Tesis Tecnologías de la Información

Permanent URI for this collectionhttp://repositorio.uta.edu.ec/handle/123456789/34849

Browse

Now showing 1 - 4 of 4

Api restful para la gestión del mantenimiento predictivo de bombas hidráulicas en la producción de crudo
(2026-01) Villacrés Espin Jaime Marcelo; Álvarez Mayorga Edison Homero; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Tecnologías de la Información
This project addresses the need to improve the maintenance management of hydraulic pumps in crude oil production, where operational and maintenance data are scattered across Excel files, isolated reports, and external platforms such as ABB, hindering historical analysis and decision-making. As a solution, a RESTful API tailored to maintenance requirements is designed and implemented, conceived as the backbone of an AI-based predictive maintenance system within the Technical University of Ambato. The methodology is structured in three phases: first, an analysis of the current data logging and usage process, identifying limitations in traceability, access, and the link between operating conditions and maintenance events; second, the design of the API's components, functions, and data model, defining functional and non-functional requirements, as well as key entities such as ingestions, raw measurements, clean measurements with preprocessing indicators, and characteristics; and third, implementation using FastAPI and PostgreSQL, integrating sources such as MQTT and OPC UA, and validating the system with real data exported from ABB. The results show a significant improvement in data centralization, quality, and availability, as well as optimized endpoints for bulk uploads and trend, dispersion, and histogram analytics modules with filters for quality, time, and variable. It is concluded that the developed API meets the stated objectives and provides a solid foundation for integration with predictive maintenance models in real-world industrial environments.
Sistema de preprocesamiento de datos sensoriales utilizando Python en la gestión de mantenimiento predictivo de bombas hidraúlicas en la producción de crudo
(2026-01) Rea Ramírez Carmen Alexandra; Álvarez Mayorga Edison Homero; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Tecnologías de la Información
Predictive maintenance management in the oil industry heavily depends on the quality, consistency, and reliability of sensor data, which often appear as raw streams with temporal irregularities, information loss, and uncontrolled variations that hinder analysis. To address this challenge, the purpose of this work was to implement a sensor data preprocessing system using Python to support predictive maintenance of hydraulic pumps in crude oil production. The CRISP-DM methodology was adopted, structuring the process from problem understanding to the final preparation of data for integration into predictive models. The developed system comprises three main phases: quality diagnosis and labeling, temporal reconstruction with controlled imputation, and statistical feature generation. Each phase produces and stores its results in independent tables, ensuring traceability and organized use of information. As a result, the system significantly improved the quality and usefulness of sensor data. The impact of data quality was demonstrated by training two models on the Phase 1 dataset, where Logistic Regression achieved an accuracy of 34.92%, showing its limited ability to handle noise, outliers, and temporal variability, while Random Forest reached 99.57%, confirming that higher data quality directly influences model learning and performance. The final system is available for use by the research team and for future extension in subsequent work.
Sistema web integrado bajo el modelo de evaluación CACES, para la gestión de procesos de autoevaluación institucional y de carreras en la FISEI
(2026-01) Lucero Estupiñan Isaac Daniel; Zapata Delgado Ricardo Steven; Álvarez Mayorga Edison Homero; Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Tecnologías de la Información
Quality assurance in higher education requires rigorous evidence-based self-assessment processes. The Faculty of Systems, Electronics, and Industrial Engineering (FISEI) at the Technical University of Ambato faced operational difficulties due to the manual and dispersed management of information required by the CACES model. The objective of this research was to develop and implement an integrated web system to automate and centralize the management of institutional and career self-assessment processes. A hybrid methodology integrating Extreme Programming (XP) for coding and Scrum for project management was used for development. The software architecture was implemented using .NET Core 9 for the backend, Blazor for the frontend, and Microsoft SQL Server 2022 as the database engine, ensuring scalability and security. The web platform automated the Teaching (10 indicators) and Research and Innovation (3 indicators) criteria, enabling the calculation of quantitative indicators and the validation of qualitative documentary evidence through controlled workflows. The results validated the tool's efficiency, successfully centralizing information and significantly reducing the administrative workload for faculty, achieving an acceptance rate of over 80% from users involved in accreditation processes.
Sistema web integrado bajo el modelo de evaluación CACES, para la gestión de procesos de autoevaluación institucional y de carreras en la FISEI
(2026-01) Zapata Delgado Ricardo Steven; Lucero Estupiñan Isaac Daniel; Álvarez Mayorga Edison Homero
Quality assurance in higher education requires rigorous evidence-based self-assessment processes. The Faculty of Systems, Electronics, and Industrial Engineering (FISEI) at the Technical University of Ambato faced operational difficulties due to the manual and dispersed management of information required by the CACES model. The objective of this research was to develop and implement an integrated web system to automate and centralize the management of institutional and career self-assessment processes. A hybrid methodology integrating Extreme Programming (XP) for coding and Scrum for project management was used for development. The software architecture was implemented using .NET Core 9 for the backend, Blazor for the frontend, and Microsoft SQL Server 2022 as the database engine, ensuring scalability and security. The web platform automated the Teaching (10 indicators) and Research and Innovation (3 indicators) criteria, enabling the calculation of quantitative indicators and the validation of qualitative documentary evidence through controlled workflows. The results validated the tool's efficiency, successfully centralizing information and significantly reducing the administrative workload for faculty, achieving an acceptance rate of over 80% from users involved in accreditation processes.