Estudio de técnicas de Inteligencia Artificial para el Mantenimiento Predictivo en Sistemas de Control Industrial

Vista sencilla de ítem
dc.contributor.advisorPimentel Díaz, Carlos Daniel
dc.contributor.authorBecerra Bayona, Carlos Felipe
dc.contributor.corporatenameUniversidad Santo Tomas
dc.date.accessioned2026-06-22T21:44:58Z
dc.date.available2026-06-22T21:44:58Z
dc.date.issued2026-06-22
dc.descriptionEl mantenimiento predictivo ha adquirido gran relevancia en la industria debido a la necesidad de mejorar la confiabilidad operativa y reducir fallas en sistemas industriales. En este contexto, la presente monografía analiza la implementación de técnicas de Inteligencia Artificial (IA) aplicadas al mantenimiento predictivo en diferentes sectores industriales, mediante un estudio de mapeo sistemático y análisis bibliométrico de literatura científica publicada en los últimos años. La metodología empleada incluyó la revisión de artículos indexados en bases de datos académicas especializadas y el análisis de tendencias mediante la herramienta VOSviewer, permitiendo identificar áreas de investigación, técnicas implementadas y sectores con mayor desarrollo tecnológico. Los resultados evidencian una amplia aplicación de herramientas como aprendizaje automático, redes neuronales artificiales y aprendizaje profundo en sectores manufactureros, energéticos y automatizados, principalmente para detección temprana de fallas, monitoreo de condición y optimización del mantenimiento. Asimismo, se identificaron desafíos relacionados con calidad de datos, escalabilidad, costos de implementación y acceso tecnológico. Finalmente, el estudio destaca el papel de la IA como elemento estratégico en la transformación digital y evolución del mantenimiento industrial.
dc.description.abstractPredictive maintenance has gained significant relevance in industry due to the need to improve operational reliability and reduce failures in industrial systems. In this context, this monograph analyzes the implementation of Artificial Intelligence (AI) techniques applied to predictive maintenance across different industrial sectors through a systematic mapping study and bibliometric analysis of scientific literature published in recent years. The adopted methodology included the review of indexed articles from specialized academic databases and trend analysis using the VOSviewer tool, allowing the identification of research areas, implemented techniques, and sectors with the highest technological development. The results reveal a wide application of tools such as machine learning, artificial neural networks, and deep learning in manufacturing, energy, and automated sectors, mainly for early fault detection, condition monitoring, and maintenance optimization. Additionally, challenges related to data quality, scalability, implementation costs, and technological accessibility were identified. Finally, the study highlights the role of AI as a strategic element in the digital transformation and evolution of industrial maintenance.
dc.description.degreelevelEspecializaciónspa
dc.description.degreenameEspecialista en Automatización Industrialspa
dc.description.domainhttps://www.ustabuca.edu.co/
dc.format.mimetypeapplication/pdf
dc.identifier.citationBecerra Bayona , C. F. (2026) Estudio de técnicas de Inteligencia Artificial para el Mantenimiento Predictivo en Sistemas de Control Industrial [Tesis de posgrado] Universidad Santo Tomás, bucaramanga, Colombia
dc.identifier.instnameinstname:Universidad Santo Tomásspa
dc.identifier.reponamereponame:Repositorio Institucional Universidad Santo Tomásspa
dc.identifier.repourlrepourl:https://repository.usta.edu.cospa
dc.identifier.urihttp://hdl.handle.net/11634/72763
dc.language.isospa
dc.publisherUniversidad Santo Tomásspa
dc.publisher.branchCRAI-USTA Bucaramanga
dc.publisher.facultyFacultad de Ingeniería Mecatrónicaspa
dc.publisher.programEspecialización Automatización Industrialspa
