Implementación de un sistema de visión artificial para el fortalecimiento del aseguramiento de calidad y liberación de piezas en procesos de inyección de plásticos
Implementation of a Computer Vision System to Enhance Quality Assurance and Product Release in Plastic Injection Molding Processes.
DOI:
https://doi.org/10.5281/zenodo.23129583Keywords:
computer vision, quality assurance, plastic injection molding, automated inspection, smart manufacturingAbstract
The plastics manufacturing industry based on injection molding processes faces significant challenges related to quality assurance, particularly in the early detection of defects during production. In many industrial environments, inspection of molded components is still performed through manual visual evaluation conducted by operators, introducing variability associated with human criteria, visual fatigue, classification errors, and limited repeatability in product release. Such conditions increase the likelihood of material waste, rework, downtime, and the release of out-of-specification products, negatively affecting process stability and industrial competitiveness.
This work presents the implementation of a computer vision system aimed at strengthening quality assurance and product release in plastic injection molding processes, focused on the automated detection of surface and dimensional defects in molded plastic container-type parts. The proposed methodology included the diagnosis of conventional inspection procedures, identification of recurrent defects, selection of measurement instruments employed in dimensional validation, definition of critical process variables, and the conceptual design of an inspection system based on image acquisition and digital image processing.
The proposed system integrates industrial cameras, controlled lighting, and image analysis algorithms for the identification of defects such as flash, sink marks, deformations, geometric irregularities, and dimensional variations, enabling objective acceptance and rejection criteria for product release. Furthermore, a technological architecture compatible with smart manufacturing and Industry 4.0 principles is proposed to improve process traceability, repeatability, and reliability.
The obtained results indicate that the incorporation of computer vision technologies constitutes a viable alternative to reduce subjectivity associated with manual inspection, strengthen quality assurance systems, and minimize risks related to defective product manufacturing. It is concluded that this type of system provides a technological foundation for future industrial automation strategies, intelligent quality control, and continuous improvement in plastic transformation processes.
References
L. H. Sperling, Introduction to Physical Polymer Science, 4th ed. Hoboken, NJ, USA: Wiley, 2005.
M. Osswald and J. Hernández-Ortiz, Polymer Processing: Modeling and Simulation. Munich, Germany: Hanser Publishers, 2006.
S. Kalpakjian and S. Schmid, Manufacturing Engineering and Technology, 7th ed. Boston, MA, USA: Pearson, 2014.
D. V. Rosato and M. G. Rosato, Injection Molding Handbook, 3rd ed. Boston, MA, USA: Springer, 2000.
J. A. Brydson, Plastics Materials, 7th ed. Oxford, U.K.: Butterworth-Heinemann, 1999.
D. C. Montgomery, Introduction to Statistical Quality Control, 8th ed. Hoboken, NJ, USA: Wiley, 2019.
A. I. Isayev, Injection and Compression Molding Fundamentals. Boca Raton, FL, USA: CRC Press, 1987.
M. Attaran, “The rise of Industry 4.0 and the importance of advanced manufacturing technologies,” Journal of Innovation Management, vol. 8, no. 4, pp. 12–31, 2020.
R. Szeliski, Computer Vision: Algorithms and Applications, 2nd ed. London, U.K.: Springer, 2022.
S. Yin, X. Li, H. Gao, and O. Kaynak, “Data-based techniques focused on modern industry: An overview,” IEEE Transactions on Industrial Electronics, vol. 62, no. 1, pp. 657–667, Jan. 2015.
A. Kumar, “Computer-vision-based fabric defect detection: A survey,” IEEE Transactions on Industrial Electronics, vol. 55, no. 1, pp. 348–363, Jan. 2008.
Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
H. Wang, Y. Li, and X. Zhang, “Deep-learning-based surface defect detection for industrial applications: A review,” Applied Sciences, vol. 11, no. 14, p. 6378, 2021.
M. Javaid, A. Haleem, R. P. Singh, and R. Suman, “Industrial artificial intelligence for smarter manufacturing: A review,” Manufacturing Letters, vol. 27, pp. 11–16, 2021.
J. Ren, Y. Wang, and X. Zhao, “Automated visual inspection in manufacturing using deep learning and computer vision techniques,” Scientific Reports, vol. 14, no. 1, pp. 1–15, 2024.
Keyence IV Series Vision Sensor, Keyence Corp., Osaka, Japan, 2026. [Online]. Available: https://www.keyence.com/products/vision/vision-sensor/iv4/. [Accessed: May 30, 2026].
Downloads
Published
How to Cite
Conference Proceedings Volume
Section
License
Copyright (c) 2026 Arturo Aguilar Pérez, Ricardo Vázquez Ortíz, José Daniel Castro Díaz, Blanca Gabriela Cuevas González, María de la Luz Delgadillo Torres, Wenceslao Cuauhtémoc Bonilla Blancas
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
