-J. Deng, C.-T. Chen, A neural network-based approach for dynamic quality prediction in a plastic injection molding process, Expert Syst. Appl. 35 (2008) 843-849.
[11] F. Yin, H. Mao, L. Hua, A hybrid of back propagation neural network and genetic algorithm for optimization of injection molding process parameters, Mater. Des. 32 (2011) 3457-3464.
[12] N. Baudet, M. Pillet, J.L. Maire, Visual inspection of products: a comparison of the methods used to evaluate surface anomalies, Int. J. Metrol. Qual. Eng. 2 (2011) 31-38.
[13] P. Nagorny, T. Lacombe, H. Favreliere, M. Pillet, E. Pairel, R. Le Goff, M. Wali,
J. Loureaux, P. Kiener, Generative Adversarial Networks for geometric surfaces prediction in injection molding, IEEE ICIT, (2018).
[14] R. Farooque, M. Asjad, S.J.A. Rizvi, A current state of art applied to injection moulding manufacturing process – A review, Mater. Today: Proc. 43 (2021) 441-446.
[15] P. Nagorny, Contrôle automatique non-invasif de la qualité des produits – Application au procédé d’injection-moulage des thermoplastiques, Grenoble: Université Grenoble Alpes, (2020).
[16] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, E. Duchesnay, Scikit-learn : Machine learning in Python, J. Mach. Learn. Res. 12 (2011) 2825-2830.
[17] G. Van Rossum, F.L. Drake Jr, Python reference manual, Centrum voor Wiskunde en Informatica Amsterdam, (1995).
[18] G. Saporta, Probabilités, analyse de données et statistique, third ed., Technip, (2011).
[19] J.-Y. Chen, V.-V. Tseng, M.-S. Huang, Quality Indexes Design for Online Monitoring Polymer Injection Molding, Adv. Polym. Technol. ID 3720127 (2019).
[20] F. Bertrand and M. Maumy-Bertrand, Partial Least Squares Regression for Generalized Linear Models, R package version 1.5.0 (2022).
[21] F. Bertrand and M. Maumy-Bertrand, “Partial Least Squares Regression for Generalized Linear Models,” in book of abstracts, User2014!, Los Angeles, (2014).
[22] N. Meyer, M. Maumy-Bertrand, F. Bertrand, Comparaison de la regression PLS et de la regression logistique PLS: application aux donnees d’allelotypage, Journal de la Societe Francaise de Statistique (2010).,.
[23] R.C. Team, R: A language and environment for statistical, Vienna, Austria: R Foundation for Statistical Computing URL, (2022).