dc.relation.referencesR. K. Mobley, An Introduction to Predictive Maintenance, 2nd ed. Burlington, USA: Butterworth-Heinemann, 2002.
dc.relation.referencesT. P. Carvalho, F. A. A. M. N. Soares, R. Vita, R. P. Francisco, J. P. Basto, and S. G. S. Alcalá, “A systematic literature review of machine learning methods applied to predictive maintenance,” Computers & Industrial Engineering, vol. 137, p. 106024, 2019.
dc.relation.referencesB. Kitchenham and S. Charters, Guidelines for Performing Systematic Literature Reviews in Software Engineering. Keele University, 2007.
dc.relation.referencesB. Kitchenham and S. Charters, Guidelines for Performing Systematic Literature Reviews in Software Engineering. Keele University, 2007.
dc.relation.referencesJ. Van Eck and L. Waltman, “Software survey: VOSviewer, a computer program for bibliometric mapping,” Scientometrics, vol. 84, no. 2, pp. 523–538, 2010.
dc.relation.referencesJ. Lee, B. Bagheri, and H. A. Kao, “A cyber-physical systems architecture industry 4.0-based manufacturing systems,” Manufacturing Letters, vol. 3, pp. 18–23, 2015.
dc.relation.referencesY. Peng, M. Dong, and M. J. Zuo, “Current status of machine prognostics in condition-based maintenance: A review,” The International Journal of Advanced Manufacturing Technology, vol. 50, pp. 297–313, 2010.
dc.relation.referencesA. K. S. Jardine, D. Lin, and D. Banjevic, “A review on machinery diagnostics and prognostics implementing condition-based maintenance,” Mechanical Systems and Signal Processing, vol. 20, no. 7, pp. 1483–1510, 2006.
dc.relation.referencesY. Lei, N. Li, L. Guo, N. Li, T. Yan, and J. Lin, “Machinery health prognostics: A systematic review from data acquisition to RUL prediction,” Mechanical Systems and Signal Processing, vol. 104, pp. 799–834, 2018.
dc.relation.referencesS. Yin and O. Kaynak, “Big data for modern industry: Challenges and trends,” Proceedings of the IEEE, vol. 103, no. 2, pp. 143–146, 2015.
dc.relation.referencesA. Ahmed, K. Mahmood, and M. Islam, “A survey of anomaly detection techniques in smart healthcare systems,” Artificial Intelligence Review, vol. 54, no. 3, pp. 2331–2375, 2021.
dc.relation.referencesZ. Chen, C. Li, and R. Sánchez, “Gearbox fault identification and classification with convolutional neural networks,” Shock and Vibration, vol. 2015, pp. 1–10, 2015.
dc.relation.referencesE. Alpaydin, Introduction to Machine Learning, 4th ed. Cambridge, USA: MIT Press, 2021.
dc.relation.referencesS. Samek, G. Montavon, A. Vedaldi, L. Hansen, and K. Müller, Explainable AI: Interpreting, Explaining and Visualizing Deep Learning. Cham, Switzerland: Springer, 2019.
dc.relation.referencesL. Da Xu, E. L. Xu, and L. Li, “Industry 4.0: State of the art and future trends,” International Journal of Production Research, vol. 56, no. 8, pp. 2941–2962, 2018.
dc.relation.referencesK. Wang, Y. Wang, Y. Sun, S. Guo, and J. Wu, “Green industrial Internet of Things architecture: An energy-efficient perspective,” IEEE Communications Magazine, vol. 54, no. 12, pp. 48–54, 2016.
dc.relation.referencesY. Qin, C. Wang, and X. Zhang, “Wind turbine fault diagnosis using artificial neural networks and vibration analysis,” Renewable Energy, vol. 116, pp. 1–8, 2018.
dc.relation.referencesD. Yang, H. Wang, and Y. Zhang, “Deep learning-based fault diagnosis for photovoltaic systems using thermal imaging,” Energy Reports, vol. 6, pp. 123–130, 2020.
dc.relation.referencesM. A. Alao, A. A. Ayodele, and O. O. Ajayi, “Predictive maintenance of centrifugal pumps using machine learning techniques,” Journal of Petroleum Science and Engineering, vol. 196, p. 107731, 2021.
dc.relation.referencesH. Shaban, M. El-Hawary, and A. Kamel, “Deep learning-based gas pipeline leak detection using acoustic emission signals,” Engineering Applications of Artificial Intelligence, vol. 95, p. 103912, 2020.
dc.relation.referencesM. Mohammadi, S. Rashidi, and H. Ahmadi, “IoT-enabled predictive maintenance for offshore compressor systems using artificial intelligence,” Sensors, vol. 22, no. 4, pp. 1–18, 2022.
