Especialización Gerencia de Mantenimiento y Gestión de Activos

URI permanente para esta colecciónhttp://hdl.handle.net/11634/56080

Examinar

Mostrando 1 - 10 de 10

Manual de aplicación integrada de las metodologías Balanced Scorecard (BSC) y AMORMS para la identificación de KPI en la gestión de activos físicos en MiPymes avícolas del Meta.
(Universidad Santo Tomás, 2026-06-05) Parra Zamudio, Onman Andrés; Córdoba Malaver, Ana Rocío; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000081827; https://orcid.org/0000-0002-5687-4378
The development of the present monograph proposes a diagnostic and management model for the formulation of the strategic map for agribusiness micro and small enterprises (MiPymes), integrating the Balanced Scorecard (BSC) and AMORMS methodologies, aligned with the ISO 55000 series. The study was applied to a poultry farm in the department of Meta, allowing the identification of administrative management indicators and Key Performance Indicators (KPI) associated with the management of physical assets, thereby enabling the evaluation of the administrative and technical maturity of the microenterprise. Based on the correlation of the BSC and AMORMS methodologies, the SWOT matrix is employed to analyze the financial, internal process, customer, human talent, and environmental-social perspectives; through the study of these methodologies, it becomes possible to demonstrate the transition from an empirical business model to a management approach with professional foundations, based on data and measurable results, optimizing decision-making, operational efficiency, and business sustainability. The present contribution to the body of knowledge in maintenance asset management, demonstrates that the correspondence between the BSC–AMORMS methodologies is an effective strategy to strengthen the management of the company and its assets; enhancing the main asset, which is human talent, as a strategic intangible resource capable of consolidating an efficient, organized, and effective corporate culture; using continuous improvement tools such as Kaizen to strengthen competitiveness and align the company’s objectives, with international market standards. Keywords: Balanced Scorecard (BSC), AMORMS Methodology, Asset Management, Administrative Management Indicators, Key Performance Indicators (KPI).
Análisis y Transferencia de Prácticas Internacionales en la Integración de Ensayos No Destructivos, Inteligencia Artificial Y Gemelos Digitales para el Mantenimiento Predictivo de Activos Industriales en Colombia
(Universidad Santo Tomás, 2026-04-01) Mendoza Sanabria, Laura Daniela; Cordoba Malaver, Ana Roció; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0000081827; https://orcid.org/0000-0002-5687-4378
Industrial asset management is currently grappling with the dual pressure of aging infrastructure and stringent regulatory compliance within a framework of cost optimization. While Non-Destructive Testing (NDT) remains a cornerstone for identifying structural integrity issues such as corrosion and fatigue, its traditional application—characterized by periodic inspections—fails to provide the real-time insights necessary for proactive intervention. In Colombia's mining, energy, and oil & gas sectors, unscheduled downtime accounts for productivity losses of up to 25% and drives operational budget overruns beyond 30%. This study emphasizes the strategic necessity of evolving toward predictive maintenance by integrating NDT data with digital twin technology and advanced modeling. By transforming static inspection results into dynamic inputs for virtual replicas, organizations can simulate asset behavior in real-time. This integration bridges the gap between technical diagnosis and high-level managerial decision-making, ensuring operational continuity and alignment with ISO 55000 sustainability standards.
Análisis del Impacto de los Macroambientes en la Transformación Digital del Mantenimiento en la Industria de Logística y Transporte
(Universidad Santo Tomás, 2026-03-19) Jimenez Pinzón, María Luisa; Muñoz Barajas, Helver Mauricio; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001446983
The logistics and transportation industry faces increasing demands for operational efficiency, reliability, and sustainability, which is driving the adoption of technologies for the digital transformation of maintenance. In Colombia, this sector represents a strategic component for the country's economic competitiveness and the efficiency of its logistics operations. However, the adoption of these technologies is influenced by political, economic, social, technological, environmental, and legal (PESTEL) factors, whose specific impact on the sector still requires further analysis.
Mantenimiento Predictivo por Medio de IoT a Motor MTU
(Universidad Santo Tomás, 2026-02-05) Vargas Sandoval, Juan Sebastián; Fernández, Grenllery; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001446660
