REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS
El mantenimiento es una actividad inherente a la industria manufacturera, cuyo propósito es garantizar la operación continúa de los equipos. Actualmente, el mantenimiento correctivo o reactivo es el más común y se basa en la intervención tras la ocurrencia de una falla, lo que acarrea diversas conse...
- Autores:
-
Marín Vásquez, Mario Esteban
- Tipo de recurso:
- Trabajo de grado de pregrado
- Fecha de publicación:
- 2025
- Institución:
- Universidad Católica de Pereira
- Repositorio:
- Repositorio Institucional - RIBUC
- Idioma:
- spa
- OAI Identifier:
- oai:repositorio.ucp.edu.co:10785/16837
- Acceso en línea:
- https://hdl.handle.net/10785/16837
https://repositorio.ucp.edu.co/home
- Palabra clave:
- 2. Ingeniería y Tecnología::2B. Ingenierías Eléctrica, Electrónica e Informática::2B04. Ingeniería de sistemas y comunicaciones
Algoritmos de inteligencia artificial
Detección de anomalías
Análisis de anomalías
Predicción de Fallas
Clasificación de Fallas
Artificial Intelligence Algorithms
Anomaly Detection
Anomaly Analysis
Failure Prediction
Fault Classification
- Rights
- closedAccess
- License
- Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)
| id |
RepoRIBUC2_cb0df8d1ae7112cac3fac8ff43deacdd |
|---|---|
| oai_identifier_str |
oai:repositorio.ucp.edu.co:10785/16837 |
| network_acronym_str |
RepoRIBUC2 |
| network_name_str |
Repositorio Institucional - RIBUC |
| repository_id_str |
|
| dc.title.spa.fl_str_mv |
REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS |
| title |
REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS |
| spellingShingle |
REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS 2. Ingeniería y Tecnología::2B. Ingenierías Eléctrica, Electrónica e Informática::2B04. Ingeniería de sistemas y comunicaciones Algoritmos de inteligencia artificial Detección de anomalías Análisis de anomalías Predicción de Fallas Clasificación de Fallas Artificial Intelligence Algorithms Anomaly Detection Anomaly Analysis Failure Prediction Fault Classification |
| title_short |
REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS |
| title_full |
REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS |
| title_fullStr |
REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS |
| title_full_unstemmed |
REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS |
| title_sort |
REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS |
| dc.creator.fl_str_mv |
Marín Vásquez, Mario Esteban |
| dc.contributor.advisor.none.fl_str_mv |
Toro Lazo, Alonso Blandón Andrade, Juan Carlos |
| dc.contributor.author.none.fl_str_mv |
Marín Vásquez, Mario Esteban |
| dc.contributor.corporatename.none.fl_str_mv |
Universidad Católica de Pereira |
| dc.contributor.jury.none.fl_str_mv |
Cortés, Carlos Andrés |
| dc.contributor.none.fl_str_mv |
Blandón Andrade, Juan Carlos Toro Lazo, Alonso |
| dc.subject.ocde.none.fl_str_mv |
2. Ingeniería y Tecnología::2B. Ingenierías Eléctrica, Electrónica e Informática::2B04. Ingeniería de sistemas y comunicaciones |
| topic |
2. Ingeniería y Tecnología::2B. Ingenierías Eléctrica, Electrónica e Informática::2B04. Ingeniería de sistemas y comunicaciones Algoritmos de inteligencia artificial Detección de anomalías Análisis de anomalías Predicción de Fallas Clasificación de Fallas Artificial Intelligence Algorithms Anomaly Detection Anomaly Analysis Failure Prediction Fault Classification |
| dc.subject.proposal.spa.fl_str_mv |
Algoritmos de inteligencia artificial Detección de anomalías Análisis de anomalías Predicción de Fallas Clasificación de Fallas |
| dc.subject.proposal.eng.fl_str_mv |
Artificial Intelligence Algorithms Anomaly Detection Anomaly Analysis Failure Prediction Fault Classification |
| description |
El mantenimiento es una actividad inherente a la industria manufacturera, cuyo propósito es garantizar la operación continúa de los equipos. Actualmente, el mantenimiento correctivo o reactivo es el más común y se basa en la intervención tras la ocurrencia de una falla, lo que acarrea diversas consecuencias negativas. En respuesta, el Mantenimiento Predictivo (PdM) surge como una solución efectiva, al anticipar posibles fallas mediante el monitoreo constante de parámetros clave mediante la utilización de tecnologías avanzadas de la Industria 4.0, como el Internet de las Cosas y la Inteligencia Artificial. En este trabajo se propone una revisión sistemática de literatura, basada en el método de Kitchenham, para identificar los algoritmos IA y las plataformas de software más utilizadas para el análisis de anomalías, clasificación y predicción de fallas en equipos industriales. Se analizaron enfoques basados en IA, plataformas de software e IoT, además de tecnologías complementarias que fortalecen el PdM. |