dc.relation.referencesA. Kusiak and A. Verma, “A data-driven approach for monitoring blade pitch faults in wind turbines,” IEEE Transactions on Sustainable Energy, vol. 2, no. 1, pp. 87–96, 2011.
dc.relation.referencesY. Zhang, H. Wang, and X. Chen, “Deep learning-based conveyor belt fault diagnosis using thermal imaging in mining environments,” Mechanical Systems and Signal Processing, vol. 152, p. 107398, 2021.
dc.relation.referencesZ. Ristovski, M. Franjic, and D. Gulan, “IoT-based predictive maintenance in mining machinery using machine learning techniques,” Mining Engineering, vol. 73, no. 5, pp. 42–49, 2021.
dc.relation.referencesJ. Kim, S. Lee, and H. Park, “Machine learning-based predictive maintenance for hospital HVAC systems,” Energy and Buildings, vol. 215, p. 109899, 2020.
dc.relation.referencesS. Ahmed, M. Khan, and R. Hussain, “Artificial neural network approach for predictive maintenance of UPS systems in healthcare facilities,” IEEE Access, vol. 9, pp. 45612–45624, 2021.
dc.relation.referencesA. Bousdekis, D. Apostolou, and G. Mentzas, “A proactive decision making framework for condition-based maintenance using IoT and predictive analytics,” International Journal of Production Research, vol. 58, no. 13, pp. 3891–3903, 2020.
dc.relation.referencesR. Zhao, R. Yan, Z. Chen, K. Mao, P. Wang, and R. X. Gao, “Deep learning and its applications to machine health monitoring,” Mechanical Systems and Signal Processing, vol. 115, pp. 213–237, 2019.
dc.relation.referencesK. Liu, Y. Shang, Q. Ouyang, and W. Widanage, “A data-driven approach with uncertainty quantification for predicting future capacities and remaining useful life of lithium-ion battery,” IEEE Transactions on Industrial Electronics, vol. 68, no. 4, pp. 3170–3180, 2021.
dc.relation.referencesA. Sharma, G. Singh, and R. Kumar, “IoT-enabled predictive maintenance framework for intelligent fleet management,” IEEE Internet of Things Journal, vol. 8, no. 18, pp. 14145–14156, 2021.
dc.rights.accessrightsinfo:eu-repo/semantics/openAccess
dc.rights.coarhttp://purl.org/coar/access_right/c_abf2
dc.rights.localAbierto (Texto Completo)spa
dc.subject.keywordArtificial Intelligence
dc.subject.keywordPredictive Maintenance
dc.subject.keywordMachine Learning
dc.subject.keywordFuzzy Logic
dc.subject.keywordIndustry 4.0
dc.subject.keywordCondition Monitoring
dc.subject.keywordInternet of Things (IoT)
dc.subject.keywordData Analysis
dc.subject.keywordIndustrial Automation
dc.subject.proposalInteligencia Artificial
dc.subject.proposalMantenimiento Predictivo
dc.subject.proposalMachine Learning
dc.subject.proposalLógica Difusa
dc.subject.proposalIndustria 4.0
dc.subject.proposalMonitoreo de Condición
dc.subject.proposalInternet de las Cosas (IoT)
dc.subject.proposalAnálisis de datos
dc.subject.proposalAutomatización industrial
dc.titleEstudio de técnicas de Inteligencia Artificial para el Mantenimiento Predictivo en Sistemas de Control Industrial
dc.typebachelor thesis
dc.type.categoryFormación de Recurso Humano para la Ctel: Trabajo de grado de Especialización
dc.type.coarhttp://purl.org/coar/resource_type/c_7a1f
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aa
dc.type.driveinfo:eu-repo/semantics/bachelorThesis
dc.type.localTesis de especializaciónspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersion

Archivos

Bloque original

Mostrando 1 - 3 de 3
Miniatura
Nombre:
2026BecerraCarlos.pdf
Tamaño:
330.58 KB
Formato:
Adobe Portable Document Format
Descripción:
Trabajo de grado
Descargar
Miniatura
Nombre:
2026BecerraCarlos1.pdf
Tamaño:
134.83 KB
Formato:
Adobe Portable Document Format
Descripción:
Carta de facultad
Descargar
Miniatura
Nombre:
2026BecerraCarlos2.pdf
Tamaño:
151.04 KB
Formato:
Adobe Portable Document Format
Descripción:
Acuerdo de publicación
Descargar

Bloque de licencias

Mostrando 1 - 1 de 1
Miniatura
Nombre:
license.txt
Tamaño:
807 B
Formato:
Item-specific license agreed upon to submission
Descripción:
Descargar

Colecciones

Especialización Automatización Industrial