Logo_Icesi
 

INRAE - Inteligencia artificial explicativa soft sensor

dc.audienceTodo Público
dc.contributor.advisorCorrales Muñoz, David Camilo
dc.contributor.authorCabrera Lozano, Alvaro José
dc.contributor.authorAragón, C.
dc.coverage.spatialCali de Lat: 03 24 00 N degrees minutes Lat: 3.4000 decimal degrees Long: 076 30 00 W degrees minutes Long: -76.5000 decimal degrees.
dc.date.accessioned2026-03-05T15:43:31Z
dc.date.available2026-03-05T15:43:31Z
dc.date.issued2025-06-27
dc.description.abstractEste trabajo presenta el desarrollo de un sensor blando aplicado al proceso de fermentación industrial, combinando modelos de aprendizaje automático de caja negra con técnicas de inteligencia artificial explicable (XAI). El objetivo del proyecto es diseñar un sistema predictivo capaz de estimar la concentración de penicilina a partir de datos históricos del proceso, mediante el uso de redes neuronales recurrentes (LSTM). Estos modelos, si bien precisos, presentan dificultades de interpretación debido a su naturaleza opaca. Para abordar este desafío, se integran técnicas XAI para visualizar y comprender la influencia de las variables más relevantes, transformando los modelos en herramientas más transparentes y confiables. La metodología incluye el uso del conjunto de datos IndPenSim, que simula condiciones normales y de falla en un entorno de fermentación a escala industrial. Además, se construye un prototipo de visualización para facilitar la interpretación de las predicciones y fortalecer la toma de decisiones basada en datos. El proyecto responde a la necesidad de lograr un equilibrio entre precisión y explicabilidad, dos pilares esenciales en la industria 4.0.spa
dc.description.abstractThis work presents the development of a soft sensor applied to the industrial fermentation process, combining black-box machine learning models with explainable artificial intelligence (XAI) techniques. The project's objective is to design a predictive system capable of estimating penicillin concentration from historical process data, through the use of recurrent neural networks (LSTM). These models, although accurate, present interpretation difficulties due to their opaque nature. To address this challenge, XAI techniques are integrated to visualize and understand the influence of the most relevant variables, transforming the models into more transparent and reliable tools. The methodology includes the use of the IndPenSim dataset, which simulates normal and fault conditions in an industrial-scale fermentation environment. Additionally, a visualization prototype is built to facilitate the interpretation of predictions and strengthen data-driven decision-making. The project responds to the need to achieve a balance between accuracy and explainability, two essential pillars in industry 4.0.eng
dc.description.degreelevelMagíster
dc.description.degreenameTrabajo de grado para optar al título de Magister en Ciencia de Datos
dc.description.tableofcontentsINRAE - Inteligencia Artificial Explicativa Soft Sensor -- Resumen -- Índice de Términos -- Introducción -- Contexto del Proyecto -- Objetivos -- Objetivo General -- Objetivo Específico -- Explicación del problema o tema en cuestión -- Justificación del proyecto -- Estado del arte -- Materiales y Métodos -- Marco Teórico -- Discusión -- Conclusiones -- Reconocimiento -- Referenciasspa
dc.format.extent38 páginas
dc.format.mediumDigital
dc.format.mimetypeapplication/pdf
dc.identifier.OLIBhttps://biblioteca2.icesi.edu.co/cgi-olib/?oid=366452
dc.identifier.instnameinstname:Universidad Icesi
dc.identifier.reponamereponame:Biblioteca Digital
dc.identifier.repourlrepourl:https://repository.icesi.edu.co/
dc.identifier.urihttps://hdl.handle.net/10906/130577
dc.language.isospa
dc.publisherUniversidad Icesi
dc.publisher.facultyBarberi de Ingeniería, Diseño y Ciencias Aplicadas
dc.publisher.placeSantiago de Cali
dc.publisher.programMaestría en Ciencia de Datos