| publishDate |
2025 |
| dc.date.accessioned.none.fl_str_mv |
2025-10-04T14:00:51Z |
| dc.date.available.none.fl_str_mv |
2025-10-04T14:00:51Z |
| dc.date.issued.none.fl_str_mv |
2025-05-30 |
| dc.type.none.fl_str_mv |
Trabajo de grado - Pregrado |
| dc.type.coar.none.fl_str_mv |
http://purl.org/coar/resource_type/c_7a1f |
| dc.type.coarversion.none.fl_str_mv |
http://purl.org/coar/version/c_970fb48d4fbd8a85 |
| dc.type.content.none.fl_str_mv |
Text |
| dc.type.driver.none.fl_str_mv |
info:eu-repo/semantics/bachelorThesis |
| dc.type.redcol.none.fl_str_mv |
http://purl.org/redcol/resource_type/TP |
| dc.type.version.none.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
| format |
http://purl.org/coar/resource_type/c_7a1f |
| status_str |
publishedVersion |
| dc.identifier.citation.none.fl_str_mv |
Marín Vásquez, M. (2025). REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS. Universidad Católica de Pereira. Disponible en: https://hdl.handle.net/10785/16837 |
| dc.identifier.uri.none.fl_str_mv |
https://hdl.handle.net/10785/16837 |
| dc.identifier.instname.none.fl_str_mv |
Universidad Católica de Pereira |
| dc.identifier.repourl.none.fl_str_mv |
https://repositorio.ucp.edu.co/home |
| identifier_str_mv |
Marín Vásquez, M. (2025). REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS. Universidad Católica de Pereira. Disponible en: https://hdl.handle.net/10785/16837 Universidad Católica de Pereira |
| url |
https://hdl.handle.net/10785/16837 https://repositorio.ucp.edu.co/home |
| dc.language.iso.none.fl_str_mv |
spa |
| language |
spa |
| dc.relation.references.none.fl_str_mv |
B. Kitchenham, O. Pearl Brereton, D. Budgen, M. Turner, J. Bailey, and S. Linkman, “Systematic literature reviews in software engineering – A systematic literature review,” Inf. Softw. Technol., vol. 51, no. 1, Art. no. 1, Jan. 2009, doi: 10.1016/j.infsof.2008.09.009. A. Lazzaro, D. M. D’Addona, and M. Merenda, “A Detailed Study on Algorithms for Predictive Maintenance in Smart Manufacturing: Chip Form Classification Using Edge Machine Learning,” IEEE Open J. Ind. Electron. Soc., vol. 5, pp. 1190–1205, 2024, doi: 10.1109/OJIES.2024.3484006. M. Ragnoli et al., “A Condition and Fault Prevention Monitoring System for Industrial Computer Numerical Control Machinery,” IEEE ACCESS, vol. 12, pp. 20919–20930, 2024, doi: 10.1109/ACCESS.2024.3359424. B. Ghasemkhani, O. Aktas, and D. Birant, “Balanced K-Star: An Explainable Machine Learning Method for Internet-of-Things-Enabled Predictive Maintenance in Manufacturing,” Machines, vol. 11, no. 3, Art. no. 3, 2023, doi: 10.3390/machines11030322. S. Park, G.-J. Ahn, and D.-H. Im, “Auto Labeling Methods Developed Through Semi-Weakly Supervised Learning in Prognostics and Health Management Applications for Rolling Ball Bearing,” IEEE Sens. J., vol. 22, no. 16, Art. no. 16, Aug. 2022, doi: 10.1109/JSEN.2022.3188310. X. Zhang, K. P. Rane, I. Kakaravada, and M. Shabaz, “Research on vibration monitoring and fault diagnosis of rotating machinery based on internet of things technology,” NONLINEAR Eng. - Model. Appl., vol. 10, no. 1, Art. no. 1, Jan. 2021, doi: 10.1515/nleng-2021-0019. M. N. Ali, M. Amer, and M. Elsisi, “Reliable IoT Paradigm With Ensemble Machine Learning for Faults Diagnosis of Power Transformers Considering Adversarial Attacks,” IEEE Trans. Instrum. Meas., vol. 72, pp. 1–13, 2023, doi: 10.1109/TIM.2023.3300444. F. Jiang et al., “PHIR: A Platform Solution of Data-Driven Health Monitoring for Industrial Robots,” ELECTRONICS, vol. 13, no. 5, Art. no. 5, Mar. 2024, doi: 10.3390/electronics13050834. J.-H. Shin and H.