Vision system for the detection of quality failures in the identification of labels in an automotive production line
Abstract
This article presents the implementation of a vision system for the detection of label identification failures in a production line of comfort electric motors for vehicles. Previously, the production line was completely dependent on visual inspection by an operator. The proposed solution considers both the technical aspects of the vision system and other key factors to ensure the quality of the process, such as: the quality assurance policies of the automotive standards in force in Mexico (IATF 6949:2016 and ISO9000), continuous improvement, statistics, ergonomics and standardization of processes. The results demonstrate the success of the implementation. The system proved effective in accurately identifying failures; a significant reduction in the risk priority number was achieved in the failure effects analysis and mode; and a reduction in the statistics of internal failures and with the client was achieved, from 2021 to 2022.
Downloads
References
Bailey, M. (2007). Six Sigma Quality Improvement With MINITAB. Technometrics, 49(1), 105–105. https://doi.org/10.1198/tech.2007.s459
Dudek-Burlikowska, M., & Szewieczek, D. (2009). The Poka-Yoke method as an improving quality tool of operations in the process. Journal of Achievements in Materials and Manufacturing Engineering, 36(1), 95–102.
Hawryluk, M., Gronostajski, Z., Jabłoński, P., Janik, M., & Suliga, M. (2023). An integrated vision control system for the evaluation of the shape-dimensional accuracy and quality of valve forgings used in motor fftruck engines. Measurement, 210, 112541.
Huang, P., Liu, C., Yang, X., Yi, D., & Zhang, H. (2022). High-speed measurement system for cord-rubber composites on conveyor belt based on machine vision. 5th International Conference on Informatics Engineering and Information Science (ICIEIS 2022), 12452, 62–68.
Johnson, C. N. (2002). The benefits fo PDCA. Quality Progress, 35(5), 120.
Karger, D. W., & Bayha, F. H. (1987). Engineered work measurement: The principles, techniques, and data of methods-time measurement background and foundations of work measurement and methods-time measurement, plus other related material. Industrial Press Inc.
Keyence México S.A de C.V. (2010). Procesamiento de imagenes: Consejos útiles Vol.1 Lentes#1. https://www. keyence.com.mx/mykeyence/?ptn=001&deqwas_inflow=QGRzcDUwOmdrLWp2Vk1NdkV5UWlGOGtXTENoWmc6dmlld2VyX2RvYzo6MTAyMjQ3MjE6MVE&ad_local=recoassetmykp
Keyence México S.A de C.V. (2019). Cómo seleccionar su primer sistema de visión.
Keyence México S.A de C.V. (2019). Catálogo de sistemas de visión multiespectral
Luckow, A., Cook, M., Ashcraft, N., Weill, E., Djerekarov, E., & Vorster, B. (2016). Deep learning in the automotive industry: Applications and tools. 2016 IEEE International Conference on Big Data (Big Data), 3759–3768.
Mode, F. (2011). Effects analysis fmea handbook (with robustness linkages) v4. 2. Ford Motor Company.
Montalvo-Arenas, C. E. (2010). Óptica. https://bct.facmed .unam.mx/wp-content/uploads/2018/08/1_optica.pdf
Peralta, J. L., Jiménez, E. A., & Pérez, M. A. R. (2014). Estudio del trabajo: Una nueva visión. Grupo Editorial Patria.
Plinta, D., Golinska, E., & Dulina, Ľ. (2021). Practical Application of the New Approach To FMEA Method according to AIAG and VDA Reference Manual. Communications - Scientific Letters of the University of Zilina, 23(4), B325–B335. https://doi.org/10.26552/com. C.2021.4.B325-B335
Shirvaikar, M. (2006). Trends in automated visual inspection. Journal of Real-Time Image Processing, 1(1), 41–43
Copyright (c) 2023 José Rodrigo Hernández-Laguna, Jorge Adan Romero-Guerrero, Carolina Reta
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