dc.relation.referencesSilva, M. R., & González, P. (2024). Machine learning operations (MLOps) for real-time monitoring of penicillin fermentation. Journal of Process Control , 120(2), 350–365. https://www.sciencedirect.com/science/article/abs/pii/S0098135424004095spa
dc.relation.referencesZhang, Y., & Li, H. (2024). Improved soft sensor model for predicting cell concentration in Pichia pastoris fermentation. Sensors , 24(10), 3017. https://www.mdpi.com/1424-8220/24/10/3017spa
dc.relation.referencesThompson, R., & Wang, L. (2023). Challenges in developing soft sensors for bioprocesses: A data science perspective. Biotechnology Advances , 41(3), 290–315. https://pmc.ncbi.nlm.nih.gov/articles/PMC8417948spa
dc.relation.referencesKim, J., & Park, S. (2020). Modern soft sensor modeling methods for fermentation processes. Sensors , 20(6), 1771. https://www.mdpi.com/1424-8220/20/6/17spa
dc.relation.referencesEuropean Commission. (2020). Sensors and software to monitor fermentation in real-time. CORDIS . https://cordis.europa.eu/article/id/88462-sensors-and-software-to-monitor-fermentation-realtime/esspa
dc.relation.referencesJ. Wang, “Fundamentals of erbium-doped fiber amplifiers arrays (Periodical style—Submitted for publication),” IEEE J. Quantum Electron. , submitted for publication.spa
dc.relation.referencesC. J. Kaufman, Rocky Mountain Research Lab., Boulder, CO, private communication, May 1995.spa
dc.relation.referencesY. Yorozu, M. Hirano, K. Oka, and Y. Tagawa, “Electron spectroscopy studies on magneto-optical media and plastic substrate interfaces(Translation Journals style),” IEEE Transl. J. Magn.Jpn. , vol. 2, Aug. 1987, pp. 740–741 [ Dig. 9 th Annu. Conf. Magnetics Japan, 1982, p. 301].spa
dc.relation.referencesM. Young, The Techincal Writers Handbook. Mill Valley, CA: University Science, 1989.spa
dc.relation.referencesJ. U. Duncombe, “Infrared navigation—Part I: An assessment of feasibility (Periodical style),” IEEE Trans. Electron Devices , vol. ED-11, pp. 34–39, Jan. 1959.spa
dc.relation.referencesS. Chen, B. Mulgrew, and P. M. Grant, “A clustering technique for digital communications channel equalization using radial basis function networks,” IEEE Trans. Neural Networks , vol. 4, pp. 570–578, July 1993.spa
dc.relation.referencesR. W. Lucky, “Automatic equalization for digital communication,” Bell Syst. Tech. J. , vol. 44, no. 4, pp. 547–588, Apr. 1965.spa
dc.relation.referencesS. P. Bingulac, “On the compatibility of adaptive controllers (Published Conference Proceedings style),” in Proc. 4th Annu. Allerton Conf. Circuits and Systems Theory , New York, 1994, pp. 8–16.spa
dc.relation.referencesG. R. Faulhaber, “Design of service systems with priority reservation,” in Conf. Rec. 1995 IEEE Int. Conf. Communications, pp. 3– 8.spa
dc.relation.referencesW. D. Doyle, “Magnetization reversal in films with biaxial anisotropy,” in 1987 Proc. INTERMAG Conf. , pp. 2.2-1–2.2-6.spa
dc.relation.referencesG. W. Juette and L. E. Zeffanella, “Radio noise currents n short sections on bundle conductors (Presented Conference Paper style),” presented at the IEEE Summer power Meeting, Dallas, TX, June 22–27, 1990, Paper 90 SM 690-0 PWRS.spa
dc.relation.referencesJ. G. Kreifeldt, “An analysis of surface-detected EMG as an amplitude-modulated noise,” presented at the 1989 Int. Conf. Medicine and Biological Engineering, Chicago, IL.spa
dc.relation.referencesJ. Williams, “Narrow-band analyzer (Thesis or Dissertation style),” Ph.D. dissertation, Dept. Elect. Eng., Harvard Univ., Cambridge, MA, 1993.spa
dc.relation.referencesN. Kawasaki, “Parametric study of thermal and chemical nonequilibrium nozzle flow,” M.S. thesis, Dept. Electron. Eng., Osaka Univ., Osaka, Japan, 1993.spa
dc.relation.referencesJ. P. Wilkinson, “Nonlinear resonant circuit devices (Patent style),” U.S. Patent 3 624 12, July 16, 1990.spa
dc.relation.referencesIEEE Criteria for Class IE Electric Systems (Standards style) , IEEE Standard 308, 1969.spa
dc.relation.referencesLetter Symbols for Quantities , ANSI Standard Y10.5-1968.spa