-B. Jun, “On condition based maintenance policy,” J. Comput. Des. Eng., vol. 2, no. 2, Art. no. 2, Apr. 2015, doi: 10.1016/j.jcde.2014.12.006. L. P. Maguluri, D. Suganthi, G. M. Dhote, D. Kapila, M. M. Jadhav, and S. Neelima, “AI-enhanced predictive maintenance in hybrid roll-to-roll manufacturing integrating multi-sensor data and self-supervised learning,” Int. J. Adv. Manuf. Technol., Aug. 2024, doi: 10.1007/s00170-024-14263-7. L. Magadán, F. J. Suárez, J. C. Granda, F. J. delaCalle, and D. F. García, “A Robust Health Prognostics Technique for Failure Diagnosis and the Remaining Useful Lifetime Predictions of Bearings in Electric Motors,” Appl. Sci. Switz., vol. 13, no. 4, Art. no. 4, 2023, doi: 10.3390/app13042220. Z. A. Bukhsh and I. Stipanovic, “Predictive Maintenance for Infrastructure Asset Management,” IT Prof., vol. 22, no. 5, pp. 40–45, 2020, doi: 10.1109/MITP.2020.2975736. R. Rosati et al., “From knowledge-based to big data analytic model: a novel IoT and machine learning based decision support system for predictive maintenance in Industry 4.0,” J. Intell. Manuf., vol. 34, no. 1, Art. no. 1, Jan. 2023, doi: 10.1007/s10845-022-01960-x. J. C. B. Andrade, “Tendencias en ciencias de la computación,” Entre Cienc. E Ing., vol. 14, no. 27, pp. 19–28, Jul. 2020, doi: 10.31908/19098367.1740. Atkin and Adrian, Total Facilities Management. 2015. Mangano, “The role of maintenance and facility management in logistics: A literature review,” vol. 32. G. Nota, D. Peluso, and A. T. Lazo, “The contribution of Industry 4.0 technologies to facility management,” Int. J. Eng. Bus. Manag., vol. 13, p. 18479790211024131, Jan. 2021, doi: 10.1177/18479790211024131. Islam Helaly Abdel-Aziz Afefy, “Implementation of Total Productive Maintenance and Overall Equipment Effectiveness Evaluation,” Feb. 2013. Giancarlo Nota, Francesco David Nota, Domenico Peluso, and Alonso Toro Lazo, “Energy Efficiency in Industry 4.0: The Case of Batch Production Processes,” Aug. 17, 2020. Mounia Achouch, Mariya Dimitrova, Khaled Ziane, Sasan Sattarpanah Karganroudi, Rizck Dhouib, and Mehdi Adda, “On Predictive Maintenance in Industry 4.0: Overview, Models, and Challenges,” 12 de agosto de 2022, vol. 12. K. Kubiak, G. Dec, and D. Stadnicka, “Possible Applications of Edge Computing in the Manufacturing Industry—Systematic Literature Review,” Sensors, vol. 22, no. 7, Art. no. 7, Jan. 2022, doi: 10.3390/s22072445. J. Moradi, H. Shahinzadeh, H. Nafisi, M. Marzband, and G. B. Gharehpetian, “Attributes of Big Data Analytics for Data-Driven Decision Making in Cyber-Physical Power Systems,” in 2020 14th International Conference on Protection and Automation of Power Systems (IPAPS), Dec. 2019, pp. 83–92. doi: 10.1109/IPAPS49326.2019.9069391. L. Monostori, “Cyber-physical Production Systems: Roots, Expectations and R&D Challenges,” Procedia CIRP, vol. 17, pp. 9–13, Jan. 2014, doi: 10.1016/j.procir.2014.03.115. R. Saka, O. Chinagozi, and O. Joe, “Exploratory Research Design in Management Science: A Review of Literature on Conduct and Application,” Int. J. Res. Innov. Soc. Sci., vol. VII, pp. 1384–1395, May 2023, doi: 10.47772/IJRISS.2023.7515. T. Akyaz and D. Engın, “Machine Learning-Based Predictive Maintenance System for Artificial Yarn Machines,” IEEE Access, vol. 12, pp. 125446–125461, 2024, doi: 10.1109/ACCESS.2024.3454548. Q. Liu, J. Zhang, J. Liu, and Z. Yang, “Feature extraction and classification algorithm, which one is more essential? An experimental study on a specific task of vibration signal diagnosis,” Int. J. Mach. Learn. Cybern., vol. 13, no. 6, Art. no. 6, Jun. 2022, doi: 10.1007/s13042-021-01477-4. Z. Kazemi, F. Naseri, M. Yazdi, and E. Farjah, “An EKF-SVM machine learning-based approach for fault detection and classification in three-phase power transformers,” IET Sci. Meas. Technol., vol. 15, no. 2, Art. no. 2, Mar. 2021, doi: 10.1049/smt2.12015. A. Yan et al., “An Online Fault Detection and Remaining Life Prediction Method Based on SVDD for Rolling Bearings,” IEEE Trans. Instrum. Meas., vol. 73, pp. 1–12, 2024, doi: 10.1109/TIM.2024.3378268. N. M. Thoppil, V. Vasu, and C. S. P. Rao, “An Integrated Learning Algorithm for Vibration Feature Selection and Remaining Useful life Estimation of Lathe Spindle Unit,” J. Fail. Anal. Prev., vol. 22, no. 4, Art. no. 4, Aug. 2022, doi: 10.1007/s11668-022-01463-0. M.-Q. Tran, M. Elsisi, K. Mahmoud, M.