Digital Twin for proactive quality control in industrial vision systems
DOI:
https://doi.org/10.17979/ja-cea.2026.47.13716Keywords:
Intelligent manufacturing systems, Process supervision, multi-agent systems applied to industrial systems, Quality assurance and maintenanceAbstract
This work presents a Digital Twin aimed at incorporating proactive quality control capabilities into industrial vision systems applied to the manufacturing of automotive components. The proposed approach combines an existing industrial inspection
system with a multi-agent platform developed using SPADE and deep learning-based models for the automatic identification of surface defects. The Digital Twin enables the synchronization of information generated by the physical inspection system with
a digital representation oriented toward defect analysis and production-process traceability. For automatic defect identification, models based on the YOLO architecture are trained using images acquired from the industrial environment. In addition, a
traceability analysis mechanism is proposed to associate specific defects with different stages of the manufacturing process. The proposed architecture has been defined and functionally validated in an industrial environment for headlamp lens inspection,
providing a basis for future supervision and proactive quality control strategies in manufacturing.
References
Frick, J., Grudowski, P., 6 2023. Quality 5.0: A paradigm shift towards proactive quality control in industry 5.0. International Journal of Business Administration 14, 51. DOI: 10.5430/ijba.v14n2p51.
International Organization for Standardization, 2021. ISO 23247-1:2021 Automation systems and integration – Digital twin framework for manufacturing–Part 1: Overview and general principles. URL: https://www.iso.org/standard/75066.html
Leberruyer, N., Bruch, J., Ahlskog, M., Afshar, S., 5 2023. Toward zero defect manufacturing with the support of artificial intelligence—insights from an industrial application. Computers in Industry 147. DOI: 10.1016/j.compind.2023.103877
Lou, H. H., Huang, Y. L., 2003. Hierarchical decision making for proactive quality control: System development for defect reduction in automotive coating operations. Engineering Applications of Artificial Intelligence 16, 237–250. DOI: 10.1016/S0952-1976(03)00060-5
Martínez, S., Ortega, J., García, J., García, A., Estévez, E., 2013. An industrial vision system for surface quality inspection of transparent parts. International Journal of Advanced Manufacturing Technology 68. DOI: 10.1007/s00170-013-4904-2
Martínez, S. S., Ortega, J. G., García, J. G., García, A. S., 2012. A machine visión system for defect characterization on transparent parts with non-plane surfaces. Machine Vision and Applications 23. DOI: 10.1007/s00138-010-0281-0
Psarommatis, F., May, G., Dreyfus, P. A., Kiritsis, D., 2020. Zero defect manufacturing: state-of-the-art review, shortcomings and future directions in research. International Journal of Production Research 58, 1–17. DOI: 10.1080/00207543.2019.1605228
Redmon, J., Divvala, S., Girshick, R., Farhadi, A., 5 2016. You only look once: Unified, real-time object detection. arXiv preprint arXiv:1506.02640. URL: http://arxiv.org/abs/1506.02640
Saadallah, A., Abdulaaty, O., B¨uscher, J., Panusch, T., Morik, K., Deuse, J., 2022. Early quality prediction using deep learning on time series sensor data. In: Procedia CIRP. Vol. 107. Elsevier B.V., pp. 611–616. DOI: 10.1016/j.procir.2022.05.034
Shahin, M., Chen, F. F., Bouzary, H., Krishnaiyer, K., 3 2020. Integration of lean practices and industry 4.0 technologies: smart manufacturing for nextgeneration enterprises. International Journal of Advanced Manufacturing Technology 107, 2927–2936. DOI: 10.1007/s00170-020-05124-0
Tzampazaki, M., Zografos, C., Vrochidou, E., Papakostas, G. A., 2 2024. Machine vision—moving from industry 4.0 to industry 5.0. Applied Sciences (Switzerland) 14. DOI: 10.3390/app14041471
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Sergio Illana Rico, Silvia Satorres Martínez, Elisabet Estévez Estévez, Alejandro Sánchez García, Diego M. Martínez Gila, Javier Gámez García
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
