MONITOREO E INTERPRETACIÓN DE LA VARIACIÓN GENERADA EN PROCESOS MULTIVARIADOS A PARTIR DE LA INTEGRACIÓN DEL GRAFICO DE CONTROL MCUSUM Y RED NEURONAL PERCEPTRON MULTICAPA (MONITORING AND INTERPRETATION OF THE VARIATION GENERATED IN MULTIVARIATE PROCESSES FROM THE INTEGRATION OF MCUSUM CONTROL CHART AND MULTILAYER PERCEPTRON NEURAL NETWORK)
Resumen
La variabilidad que se encuentra dentro de los procesos de fabricación, origina muchos de los problemas de calidad que sufren las organizaciones manufactureras. En el caso de no ser monitoreada correctamente, aumenta las probabilidades de producir productos de baja calidad y, por consecuencia, aumentan los costos de producción. El objetivo del control estadístico de la calidad es poder detectar rápidamente la ocurrencia de causas asignables de variación en el proceso de fabricación e investigar las causas que la han generado para reducirlas o eliminarlas. En el artículo se presenta el desarrollo de una metodología que integra el grafico de control MCUSUM y la red neuronal artificial perceptrón multicapa para la detección e interpretación de las fuentes de variación que se generan en los sistemas productivos. De esta manera, la metodología permitirá localizar la(s) variable(s) que causa(n) el descontrol en el proceso, logrando emprender acciones correctivas que consigan reducirlas o eliminarlas en la fabricación de productos fuera de especificación de forma oportuna. La metodología propuesta fue implementada en un proceso de fabricación de placas de circuito impreso y se logra clasificar el origen de la variación generada en el sistema productivo con una exactitud promedio del 96.71%.
Palabras clave: red neuronal artificial, Control estadístico multivariado, Grafico de control multivariado, MCUSUM, Red neuronal artificial.
Abstract
(The variability found within manufacturing processes causes many of the quality problems experienced by manufacturing organizations. If not properly monitored, it increases the probability of producing low quality products and, consequently, increases production costs. The objective of statistical quality control is to be able to quickly detect the occurrence of assignable causes of variation in the manufacturing process and to investigate the causes that have generated it in order to reduce or eliminate them. This article presents the development of a methodology that integrates the MCUSUM control chart and the multilayer perceptron artificial neural network for the detection and interpretation of the sources of variation generated in production systems. In this way, the methodology will allow locating the variable(s) that cause(s) the lack of control in the process, being able to take corrective actions to reduce or eliminate them in the manufacture of products out of specification in a timely manner. The proposed methodology was implemented in a printed circuit board manufacturing process and it was possible to classify the origin of the variation generated in the production system with an average accuracy of 96.71%).
Keywords: Artificial neural network, Multivariate statistical control, Multivariate control chart, MCUSUM, Multivariate control chart.
Texto completo:
426-445 PDFReferencias
Aguado, D., Ferrer, A., Ferrer, J., & Seco, A. (2007). Multivariate SPC of a sequencing batch reactor for wastewater treatment. Chemometrics And Intelligent Laboratory Systems, 85(1), 82-93. https://doi.org/10.1016/j.chemolab.2006.05.003.
Ahsan, M., Mashuri, M., Khusna, H., & Wibawati, N. (2022). Kernel principal component analysis (PCA) control chart for monitoring mixed non-linear variable and attribute quality characteristics. Heliyon, 8(6), e09590. https://doi.org/10.1016/j.heliyon.2022.e09590.
Anojahatlo, K., & Sabri-Laghaie, K. (2022). Enhancing the detection power of multivariate time between events control charts for Gumbel’s bivariate exponential distribution. Computers & Industrial Engineering, 171, 108215. https://doi.org/10.1016/j.cie.2022.108215.
Bays, H. E., Fitch, A., Cuda, S., Gonsahn-Bollie, S., Rickey, E., Hablutzel, J., Coy, R., & Censani, M. (2023). Artificial intelligence and obesity management: An Obesity Medicine Association (OMA) Clinical Practice Statement (CPS) 2023. Obesity Pillars, 6, 100065 https://doi.org/10.1016/j.obpill.2023.100065.
