Intelligent system for the continuous improvement of visual inspection of damage in auto parts in the industry
DOI:
https://doi.org/10.61117/ipsumtec.v5i5.145Keywords:
Intelligent system, Vision sensor, Visual inspection, Artificial intelligence, Industry 4.0, Neural networksAbstract
This article discusses ongoing research at the Instituto Tecnológico Nacional de México, Ciudad Juárez campus, focused on the Keyence vision sensor and its application in the visual inspection of labels with QR codes. The study highlights the importance of this technology in the automotive industry. The Keyence sensor is capable of comparing images in real time by referencing a master image and identifying errors based on a defined acceptance percentage.
The research aims to identify the key factors influencing image comparison using the vision sensor. Tests are being conducted to refine these factors and determine the criteria necessary for an image to be accepted by the sensor. The study is investigating how artificial intelligence can enhance image comparison accuracy. By defining these influencing factors, the goal is to improve the quality of images accepted by the sensor, ultimately achieving a higher level of excellence in visual inspections. This research supports the development of tools based on such findings, contributing to the advancement of Industry 4.0 technologies.
Downloads
Metrics
References
Jaramillo Ortiz, A., Jiménez, R., & Ramos, O. L. (2014). Inspección de calidad para un sistema de producción industrial basado en el procesamiento de imágenes. Tecnura, 18(41),76-90. DOI: https://doi.org/10.14483/udistrital.jour.tecnura.2014.3.a06
Cognex. (2022). QUÉ ES LA VISIÓN ARTIFICIAL. Retrieved from https://www.cognex.com/es-mx/what-is/machine-vision/what-is-machine-vision
Galán, H., & Martínez, A. (1998). Inteligencia artificial. Redes neuronales y aplicaciones. Carlos III Madrid.
Calatayud, A., & Katz, R. (2019). Cadena de suministro 4.0: Mejores prácticas internacionales y hoja de ruta para América Latina (Vol. 744): Inter-American Development Bank. DOI: https://doi.org/10.18235/0001956
Kuric, I., Klarák, J., Bulej, V., Sága, M., Kandera, M., Hajdučík, A., & Tucki, K. (2022). Approach to Automated Visual Inspection of Objects Based on Artificial Intelligence. Applied Sciences, 12(2), 864. DOI: https://doi.org/10.3390/app12020864
Rabiza, M. (2022). Point and Network Notions of Artificial Intelligence Agency. Paper presented at the Proceedings. DOI: https://doi.org/10.3390/proceedings2022081018
Bowen, A. M., Telemática, I., & Asensio, H. G. Inteligencia artificial. Redes neuronales y aplicaciones.
Aponte, A. (2012). Aplicación de técnicas de visión artificial para la inspección visual de recubrimiento de cable. (Maestría en Ingeniería: Ingeniería de Sistemas). Pontificia Universidad Javeriana Facultad de Ingenierías Santiago de Cali, Santiago de Cali. Retrieved from https://www.hbenitez.org/Students_files/monografia.pdf
Benbarrad, T., Salhaoui, M., Kenitar, S. B., & Arioua, M. (2021). Intelligent machine vision model for defective product inspection based on machine learning. Journal of Sensor and Actuator Networks, 10(1), 7. DOI: https://doi.org/10.3390/jsan10010007
Keyence. (2021a). Sistema de medición dimensional de imágenes Serie IM-8000. In.
Keyence. (2021b). Serie VR-6000 Perfilómetro Óptico 3D. In.
Keyence. (2022). IV-Navigator (IV-H1) Software. In.
Selmaier, A., Kunz, D., Kisskalt, D., Benaziz, M., Fürst, J., & Franke, J. (2022). Artificial Intelligence-Based Assistance System for Visual Inspection of X-ray Scatter Grids. Sensors, 22(3), 811. DOI: https://doi.org/10.3390/s22030811
Keyence. (2017). Soluciones de Trazabilidad para las Industrias Automotriz y de Autopartes. In.
Keyence. (2019). Sistema de visión multidimensional Serie CV-X/XG-X. In.
Published
How to Cite
Issue
Section
License
Copyright (c) 2022 Janeth Yessenia Reyes Chávez, Humberto García Castellanos, Carlos Alberto Ochoa Ortiz, David Díaz Murillo
This work is licensed under a Creative Commons Attribution 4.0 International License.