-K. Liu, M. Lehtonen, and M. M. F. Darwish, “Experimental Setup for Online Fault Diagnosis of Induction Machines via Promising IoT and Machine Learning: Towards Industry 4.0 Empowerment,” IEEE ACCESS, vol. 9, pp. 115429–115441, 2021, doi: 10.1109/ACCESS.2021.3105297. B. Tasci, A. Omar, and S. Ayvaz, “Remaining useful lifetime prediction for predictive maintenance in manufacturing,” Comput. Ind. Eng., vol. 184, p. 109566, Oct. 2023, doi: 10.1016/j.cie.2023.109566. H. Xiao, W. Hu, G. Liu, and H. Zhou, “Edge computing-based unified condition monitoring system for process manufacturing,” Comput. Ind. Eng., vol. 177, 2023, doi: 10.1016/j.cie.2023.109032. X. Li and H. Zhao, “Performance Prediction of Rolling Bearing Using EEMD and WCDPSO-KELM Methods,” Appl. Sci.-BASEL, vol. 12, no. 9, Art. no. 9, May 2022, doi: 10.3390/app12094676. A. K. Verma, P. D. Raval, N. Rajagopalan, V. Khariya, and R. Sudha, “Development of an AI-based FSA for real-time condition monitoring for industrial machine,” Neural Comput. Appl., vol. 34, no. 11, Art. no. 11, 2022, doi: 10.1007/s00521-021-06741-w. R. Kizito, P. Scruggs, X. Li, M. Devinney, J. Jansen, and R. Kress, “Long Short-Term Memory Networks for Facility Infrastructure Failure and Remaining Useful Life Prediction,” IEEE Access, vol. 9, pp. 67585–67594, 2021, doi: 10.1109/ACCESS.2021.3077192. H. Chen, X. Wang, and Z.-X. Yang, “Fast Robust Capsule Network With Dynamic Pruning and Multiscale Mutual Information Maximization for Compound-Fault Diagnosis,” IEEEASME Trans. Mechatron., vol. 28, no. 2, Art. no. 2, Apr. 2023, doi: 10.1109/TMECH.2022.3214865. M.-Q. Tran et al., “Robust fault recognition and correction scheme for induction motors using an effective IoT with deep learning approach,” MEASUREMENT, vol. 207, p. 112398, Feb. 2023, doi: 10.1016/j.measurement.2022.112398. F. De Vita, D. Bruneo, and S. K. Das, “On the use of a full stack hardware/software infrastructure for sensor data fusion and fault prediction in industry 4.0,” PATTERN Recognit. Lett., vol. 138, pp. 30–37, Oct. 2020, doi: 10.1016/j.patrec.2020.06.028. Y. Niu et al., “A Sparse Learning Method with Regularization Parameter as a Self-Adaptation Strategy for Rolling Bearing Fault Diagnosis,” ELECTRONICS, vol. 12, no. 20, Art. no. 20, Oct. 2023, doi: 10.3390/electronics12204282. S. Liu, Z. Ji, Z. Zhang, and Y. Wang, “An Improved Deep Transfer Learning Method for Rotating Machinery Fault Diagnosis Based on Time Frequency Diagram and Pretraining Model,” IEEE Trans. Instrum. Meas., vol. 73, pp. 1–12, 2024, doi: 10.1109/TIM.2023.3345907. W. Mao, J. Chen, J. Liu, and X. Liang, “Self-Supervised Deep Domain-Adversarial Regression Adaptation for Online Remaining Useful Life Prediction of Rolling Bearing Under Unknown Working Condition,” IEEE Trans. Ind. Inform., vol. 19, no. 2, Art. no. 2, Feb. 2023, doi: 10.1109/TII.2022.3172704. X. Zhao, F. Shao, and Y. Zhang, “A Novel Joint Adversarial Domain Adaptation Method for Rotary Machine Fault Diagnosis under Different Working Conditions,” SENSORS, vol. 22, no. 22, Art. no. 22, Nov. 2022, doi: 10.3390/s22229007. Y. Cao, Q. Ni, M. Jia, X. Zhao, and X. Yan, “Online Knowledge Distillation for Machine Health Prognosis Considering Edge Deployment,” IEEE Internet Things J., vol. 11, no. 16, Art. no. 16, Aug. 2024, doi: 10.1109/JIOT.2024.3404112. O. Yotov and A. Aleksieva-Petrova, “Data-Driven Prediction Model for Analysis of Sensor Data,” Electron. Switz., vol. 13, no. 10, Art. no. 10, 2024, doi: 10.3390/electronics13101799. M. Han, Y. Wu, Y. Wang, and W. Liu, “Roller bearing fault diagnosis based on LMD and multi-scale symbolic dynamic information entropy,” J. Mech. Sci. Technol., vol. 35, no. 5, Art. no. 5, May 2021, doi: 10.1007/s12206-021-0417-3. H. A. Raja et al., “Signal Spectrum-Based Machine Learning Approach for Fault Prediction and Maintenance of Electrical Machines,” Energies, vol. 15, no. 24, Art. no. 24, 2022, doi: 10.3390/en15249507. M. Yousuf, T. Alsuwian, A. A. Amin, S. Fareed, and M. Hamza, “IoT-based health monitoring and fault detection of industrial AC induction motor for efficient predictive maintenance,” Meas. Control U. K., vol. 57, no. 8, Art. no. 8, 2024, doi: 10.1177/00202940241231473. |
| dc.rights.license.none.fl_str_mv |
Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0) |
| dc.rights.accessrights.none.fl_str_mv |
info:eu-repo/semantics/closedAccess |
| dc.rights.coar.none.fl_str_mv |
http://purl.org/coar/access_right/c_14cb |
| rights_invalid_str_mv |
Atribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0) http://purl.org/coar/access_right/c_14cb |
| eu_rights_str_mv |
closedAccess |
| dc.format.extent.none.fl_str_mv |
86 |
| dc.format.mimetype.none.fl_str_mv |
application/pdf |
| dc.publisher.none.fl_str_mv |
Universidad Católica de Pereira |
| dc.publisher.faculty.none.fl_str_mv |
Facultad de Ciencias Básicas e Ingeniería |
| dc.publisher.place.none.fl_str_mv |
Pereira |
| dc.publisher.program.none.fl_str_mv |
Ingeniería de Sistemas y Telecomunicaciones |
| publisher.none.fl_str_mv |
Universidad Católica de Pereira |
| institution |
Universidad Católica de Pereira |
| bitstream.url.fl_str_mv |
https://repositorio.ucp.edu.co/bitstreams/541b1648-ac55-42fa-a01d-627364322d8a/download https://repositorio.ucp.edu.co/bitstreams/5ca52d40-4ca3-422e-a19c-72dc19002420/download https://repositorio.ucp.edu.co/bitstreams/0f9a5052-7d3f-4206-b13b-2c213fc95d0e/download https://repositorio.ucp.edu.co/bitstreams/e35c944a-b27f-497c-b686-45c48236d32d/download |
| bitstream.checksum.fl_str_mv |
3e5100a681442ffd664e4e3aacdd4901 73a5432e0b76442b22b026844140d683 82f79b8b728c2d158ea5ec313347c302 6c0a59c2635c675f33727c180c898ba5 |
| bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 |
| repository.name.fl_str_mv |
Repositorio Institucional de la Universidad Católica de Pereira - RIBUC |
| repository.mail.fl_str_mv |
bdigital@metabiblioteca.com |
| _version_ |
1851054271932399616 |
| spelling |
Blandón Andrade, Juan CarlosToro Lazo, AlonsoToro Lazo, AlonsoBlandón Andrade, Juan Carlosvirtual::30-1Marín Vásquez, Mario EstebanUniversidad Católica de PereiraCortés, Carlos Andrés2025-10-04T14:00:51Z2025-10-04T14:00:51Z2025-05-30Marín Vásquez, M. (2025). REVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLAS. Universidad Católica de Pereira. Disponible en: https://hdl.handle.net/10785/16837https://hdl.handle.net/10785/16837Universidad Católica de Pereirahttps://repositorio.ucp.edu.co/homeEl mantenimiento es una actividad inherente a la industria manufacturera, cuyo propósito es garantizar la operación continúa de los equipos. Actualmente, el mantenimiento correctivo o reactivo es el más común y se basa en la intervención tras la ocurrencia de una falla, lo que acarrea diversas consecuencias negativas. En respuesta, el Mantenimiento Predictivo (PdM) surge como una solución efectiva, al anticipar posibles fallas mediante el monitoreo constante de parámetros clave mediante la utilización de tecnologías avanzadas de la Industria 4.0, como el Internet de las Cosas y la Inteligencia Artificial. En este trabajo se propone una revisión sistemática de literatura, basada en el método de Kitchenham, para identificar los algoritmos IA y las plataformas de software más utilizadas para el análisis de anomalías, clasificación y predicción de fallas en equipos industriales. Se analizaron enfoques basados en IA, plataformas de software e IoT, además de tecnologías complementarias que fortalecen el PdM.Maintenance is an inherent activity in the manufacturing industry, aimed at ensuring the continuous operation of equipment. Currently, corrective or reactive maintenance is the most common approach, based on intervention after a failure occurs, which leads to various negative consequences. In response, Predictive Maintenance (PdM) emerges as an effective solution by anticipating potential failures through constant monitoring of key parameters, enabled by advanced Industry 4.0 technologies such as the Internet of Things (IoT) and Artificial Intelligence (AI). This work proposes a systematic literature review, based on the Kitchenham method, to identify the most commonly used AI algorithms and software platforms for anomaly detection, fault classification and prediction in industrial equipment. The review analyzes AI-based approaches, software and IoT platforms, as well as complementary technologies that strengthen the implementation of PdM.RESUMEN 9 1. INTRODUCCIÓN 11 2. PLANTEAMIENTO DEL PROBLEMA 13 3. DELIMITACIÓN 15 4. JUSTIFICACIÓN 16 5. OBJETIVOS 18 5.1 OBJETIVO GENERAL 18 5.2 OBJETIVOS ESPECÍFICOS 18 6. MARCO TEÓRICO 19 6.1 Gestión de instalaciones 19 6.2 Mantenimiento 19 6.3 Mantenimiento Productivo Total 22 6.4 Tecnologías relacionadas 24 7. METODOLOGÍA 28 7.1 Cronograma 28 7.2 Presupuesto 29 8. DESARROLLO DEL PROYECTO 30 8.1 Preguntas de investigación 30 8.2 Proceso de búsqueda 31 8.3 Criterios de inclusión y exclusión 32 8.4 Evaluación de la calidad 33 8.5 Recopilación de datos 34 8.6 Análisis de datos 34 9. ANÁLISIS DE RESULTADOS 35 9.1 Preguntas de investigación 35 9.2 Proceso de búsqueda 35 9.3 Criterios de inclusión y exclusión 37 9.4 Evaluación de la calidad 38 9.5 Recopilación de datos 39 9.6 Análisis de datos 39 9.7 Discusión 57 10. CONCLUSIONES 77 11. RECOMENDACIONES 79 REFERENCIAS 80 ANEXOS 84PregradoIngeniero de Sistemas y Telecomunicaciones86application/pdfspaUniversidad Católica de PereiraFacultad de Ciencias Básicas e IngenieríaPereiraIngeniería de Sistemas y TelecomunicacionesREVISIÓN SISTEMÁTICA DE LITERATURA SOBRE ALGORITMOS IA Y PLATAFORMAS DE SOFTWARE PARA PREDICCIÓN DE FALLASTrabajo de grado - Pregradohttp://purl.org/coar/resource_type/c_7a1fhttp://purl.org/coar/version/c_970fb48d4fbd8a85Textinfo:eu-repo/semantics/bachelorThesishttp://purl.org/redcol/resource_type/TPinfo:eu-repo/semantics/publishedVersionAtribución-NoComercial-SinDerivadas 4.0 Internacional (CC BY-NC-ND 4.0)info:eu-repo/semantics/closedAccesshttp://purl.org/coar/access_right/c_14cbB. Kitchenham, O. Pearl Brereton, D. Budgen, M. Turner, J. Bailey, and S. Linkman, “Systematic literature reviews in software engineering – A systematic literature review,” Inf. Softw. Technol., vol. 51, no. 1, Art. no. 1, Jan. 2009, doi: 10.1016/j.infsof.2008.09.009.A. Lazzaro, D. M. D’Addona, and M. Merenda, “A Detailed Study on Algorithms for Predictive Maintenance in Smart Manufacturing: Chip Form Classification Using Edge Machine Learning,” IEEE Open J. Ind. Electron. Soc., vol. 5, pp. 1190–1205, 2024, doi: 10.1109/OJIES.2024.3484006.M. Ragnoli et al., “A Condition and Fault Prevention Monitoring System for Industrial Computer Numerical Control Machinery,” IEEE ACCESS, vol. 12, pp. 20919–20930, 2024, doi: 10.1109/ACCESS.2024.3359424.B. Ghasemkhani, O. Aktas, and D. Birant, “Balanced K-Star: An Explainable Machine Learning Method for Internet-of-Things-Enabled Predictive Maintenance in Manufacturing,” Machines, vol. 11, no. 3, Art. no. 3, 2023, doi: 10.3390/machines11030322.S. Park, G.-J. Ahn, and D.-H. Im, “Auto Labeling Methods Developed Through Semi-Weakly Supervised Learning in Prognostics and Health Management Applications for Rolling Ball Bearing,” IEEE Sens. J., vol. 22, no. 16, Art. no. 16, Aug. 2022, doi: 10.1109/JSEN.2022.3188310.X. Zhang, K. P. Rane, I. Kakaravada, and M. Shabaz, “Research on vibration monitoring and fault diagnosis of rotating machinery based on internet of things technology,” NONLINEAR Eng. - Model. Appl., vol. 10, no. 1, Art. no. 1, Jan. 2021, doi: 10.1515/nleng-2021-0019.M. N. Ali, M. Amer, and M. Elsisi, “Reliable IoT Paradigm With Ensemble Machine Learning for Faults Diagnosis of Power Transformers Considering Adversarial Attacks,” IEEE Trans. Instrum. Meas., vol. 72, pp. 1–13, 2023, doi: 10.1109/TIM.2023.3300444.F. Jiang et al., “PHIR: A Platform Solution of Data-Driven Health Monitoring for Industrial Robots,” ELECTRONICS, vol. 13, no. 5, Art. no. 5, Mar. 2024, doi: 10.3390/electronics13050834.J.-H. Shin and H.-B. Jun, “On condition based maintenance policy,” J. Comput. Des. Eng., vol. 2, no. 2, Art. no. 2, Apr. 2015, doi: 10.1016/j.jcde.2014.12.006.L. P. Maguluri, D. Suganthi, G. M. Dhote, D. Kapila, M. M. Jadhav, and S. Neelima, “AI-enhanced predictive maintenance in hybrid roll-to-roll manufacturing integrating multi-sensor data and self-supervised learning,” Int. J. Adv. Manuf. Technol., Aug. 2024, doi: 10.1007/s00170-024-14263-7.L. Magadán, F. J. Suárez, J. C. Granda, F. J. delaCalle, and D. F. García, “A Robust Health Prognostics Technique for Failure Diagnosis and the Remaining Useful Lifetime Predictions of Bearings in Electric Motors,” Appl. Sci. Switz., vol. 13, no. 4, Art. no. 4, 2023, doi: 10.3390/app13042220.Z. A. Bukhsh and I. Stipanovic, “Predictive Maintenance for Infrastructure Asset Management,” IT Prof., vol. 22, no. 5, pp. 40–45, 2020, doi: 10.1109/MITP.2020.2975736.R. Rosati et al., “From knowledge-based to big data analytic model: a novel IoT and machine learning based decision support system for predictive maintenance in Industry 4.0,” J. Intell. Manuf., vol. 34, no. 1, Art. no. 1, Jan. 2023, doi: 10.1007/s10845-022-01960-x.J. C. B. Andrade, “Tendencias en ciencias de la computación,” Entre Cienc. E Ing., vol. 14, no. 27, pp. 19–28, Jul. 2020, doi: 10.31908/19098367.1740.Atkin and Adrian, Total Facilities Management. 2015.Mangano, “The role of maintenance and facility management in logistics: A literature review,” vol. 32.G. Nota, D. Peluso, and A. T. Lazo, “The contribution of Industry 4.0 technologies to facility management,” Int. J. Eng. Bus. Manag., vol. 13, p. 18479790211024131, Jan. 2021, doi: 10.1177/18479790211024131.Islam Helaly Abdel-Aziz Afefy, “Implementation of Total Productive Maintenance and Overall Equipment Effectiveness Evaluation,” Feb. 2013.Giancarlo Nota, Francesco David Nota, Domenico Peluso, and Alonso Toro Lazo, “Energy Efficiency in Industry 4.0: The Case of Batch Production Processes,” Aug. 17, 2020.Mounia Achouch, Mariya Dimitrova, Khaled Ziane, Sasan Sattarpanah Karganroudi, Rizck Dhouib, and Mehdi Adda, “On Predictive Maintenance in Industry 4.0: Overview, Models, and Challenges,” 12 de agosto de 2022, vol. 12.K. Kubiak, G. Dec, and D. Stadnicka, “Possible Applications of Edge Computing in the Manufacturing Industry—Systematic Literature Review,” Sensors, vol. 22, no. 7, Art. no. 7, Jan. 2022, doi: 10.3390/s22072445.J. Moradi, H. Shahinzadeh, H. Nafisi, M. Marzband, and G. B. Gharehpetian, “Attributes of Big Data Analytics for Data-Driven Decision Making in Cyber-Physical Power Systems,” in 2020 14th International Conference on Protection and Automation of Power Systems (IPAPS), Dec. 2019, pp. 83–92. doi: 10.1109/IPAPS49326.2019.9069391.L. Monostori, “Cyber-physical Production Systems: Roots, Expectations and R&D Challenges,” Procedia CIRP, vol. 17, pp. 9–13, Jan. 2014, doi: 10.1016/j.procir.2014.03.115.R. Saka, O. Chinagozi, and O. Joe, “Exploratory Research Design in Management Science: A Review of Literature on Conduct and Application,” Int. J. Res. Innov. Soc. Sci., vol. VII, pp. 1384–1395, May 2023, doi: 10.47772/IJRISS.2023.7515.T. Akyaz and D. Engın, “Machine Learning-Based Predictive Maintenance System for Artificial Yarn Machines,” IEEE Access, vol. 12, pp. 125446–125461, 2024, doi: 10.1109/ACCESS.2024.3454548.Q. Liu, J. Zhang, J. Liu, and Z. Yang, “Feature extraction and classification algorithm, which one is more essential? An experimental study on a specific task of vibration signal diagnosis,” Int. J. Mach. Learn. Cybern., vol. 13, no. 6, Art. no. 6, Jun. 2022, doi: 10.1007/s13042-021-01477-4.Z. Kazemi, F. Naseri, M. Yazdi, and E. Farjah, “An EKF-SVM machine learning-based approach for fault detection and classification in three-phase power transformers,” IET Sci. Meas. Technol., vol. 15, no. 2, Art. no. 2, Mar. 2021, doi: 10.1049/smt2.12015.A. Yan et al., “An Online Fault Detection and Remaining Life Prediction Method Based on SVDD for Rolling Bearings,” IEEE Trans. Instrum. Meas., vol. 73, pp. 1–12, 2024, doi: 10.1109/TIM.2024.3378268.N. M. Thoppil, V. Vasu, and C. S. P. Rao, “An Integrated Learning Algorithm for Vibration Feature Selection and Remaining Useful life Estimation of Lathe Spindle Unit,” J. Fail. Anal. Prev., vol. 22, no. 4, Art. no. 4, Aug. 2022, doi: 10.1007/s11668-022-01463-0.M.-Q. Tran, M. Elsisi, K. Mahmoud, M.-K. Liu, M. Lehtonen, and M. M. F. Darwish, “Experimental Setup for Online Fault Diagnosis of Induction Machines via Promising IoT and Machine Learning: Towards Industry 4.0 Empowerment,” IEEE ACCESS, vol. 9, pp. 115429–115441, 2021, doi: 10.1109/ACCESS.2021.3105297.B. Tasci, A. Omar, and S. Ayvaz, “Remaining useful lifetime prediction for predictive maintenance in manufacturing,” Comput. Ind. Eng., vol. 184, p. 109566, Oct. 2023, doi: 10.1016/j.cie.2023.109566.H. Xiao, W. Hu, G. Liu, and H. Zhou, “Edge computing-based unified condition monitoring system for process manufacturing,” Comput. Ind. Eng., vol. 177, 2023, doi: 10.1016/j.cie.2023.109032.X. Li and H. Zhao, “Performance Prediction of Rolling Bearing Using EEMD and WCDPSO-KELM Methods,” Appl. Sci.-BASEL, vol. 12, no. 9, Art. no. 9, May 2022, doi: 10.3390/app12094676.A. K. Verma, P. D. Raval, N. Rajagopalan, V. Khariya, and R. Sudha, “Development of an AI-based FSA for real-time condition monitoring for industrial machine,” Neural Comput. Appl., vol. 34, no. 11, Art. no. 11, 2022, doi: 10.1007/s00521-021-06741-w.R. Kizito, P. Scruggs, X. Li, M. Devinney, J. Jansen, and R. Kress, “Long Short-Term Memory Networks for Facility Infrastructure Failure and Remaining Useful Life Prediction,” IEEE Access, vol. 9, pp. 67585–67594, 2021, doi: 10.1109/ACCESS.2021.3077192.H. Chen, X. Wang, and Z.