Calabrò, A., Marchetti, E., PawełSkrzypek, N., & Marchel, J. (2025). CONCERN: A model-based monitoring infrastructure. Internet Of Things, 101557. https://doi.org/10.1016/j.iot.2025.101557.
Chen, J., Shao, Z., Zhu, H., Chen, Y., Li, Y., Zeng, Z., Yang, Y., Wu, J., & Hu, B. (2023). Sustainable interior design: A new approach to intelligent design and automated manufacturing based on Grasshopper. Computers & Industrial Engineering, 183, 109509. https://doi.org/10.1016/j.cie.2023.109509.
Clark, C. A., Behrendt, M. G., Long, T., & Dauer, J. T. (2025). Neural responses to errors in models and their relevance for longer term learning among undergraduate life sciences students. Trends In Neuroscience And Education, 100253. https://doi.org/10.1016/j.tine.2025.100253.
Daniel, V. A. A., Vijayalakshmi, K., Pawar, P. P., Kumar, D., Bhuvanesh, A., & Christilda, A. J. (2024). Enhanced affinity propagation clustering with a modified extreme learning machine for segmentation and classification of hyperspectral imaging. e-Prime - Advances In Electrical Engineering Electronics And Energy, 9, 100704. https://doi.org/10.1016/j.prime.2024.100704.
De Almeida Moreira, B. R., Cruz, V. H., Cunha, M. L. O., & Da Silva Viana, R. (2021). Full-scale production of high-quality wood pellets assisted by multivariate statistical process control. Biomass And Bioenergy, 151, 106159. https://doi.org/10.1016/j.biombioe.2021.106159.
De Lima, S. M., Silva, B. F. A., Pontes, D. V., Pereira, C. F., Stragevitch, L., & Pimentel, M. F. (2013). In-line monitoring of the transesterification reactions for biodiesel production using NIR spectroscopy. Fuel, 115, 46-53. https://doi.org/10.1016/j.fuel.2013.06.057.
Dittrich, I., Gertz, M., Maassen-Francke, B., Krudewig, K., Junge, W., & Krieter, J. (2022). Estimating risk probabilities for sickness from behavioural patterns to identify health challenges in dairy cows with multivariate cumulative sum control charts. Animal, 16(8), 100601. https://doi.org/10.1016/j.animal.2022.100601.
Dutoit, C., Dehombreux, P., Lorphèvre, E. R., & Equeter, L. (2019). Statistical Process Control and Maintenance Policies for Continuous Production Systems Subjected to Different Failure Impact Models: Literature Review. Procedia CIRP, 86, 55-60. https://doi.org/10.1016/j.procir.2020.01.050.
Hoga, Y. (2016). Monitoring multivariate time series. Journal Of Multivariate Analysis, 155, 105-121. https://doi.org/10.1016/j.jmva.2016.12.003.
Hu, W., Jiao, Q., Liu, H., Wang, K., Jiang, Z., Wu, J., Cong, F., & Hao, G. (2024). A transferable diagnosis method with incipient fault detection for a digital twin of wind turbine. Digital Engineering., 1, 100001. https://doi.org/10.1016/j.dte.2024.100001.
Issam, B. K., & Mohamed, L. (2008). Support vector regression based residual MCUSUM control chart for autocorrelated process. Applied Mathematics And Computation, 201(1-2), 565-574. https://doi.org/10.1016/j.amc.2007.12.059.
Jayasinghe, S., Mahmoodian, M., Alavi, A., Sidiq, A., Shahrivar, F., Sun, Z., Thangarajah, J., & Setunge, S. (2025). A review on the applications of artificial neural network techniques for accelerating finite element analysis in the civil engineering domain. Computers & Structures, 310, 107698. https://doi.org/10.1016/j.compstruc.2025.107698.
Knoth, S., & Schmid, W. (2021). Frontiers in Statistical Quality Control 13. En Springer eBooks. https://doi.org/10.1007/978-3-030-67856-2.
Kong, D., Hu, X., Zhang, J., Liu, X., & Zhang, D. (2024). Design of intelligent inspection system for solder paste printing defects based on improved YOLOX. iScience, 27(3), 109147. https://doi.org/10.1016/j.isci.2024.109147.