dc.relation.referencesR. E. Haskell and C. T. Case, “Transient signal propagation in lossless isotropic plasmas (Report style),” USAF Cambridge Res. Lab., Cambridge, MA Rep. ARCRL-66-234 (II), 1994, vol. 2.spa
dc.relation.referencesE. E. Reber, R. L. Michell, and C. J. Carter, “Oxygen absorption in the Earth’s atmosphere,” Aerospace Corp., Los Angeles, CA, Tech. Rep. TR-0200 (420-46)-3, Nov. 1988.spa
dc.relation.references(Handbook style) Transmission Systems for Communications, 3rd ed., Western Electric Co., Winston-Salem, NC, 1985, pp. 44–60.spa
dc.relation.referencesMotorola Semiconductor Data Manual, Motorola Semiconductor Products Inc., Phoenix, AZ, 1989.spa
dc.relation.references(Basic Book/Monograph Online Sources) J. K. Author. (year, month, day). Title (edition) [Type of medium]. Volume(issue). Available: http://www.(URL )spa
dc.relation.referencesJ. Jones. (1991, May 10). Networks (2nd ed.) [Online]. Available: http://www.atm.comspa
dc.relation.references(Journal Online Sources style) K. Author. (year, month). Title. Journal [Type of medium]. Volume(issue), paging if given. Available: http://www.(URL )spa
dc.relation.referencesR. J. Vidmar. (1992, August). On the use of atmospheric plasmas as electromagnetic reflectors. IEEE Trans. Plasma Sci. [Online]. 21(3). pp. 876—880. Available: http://www.halcyon.com/pub/journals/21ps03-vidmarspa
dc.relation.referencesMetcalfe, B., Silva, M. R., Corrales, D. C., et al. (2025). Explainable artificial intelligence for soft sensors in bioprocessing: A benchmark study. Computers and Chemical Engineering, 194, 108991.spa
dc.relation.referencesSilva, M. R., & González, P. (2025). Towards a machine learning operations (MLOps) soft sensor for real-time predictions in industrial-scale fed-batch fermentation. Journal of Process Control, 120(2), 350–365.spa
dc.relation.referencesCorrales, D. C., Metcalfe, B., Silva, M. R., & González, P. (2025). Detecting and interpreting concept drift in soft sensors for bioprocesses using statistical and spectral methods. Industrial & Engineering Chemistry Research, 64(7), 1190–1203.spa
dc.rightsEL AUTOR, expresa que la obra objeto de la presente autorización es original y la elaboró sin quebrantar ni suplantar los derechos de autor de terceros, y de tal forma, la obra es de su exclusiva autoría y tiene la titularidad sobre éste. PARÁGRAFO: en caso de queja o acción por parte de un tercero referente a los derechos de autor sobre el artículo, folleto o libro en cuestión, EL AUTOR, asumirá la responsabilidad total, y saldrá en defensa de los derechos aquí autorizados; para todos los efectos, la Universidad Icesi actúa como un tercero de buena fe. Esta autorización, permite a la Universidad Icesi, de forma indefinida, para que en los términos establecidos en la Ley 23 de 1982, la Ley 44 de 1993, leyes y jurisprudencia vigente al respecto, haga publicación de este con fines educativos.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.rights.coarhttp://purl.org/coar/access_right/c_abf2
dc.rights.licenseAttribution-NonCommercial-NoDerivatives 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject.proposalInteligencia artificialspa
dc.subject.proposalFermentaciónspa
dc.subject.proposalLSTMspa
dc.subject.proposalSensor blandospa
dc.subject.proposalArtificial Intelligenceeng
dc.subject.proposalFermentationeng
dc.subject.proposalLSTMeng
dc.subject.proposalSoft Sensoreng
dc.subject.proposalTesis de Maestría en Ciencia de Datosspa
dc.titleINRAE - Inteligencia artificial explicativa soft sensorspa
dc.typemaster thesis
dc.type.coarhttp://purl.org/coar/resource_type/c_bdcc
dc.type.coarversionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.driverinfo:eu-repo/semantics/masterThesis
dc.type.localTesis de maestría
dc.type.versioninfo:eu-repo/semantics/publishedVersion

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
T03090.pdf
Tamaño:
2.89 MB
Formato:
Adobe Portable Document Format

Bloque de licencias

Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
1.71 KB
Formato:
Item-specific license agreed upon to submission
Descripción: