Especialización Gerencia de Mantenimiento y Gestión de Activos
URI permanente para esta colecciónhttp://hdl.handle.net/11634/56080
Examinar
Envíos recientes
Ítem Revisión del Mantenimiento Predictivo Potenciado por Machine Learning en el Sector Industrial de América Latina: Situación Actual, Desafíos y Tendencia(Universidad Santo Tomás, 2025-05-05) Romero Ramírez, Henry Esteban; Poveda Pachón, Marlon Yesid; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0002132921; https://scholar.google.es/citations?user=5kKmXFkAAAAJ&hl=es&oi=ao; https://orcid.org/0009-0001-3180-7099This study examines the current situation, challenges, and trends of predictive maintenance powered by Machine Learning in the industrial sector of Latin America through a systematic review that included 60 implementation cases identified in Scopus, ScienceDirect, and Google Scholar. Only documents published from 2014 onward in Spanish, English, or Portuguese were selected, all applying Machine Learning techniques to predict failures in real industrial equipment or systems within Latin American companies. The results show that Brazil accounts for the largest number of publications (48%), followed by Ecuador (18%) and Colombia (15%), while Mexico, Argentina, Chile, and Peru represent 19% of the cases. The adoption of these technologies mainly focuses on the manufacturing, energy, and automotive industries, where critical equipment such as turbines, wind turbines, and heavy machinery receive the most attention. Among the most widely used Machine Learning techniques are Random Forests (RF), Support Vector Machines (SVM), and Decision Trees (DT), with Python as the predominant programming language due to its accessibility and versatility. The main barriers identified include the lack of technological infrastructure, managerial unawareness, resistance to change, and data confidentiality. Nevertheless, future initiatives are expected to prioritize solutions related to waste management, resource optimization, and enhanced energy sustainability, offering opportunities to transform industrial processes and improve regional competitiveness.