Maestría en Ingeniería (tesis)
URI permanente para esta colección
Examinar
Envíos recientes
Publicación Prototipado de un sistema de análisis de datos para la disminución del tiempo de limpieza de paneles solares basado en telemetría, inteligencia artificial y visualización en tiempo real(Universidad EAFIT, 2026-03-09) Echeverri Tamayo, Camilo; Castaño Cano, DavinsonThis work presents a real-time analysis and telemetry system prototype to optimize solar panel cleaning through artificial intelligence and an interactive dashboard. It integrates a Node.js simulation, Java and Python microservices, and a React interface. Results showed dust reduction between 55% and 90% and power increases from 0.9% to 8.1%, confirming its value for operational efficiency and energy sustainability.Publicación Prevención de la obsolescencia tecnológica en funciones serverless de amazon web services a través de automatización e inteligencia artificial(Universidad EAFIT, 2025-12-01) Muñoz Muñoz, Victor Daniel; Diaz León, Christian AndrésPublicación Comparación del uso de asistentes de IA generativa Chatgpt, Github Copilot y Gemini para la detección y corrección de errores de aplicación de principios solid, estilo, lógica y ejecución en código Java(Universidad EAFIT, 2025) Fernández Restrepo, Alejandro; Correo Botero, DanielPublicación Modelo de capacidad para los procesos de check-in y filtro de seguridad para vuelos nacionales mediante teoría de colas y simulación de eventos discretos en el aeropuerto internacional José María Córdova(Universidad EAFIT, 2025-11-28) Cruz Ibarra, Daniel Felipe; Ramírez Echeverri, Sergio Augusto; Sociedad Operadora de Aeropuertos Centro Norte Airplan S.A.S.Publicación Development of an Autonomous and Interactive Robot Guide for Industrial Museum Environments Using IoT and AI Technologies(Universidad EAFIT, 2025-12-01) Arteaga Vargas, Andrés; Velásquez Rendón, David; Giraldo Pérez, Juan Pablo; Sanín Villa, Daniel; Velásquez Rendón, David; Sanín Villa, DanielPublicación Data-Driven Mathematical Framework for Reliability and Maintainability Analysis of Complex Industrial Systems Based on Non-Parametric KDE(Universidad EAFIT, 2026-03-06) Díaz Feria, Cristian David; Martinod Restrepo, Ronald MauricioPublicación Estado del arte sobre el uso de aislamiento sísmico a media altura - (MSI)(Universidad EAFIT, 2025) Arroyave Lopera, Camilo; Fuentes García, Juan Manuel; Fuentes García, Juan ManuelSeismic isolation has proven to be an effective strategy for significantly reducing seismic demand in buildings, allowing both structural integrity and post-earthquake functionality to be preserved. Traditionally, this technology has been implemented at the base level; however, over the past two decades an innovative variant known as mid-story isolation (MSI) has emerged. Its application has gained relevance in structures with functional, architectural, or retrofit constraints that prevent the placement of isolators at the base. This article presents a detailed state-of-the-art review of the application of MSI, covering experimental studies, analytical research, and constructed projects worldwide. To facilitate a comprehensive understanding of this technology, different typological schemes are analyzed, ranging from isolation at a single intermediate level to multiple or hybrid configurations. In addition, the main associated challenges are discussed, such as the accurate identification of tributary masses, the appropriate definition of isolation levels, and the dynamic interaction between the upper and lower portions of the structure. The paper includes a critical discussion on the current feasibility and limitations of MSI in different seismic and regulatory contexts, highlighting the key role of this technology in the rehabilitation of existing structures, particularly in urban areas with geometric or operational constraints. This work aims to contribute to the dissemination and consolidation of an emerging technology with strong potential to enhance structural resilience in situations where traditional base isolation is no longer viable.Publicación Estrategias en universidades para mejorar la permanencia de mujeres en estudios de ingeniería, resultados de un mapeo sistemático de la literatura(Universidad EAFIT, 2026-03-17) Henao Ocampo, José David; Suescún Monsalve, Elizabeth; Alianza 4UPublicación Proposal for a predictive model for micropiles bond resistance based on load tests(Universidad EAFIT, 2026-02-20) Molano Quiroz, Mauricio Alejandro; Ruiz Restrepo, Daniel Felipe; NAThe use of micropiles has gained increasing popularity in Latin America as a foundation system due to their versatility, ease of installation in complex conditions, and growing load-bearing capacity, driven by the availability of specialized equipment, materials, advanced technologies, technical expertise, and a maturing culture of load testing. This allows the designers to reduce uncertainty, particularly from the geotechnical perspective, specifically when comparing them with other foundation systems commonly used in the region. Additionally, the increased implementation of both verification and quality control static load test programs commonly known as verification test and proof test based on the definition presented in the FHWA document for Design and Construction of Micropiles [1], has made it possible to collect sufficient data for estimating design parameters, developing predictive models, and implementing Reliability-Based design (RBD) approaches across different soil conditions. This approach enables optimized solutions that are better adapted to specific loading, geotechnical and geological conditions. This considers the possibility of proposing site resistance factors for geotechnical design of micropiles as mentioned in [2]. To develop the model proposal presented in this study, various tasks were carried out to characterize the geotechnical conditions of the site and to assess the load-deformation behavior of micropiles subjected to tension, compression, and lateral loads. This information served as the foundation for building a strategic framework that allows a comprehensive methodology for the development of a predictive model adaptable to different site conditions considering the information available and allowed comparisons between different construction techniques and their associated skin friction resistance represented in literature as αbond or \tau (tau). A total of 40 load tests were collected and analyzed, located in the fine alluvial deposit zone of the La Pereira stream in the municipality of La Ceja, Antioquia. These tests were performed using two different installation techniques on two different sites in the same geotechnical and geological environment which permit stablish comparison between the two sites. The techniques used were self-drilling micropiles (simultaneous drilling and grouting), and pre-drilled micropiles with Type B or Type C injection, based on the classification presented in [1]. This dual approach enabled comparative analysis of behavior and ground to grout adhesion for different cases regarding injection type and load application (compression and tension). With the purpose of validating and as a benchmark values, additional load test reaching failure were included from other sites.Publicación Modelo para inscripción de informalidades por posesiones y ocupaciones en el catastro de Medellín : estudio de caso(Universidad EAFIT, 2026-02-28) Mendoza, Julio César; Salcedo Saldaña, DannyThe objective of this case study is to propose a model for registering informal occupations and possessions in the cadastre of the city of Medellín. The lack of formalization of these occupations within the city's cadastral system represents a significant challenge for urban management, the provision of public services, the legal certainty of residents, and territorial planning. In this regard, this work proposes an information system that enables these occupations to be incorporated into the cadastre as effectively as possible. The research addresses the technical, legal, and social challenges surrounding the registration of informal occupations and proposes a solution based on the use of geographic information technologies and an up-to-date database. The proposed model is expected to contribute to a more just, equitable, and sustainable urban management by enabling greater numbers of individuals, businesses, and economic activities to become formalized, while facilitating improved access to regularized property and urban services.Publicación Determinación de las especificaciones técnicas de las mangueras de riego en polietileno reciclado en la empresa Biomangueras San Martín S.A.S.(Universidad EAFIT, 2026) Fernández Paz, Juliana; Rodríguez Arroyave, Carlos ArturoPublicación Diseño de una metodología para la estandarización de la gestión de proyectos de nuevos empaques plásticos para el sector cosmético(Universidad EAFIT, 2026) Hincapié Salazar, Lina; Rodríguez Arroyave, Carlos ArturoPublicación Arquitectura de referencia para interfaces adaptativas en portales de empleo, orientadas a una experiencia de usuario personalizada, accesible y transparente(Universidad EAFIT, 2025) López Cuartas, Juan Camilo; Suescún Monsalve, ElizabethPublicación Modelos matemáticos de la interacción luz-tejido y sus implicaciones en simulaciones orientadas a la Tomografía de Coherencia Óptica(Universidad EAFIT, 2026) Cañas Jiménez, Sebastián; Restrepo Gómez, RenéPublicación Impacto de la ingeniería de líneas de productos de software en la calidad del proyecto base y la eficiencia de su derivación para aplicaciones móviles en Pragma S.A.