-X. Yang, “Fast Robust Capsule Network With Dynamic Pruning and Multiscale Mutual Information Maximization for Compound-Fault Diagnosis,” IEEEASME Trans. Mechatron., vol. 28, no. 2, Art. no. 2, Apr. 2023, doi: 10.1109/TMECH.2022.3214865.M.-Q. Tran et al., “Robust fault recognition and correction scheme for induction motors using an effective IoT with deep learning approach,” MEASUREMENT, vol. 207, p. 112398, Feb. 2023, doi: 10.1016/j.measurement.2022.112398.F. De Vita, D. Bruneo, and S. K. Das, “On the use of a full stack hardware/software infrastructure for sensor data fusion and fault prediction in industry 4.0,” PATTERN Recognit. Lett., vol. 138, pp. 30–37, Oct. 2020, doi: 10.1016/j.patrec.2020.06.028.Y. Niu et al., “A Sparse Learning Method with Regularization Parameter as a Self-Adaptation Strategy for Rolling Bearing Fault Diagnosis,” ELECTRONICS, vol. 12, no. 20, Art. no. 20, Oct. 2023, doi: 10.3390/electronics12204282.S. Liu, Z. Ji, Z. Zhang, and Y. Wang, “An Improved Deep Transfer Learning Method for Rotating Machinery Fault Diagnosis Based on Time Frequency Diagram and Pretraining Model,” IEEE Trans. Instrum. Meas., vol. 73, pp. 1–12, 2024, doi: 10.1109/TIM.2023.3345907.W. Mao, J. Chen, J. Liu, and X. Liang, “Self-Supervised Deep Domain-Adversarial Regression Adaptation for Online Remaining Useful Life Prediction of Rolling Bearing Under Unknown Working Condition,” IEEE Trans. Ind. Inform., vol. 19, no. 2, Art. no. 2, Feb. 2023, doi: 10.1109/TII.2022.3172704.X. Zhao, F. Shao, and Y. Zhang, “A Novel Joint Adversarial Domain Adaptation Method for Rotary Machine Fault Diagnosis under Different Working Conditions,” SENSORS, vol. 22, no. 22, Art. no. 22, Nov. 2022, doi: 10.3390/s22229007.Y. Cao, Q. Ni, M. Jia, X. Zhao, and X. Yan, “Online Knowledge Distillation for Machine Health Prognosis Considering Edge Deployment,” IEEE Internet Things J., vol. 11, no. 16, Art. no. 16, Aug. 2024, doi: 10.1109/JIOT.2024.3404112.O. Yotov and A. Aleksieva-Petrova, “Data-Driven Prediction Model for Analysis of Sensor Data,” Electron. Switz., vol. 13, no. 10, Art. no. 10, 2024, doi: 10.3390/electronics13101799.M. Han, Y. Wu, Y. Wang, and W. Liu, “Roller bearing fault diagnosis based on LMD and multi-scale symbolic dynamic information entropy,” J. Mech. Sci. Technol., vol. 35, no. 5, Art. no. 5, May 2021, doi: 10.1007/s12206-021-0417-3.H. A. Raja et al., “Signal Spectrum-Based Machine Learning Approach for Fault Prediction and Maintenance of Electrical Machines,” Energies, vol. 15, no. 24, Art. no. 24, 2022, doi: 10.3390/en15249507.M. Yousuf, T. Alsuwian, A. A. Amin, S. Fareed, and M. Hamza, “IoT-based health monitoring and fault detection of industrial AC induction motor for efficient predictive maintenance,” Meas. Control U. K., vol. 57, no. 8, Art. no. 8, 2024, doi: 10.1177/00202940241231473.2. Ingeniería y Tecnología::2B. Ingenierías Eléctrica, Electrónica e Informática::2B04. Ingeniería de sistemas y comunicacionesAlgoritmos de inteligencia artificialDetección de anomalíasAnálisis de anomalíasPredicción de FallasClasificación de FallasArtificial Intelligence AlgorithmsAnomaly DetectionAnomaly AnalysisFailure PredictionFault ClassificationPublicationhttps://scholar.google.com/citations?hl=en&user=qbPhSmkAAAAJvirtual::30-10000-0003-1566-1832virtual::30-1https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001170503virtual::30-12a35c4b1-0908-4455-984d-3638d88c8106virtual::30-12a35c4b1-0908-4455-984d-3638d88c8106virtual::30-1ORIGINALDDMIST307DDMIST307application/pdf1385161https://repositorio.ucp.edu.co/bitstreams/541b1648-ac55-42fa-a01d-627364322d8a/download3e5100a681442ffd664e4e3aacdd4901MD51LICENSElicense.txtlicense.txttext/plain; charset=utf-815543https://repositorio.ucp.edu.co/bitstreams/5ca52d40-4ca3-422e-a19c-72dc19002420/download73a5432e0b76442b22b026844140d683MD53TEXTDDMIST307.txtDDMIST307.txtExtracted texttext/plain101752https://repositorio.ucp.edu.co/bitstreams/0f9a5052-7d3f-4206-b13b-2c213fc95d0e/download82f79b8b728c2d158ea5ec313347c302MD54THUMBNAILDDMIST307.jpgDDMIST307.jpgGenerated Thumbnailimage/jpeg6401https://repositorio.ucp.edu.co/bitstreams/e35c944a-b27f-497c-b686-45c48236d32d/download6c0a59c2635c675f33727c180c898ba5MD5510785/16837oai:repositorio.ucp.edu.co:10785/168372025-10-05 03:01:12.209restrictedhttps://repositorio.ucp.edu.coRepositorio Institucional de la Universidad Católica de Pereira - RIBUCbdigital@metabiblioteca.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 |