In high-criticality industrial systems, internal combustion engines used in power generation play a fundamental role as strategic assets, since their level of reliability and availability directly affects the operational and financial results of organizations. In this sense, MTU engines constitute capital-intensive investments that require the adoption of management strategies aimed at risk mitigation and value maximization. According to the International Organization for Standardization, through the ISO 55000 standard, asset management goes beyond the physical maintenance of equipment and is conceived as a coordinated activity intended to balance costs, risks, and performance throughout the asset's life cycle (ISO, 2014). However, traditional preventive maintenance approaches show significant limitations when applied to scenarios characterized by load variability and changing operating conditions. In this context, Zambrano-Castro and Pérez-Guerrero (2021) point out that, in industrial diesel engines, exclusive reliance on maintenance scheduled by hours of operation can lead both to unnecessary interventions and to unforeseen failures. Consequently, the current trend is moving toward diagnostic schemes based on the actual condition of the equipment. This position is consistent with what Amendola (2020) states, who affirms that modern availability management requires surpassing traditional cyclical models in order to optimize the asset's life cycle. From this perspective, the Internet of Things (IoT) is consolidated as the main technological enabler of maintenance transformation (Red Hat, n.d.). In particular, Porter and Heppelmann (2015) highlight that the evolution towards smart and connected products allows the data generated by assets to cease being simple historical records and become strategic inputs with competitive advantage potential. Complementarily, the integration of sensors and advanced analytics tools promotes proactive maintenance management, in accordance with the ECLAC (2021) vision of digitalization as a mechanism to reduce operational uncertainty in the region's industry. From a financial perspective, it is essential that the implementation of IoT-based solutions is supported by criteria of profitability and value generation. In this regard, García Palencia (2012) emphasizes that any investment in monitoring systems must be evaluated based on financial indicators such as present value and reduction of economic risk, providing objective information for decision-making related to the continuity, modernization, or replacement of the asset. Despite the technological advances described, a significant gap persists between real-time condition monitoring and its effective integration into financial decision-making processes. Therefore, the aim of the present work is to develop and evaluate an IoT-based maintenance strategy applied to an MTU engine, oriented towards fault anticipation and cost optimization, under the guidelines established by the ISO 55000 standard.
Propuesta de Modelo de Digitalización de Datos Maestros, Históricos y de Condición en CMMS/EAM para la Toma de Decisiones en Gestión de Activos
(Universidad Santo Tomás, 2026-02-06) Suarez Rivera, Juan Sebastian; Universidad Santo Tomás
This poster presents a proposed model for the digitization of master data, historical work order data, and condition data in a CMMS/EAM and using them in asset management decisions based on risk, criticality, and TOTEX costs
Formulación de un plan de mantenimiento predictivo para un equipo de Soldadura por Fricción Rotacional
(Universidad Santo Tomás, 2025-05-02) Faustino Molina, Katherin Johanna; Martinez Sarache, Handel Andres; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001467576; https://scholar.google.com/citations?user=cYDq-4YAAAAJ&hl=es; https://orcid.org/0000-0002-2879-4899
The rotary friction welding equipment, located in the metallurgical engineering laboratories of the Universidad Pedagógica y Tecnológica de Colombia, is a key tool in academic training and research on solid-state welding. To ensure the reliability of experimental results and extend the equipment's service life, it is essential to implement appropriate maintenance strategies. In this context, a predictive maintenance plan was designed, which, through visual inspections and on-site visits, allowed for the assessment of its operational status and working environment. The applied methodology follows the (ISO 14224, 2016) standard, including a taxonomic analysis, the definition of operational limits, and the coding of systems and components to facilitate failure analysis. Using a root cause diagram, failure mechanisms related to vibrations during welding, electrical and instrumentation failures, as well as issues caused by unauthorized handling, were identified. These findings were compared with Tables B.2 and B.3 of the (ISO 14224, 2016) standard. Based on the obtained results, specific predictive actions were proposed, such as thermography, magnetic particle testing, and hydraulic oil analysis, complemented by a standardized inspection format. The documentation of the operational history will allow for a more accurate analysis to efficiently schedule predictive maintenance while aligning with the available budget. Furthermore, this methodology not only optimizes the performance of the studied equipment but can also be applied to other machinery requiring evaluation and optimization.