(Universidad EAFIT, 2026) Morales Jaimes, Darry Alejandro; Mazo Peña, Raúl IvánThe mobile application market continues to experience rapid growth and, in this context, the generation of base projects in software development organizations is vital and often depends on manual processes with high variability in quality and effort. This work evaluates the impact of adopting software product line (SPL) engineering practices to derive base projects for mobile applications at Pragma S.A. Under the Design Science Research paradigm, a formal model of characteristics for mobile application architecture (MAAFM) and its reduced operational version (MAAFM-RO) with 72 points of variability; additionally, a configurator was implemented in VariaMos and semi-automatic generation integrations using Mason (Flutter), Gradle/CocoaPods, and XCodegen (Android/iOS), covering up to 80% of the variability modeled for Flutter and 70% for native technologies. The proposal was evaluated with a quasi-experimental paired design in six scenarios (Flutter, Android, and iOS for financial and retail domains), comparing manual derivation vs. LPS-supported derivation. Quality was measured using the IQ_ARQ index, based on ISO/IEC 25010 and composed of SonarCloud metrics and heuristic evaluation by engineers. The results showed evidence of an average reduction in derivation time of 49% and an average increase in architectural quality of 33%, with consistent bootstrap confidence intervals. Based on this, it is concluded that LPS significantly improves derivation efficiency and the quality of the base project, being sensitive to the maturity and maintenance of the initial generators and templates.Publicación Modelo de referencia de sistema basado en inteligencia artificial para facilitar la modernización de sistemas heredados(Universidad EAFIT, 2026) Roldán Vélez, Carlos David; Gutiérrez Betancur, Sergio ArmandoThis research proposes a reference model based on multi-agent systems powered by artificial intelligence to facilitate the modernization of legacy systems. Through a systematic literature mapping and the harmonization of multiple approaches, a reference architecture is designed that integrates AI techniques to support code migration, comprehension, and transformation in organizational environmentsPublicación Aplicación de algoritmos en la reconstrucción de estructuras reticulares en modelos BIM(Universidad EAFIT, 2026) Moncada Hernández, Alexandra Milena; Botero Botero, Luis FernandoPublicación Correlación entre propiedades mecánicas y velocidades sísmicas en depósitos fluvio-volcánicos en la ciudad de Manizales(Universidad EAFIT, 2025) Muñoz Castillo, Cristian Camilo; Aristizábal Arias, Jorge AlonsoPublicación Desarrollo de modelo predictivo basado en machine learning para anticipar fallas en el probador de suspensión de la línea de livianos del Centro de Diagnóstico Automotor Certi Express Pereira S.A.S.(Universidad EAFIT, 2026) Vallejo Yepes, Mauricio; Martínez Vargas, Juan DavidPredictive maintenance has become a fundamental mechanism for ensuring the reliability, availability, and efficiency of industrial equipment. In the Colombian automotive sector, Automotive Diagnostic Centers (CDAs) play a crucial role in road safety by ensuring that vehicles meet the technical requirements of national regulations. However, traditional corrective and preventive maintenance methods generate downtime and additional costs that affect the continuous operation of inspection equipment. This research develops a machine learning-based solution to analyze the results of adhesion tests obtained using the suspension tester of the light vehicle line at the Certi Express Pereira S.A.S. Automotive Diagnostic Center. 2,360 test records were collected and, after a cleaning, normalization, and variable analysis process, a predictive model was built capable of detecting patterns associated with potential failures in both the measuring equipment and the inspected vehicles. The results show that the application of machine learning models in automotive diagnostic environments significantly improves the early detection of anomalies, allows for optimized maintenance planning, and contributes to reducing operating costs and downtime.Publicación Aproximación para personalización de interfaces basado en datos históricos en un caso aplicado de la banca(Universidad EAFIT, 2025) Vergara Marín, Natalia Andrea; Arbeláez, Juan CarlosThis project proposes an approach to generate personalization proposals through a user grouping model based on pattern identification in transaction history, with the aim of improving each user's experience by allowing them to view options that suit their particular needs. The project has two stages: the development of the user grouping model using machine learning (ML) algorithms through the CRISP-DM methodology, achieving a result of six user clusters with a silhouette coefficient of 64%, which represents adequate cohesion and distinguishable patterns; and secondly, the development of personalized proposals using the design thinking methodology. This was the result of a case study applied to a digital channel of a financial institution in Colombia, where, based on customer validations, a 90% favorability rating was obtained in terms of the perceived value of the proposal made for the specific cluster of each group, with an average of 30% more compared to the control variants.