Lin, T., McLachlan, G. J., & Lee, S. X. (2015). Extending mixtures of factor models using the restricted multivariate skew-normal distribution. Journal Of Multivariate Analysis, 143, 398-413. https://doi.org/10.1016/j.jmva.2015.09.025.
Lokuge, S., Sedera, D., Grover, V., & Sarker, S. (s. f.). Orchestrating Digital Technologies with Incumbent Enterprise Systems for Attaining Innovation. Information & Management, 104066. https://doi.org/10.1016/j.im.2024.104066.
Majout, B., Bossoufi, B., Karim, M., Skruch, P., Mobayen, S., Mourabit, Y. E., & Laggoun, Z. E. Z. (2024). Artificial neural network-based direct power control to enhance the performance of a PMSG-wind energy conversion system under real wind speed and parameter uncertainties: An experimental validation. Energy Reports, 11, 4356-4378. https://doi.org/10.1016/j.egyr.2024.03.039.
Melanie, S., Benedikt, K., Pfaffl, M. W., & Irmgard, R. (2015). The potential of circulating extracellular small RNAs (smexRNA) in veterinary diagnostics—Identifying biomarker signatures by multivariate data analysis. Biomolecular Detection And Quantification, 5, 15-22. https://doi.org/10.1016/j.bdq.2015.08.001.
Miekley, B., Stamer, E., Traulsen, I., & Krieter, J. (2013). Implementation of multivariate cumulative sum control charts in mastitis and lameness monitoring. Journal Of Dairy Science, 96(9), 5723-5733. https://doi.org/10.3168/jds.2012-6460.
Monaco, S., Apiletti, D., Francica, A., & Cerquitelli, T. (2025). Quantify production planning efficiency through predictive modeling in manufacturing systems. Computers & Industrial Engineering, 110919. https://doi.org/10.1016/j.cie.2025.110919.
Montgomery, D. C. (2012b). Statistical quality control. John Wiley & Sons.
Oakland, J. S. (2008b). Statistical process control. Routledge. Butterworth-Heinemann.
Raj, J. J. R., Rahman, S., & Anand, S. (2016). 8051 microcontroller to FPGA and ADC interface design for high speed parallel processing systems – Application in ultrasound scanners. Engineering Science And Technology An International Journal, 19(3), 1416-1423. https://doi.org/10.1016/j.jestch.2016.04.004.
Richter, L., Lehna, M., Marchand, S., Scholz, C., Dreher, A., Klaiber, S., & Lenk, S. (2022). Artificial Intelligence for Electricity Supply Chain automation. Renewable And Sustainable Energy Reviews, 163, 112459. https://doi.org/10.1016/j.rser.2022.112459.
Wang, J., Deng, Y., Zhang, Z., Jin, J., & Liu, P. (2025). Thermal Stress Behavior and Optimization of Solder Joints in CSP-LED Packages. Results In Engineering, 104712. https://doi.org/10.1016/j.rineng.2025.104712.
Xu, Y., Chi, M., Lee, C., Chong, H., & Skitmore, M. (2025). Effect of blockchain and inter-organizational trust on collaboration between contractors and supply chain partners. Ain Shams Engineering Journal, 16(6), 103396. https://doi.org/10.1016/j.asej.2025.103396.
Yao, W., Li, D., & Gao, L. (2022). Fault detection and diagnosis using tree-based ensemble learning methods and multivariate control charts for centrifugal chillers. Journal Of Building Engineering, 51, 104243. https://doi.org/10.1016/j.jobe.2022.104243.
Zippelius, A., Hanß, A., Schmid, M., Pérez-Velázquez, J., & Elger, G. (2022). Reliability analysis and condition monitoring of SAC+ solder joints under high thermomechanical stress conditions using neuronal networks. Microelectronics Reliability, 129, 114461. https://doi.org/10.1016/j.microrel.2021.114461.
URL de la licencia: https://creativecommons.org/licenses/by/3.0/deed.es
Pistas Educativas está bajo la Licencia Creative Commons Atribución 3.0 No portada. 
TECNOLÓGICO NACIONAL DE MÉXICO / INSTITUTO TECNOLÓGICO DE CELAYA
Antonio García Cubas Pte #600 esq. Av. Tecnológico, Celaya, Gto. México
Tel. 461 61 17575 Ext 5450 y 5146
pistaseducativas@itcelaya.edu.mx