Aplicación del Mantenimiento Predictivo en la Industria Petrolera: Una Revisión Exhaustiva
(Universidad Santo Tomás, 2025-05-28) Gutiérrez Jiménez, Yekini Mateo; Maldonado Moreno, Jerson Fabian; Universidad Santo Tomás; https://scienti.minciencias.gov.co/cvlac/visualizador/generarCurriculoCv.do?cod_rh=0001712701; https://scholar.google.es/citations?hl=es&user=uRbUPY0AAAAJ&scilu=&scisig=AMD79ooAAAAAY4TC_QQaJ-vuzqcbyHlq4PrrSfuKuSSn&gmla=AJsN-F6MrzbVxRU5sjJmSAp44MFRC7hNNIktxgWtD8MYd8q6XsLGqNWOr61BiEPBA-MBsvBWsX01xFdJ6EWHM5l1YL4v8V7itEr0-6wHkrcfWRqXpEt3ZrW1tBWKORvpJcXsazcgI-27&sciund=7173997066276809121; https://orcid.org/0000-0002-4919-6150
Predictive maintenance has revolutionized the oil industry by optimizing asset management and reducing operational costs through the anticipation of failures in critical equipment. This article provides a comprehensive review of the technologies applied in the sector, highlighting the use of machine learning, neural networks, support vector machines, and Weibull analysis. Recent studies that have implemented these techniques to enhance the reliability of pumping systems, turbo compressors, and other key equipment are analyzed. The results demonstrate that the use of advanced algorithms enables highly accurate failure prediction, reducing downtime and optimizing maintenance decision-making. Finally, the main challenges in implementing these technologies are identified, and future research directions are proposed to improve their adoption in the oil industry.
Propuesta plan de negocios para la creación de una Empresa prestadora de servicios de consultoría, mantenimiento eléctrico y mecánico
(Universidad Santo Tomás, 2025-05-25) Cárdenas Nonsoque, Freyner Camilo; Moreno Castiblanco, Mayra Lorena; Carmona Rivera, Jairo Andres; Cetina Torres, Leonel; Universidad Santo Tomás; https://scholar.google.com/citations?user=131nUS4AAAAJ&hl=es
This work presents a business plan for the creation of a consulting and maintenance company specializing in electrical and mechanical systems, based on the growing need for specialized services that ensure the efficient and safe operation of organizations. The study begins by recognizing that many companies underestimate the importance of proper maintenance, which can lead to unforeseen costs and long-term risks. In response, a strategic solution is proposed that combines precise technical diagnostics, preventive maintenance, and customized programs tailored to each client's specific needs. The document is structured into several chapters that address the project's justification, the methodology used for market analysis, and the development of implementation strategies. It also includes a detailed study of the competition, the definition of the organizational structure, the necessary human resources, and a financial analysis that evaluates the economic feasibility of the project. Overall, this work provides a solid framework for the launch of a sustainable, efficient company that complies with the regulations of the electrical and mechanical maintenance sector.
Influencia del mantenimiento basado en condición de los lubricantes: una revisión sistemática en los motores de encendido por compresión
(Universidad Santo Tomás, 2025-05-14) Garrido Pérez, Wilson Enrique; Vera Rozo, James Donald; Universidad Santo Tomás; https://scholar.google.es/citations?user=OY25FjcAAAAJ&hl=es; https://orcid.org/0000-0003-0516-3936
Condition-Based Maintenance (CBM) has become a key strategy for optimizing the maintenance of compression ignition engines, allowing for the real-time assessment of lubricant condition and the adjustment of oil change intervals based on its degradation. This study presents a systematic review of the literature on CBM applied to lubricants, analyzing its impact on operational efficiency, cost reduction, and industrial sustainability. For this purpose, scientific databases were utilized to identify trends and technological advancements in lubricant tribology, considering methods such as spectroscopic, ferrographic, and viscosity analysis. The results show that CBM implementation reduces lubricant waste, extends engine lifespan, and lowers operational costs by minimizing unexpected failures. Additionally, the increasing adoption of IoT sensors and predictive algorithms for real-time oil monitoring is highlighted, improving maintenance management. Despite its advantages, challenges remain in standardizing degradation parameters and integrating advanced technologies for real-time monitoring across various industrial environments. Future research directions include the development of artificial intelligence models to predict lubricant degradation and the expansion of CBM into sectors such as Oil & Gas, aviation, and mining. This study provides a foundation for optimizing maintenance management and promoting more efficient and sustainable industry practices. Keywords: Tribology, condition-based maintenance, oil analysis, prediction, lubricant monitoring.
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/0009-0001-3180-7099
This 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.

Examinar

Envíos recientes