Unidad de Posgrados
Permanent URI for this communityhttp://repositorio.uta.edu.ec/handle/123456789/11
Browse
5 results
Search Results
Item Diseño de un modelo para el control del consumo de filtros y lubricantes del equipo caminero y maquinaria pesada del GAD del Cantón La Maná mediante algoritmos de inteligencia artificial(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Maestría en Matemática Aplicada, 2023) Ortiz Reyes, Juan Carlos; Loza Aguirre, Edison FernandoEl objetivo principal de este estudio fue dise˜nar un modelo matemático utilizando algoritmos de inteligencia artificial para predecir el consumo de lubricantes en la maquinaria pesada del GAD del Cantón La Maná. Para ello se recopilo información de diferentes tipos de algoritmos de inteligencia artificial que podrían ser útiles para la predicción de consumo, y se eligió la red neuronal artificial no lineal autorregresiva como la mejor opción. La información utilizada en este estudio fue obtenida de los registros diarios de la Unidad de Transporte y Maquinaria del GAD Municipal La Maná en los años 2018 y 2019, donde se registraron los kilometrajes y horómetros diarios al inicio y al final de la jornada laboral. La precisión del modelo se evaluó mediante el cálculo del error medio cuadr´atico (MSE), que mide la diferencia cuadrática promedio entre los valores predichos y los valores reales. Los resultados mostraron que la red neuronal que utiliza el algoritmo Retropropagación Levenberg-Marquardt con la arquitectura 128, 64 en las capas ocultas de la red neuronal fue el mejor modelo, con un MSE de 0.000301. En resumen, se concluye que el modelo de red neuronal no lineal autorregresiva puede ser una herramienta ´util para predecir el kilometraje y hor´ometro de las maquinaria pesada, y por ende estimar el consumo de lubricantes, lo que podría permitir una mejor planificación y optimizaci´on del uso de lubricantes.Item Revisión sistemática de metodologías de mantenimiento de oleoductos basadas en Industria 4.0(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Maestría en Producción y Operaciones Industriales, 2022) López Vargas, Nancy Fabiola; García Sánchez, Marcelo VladimirThe fourth industrial revolution was a milestone at the industrial level. It forced most industries to evolve technically and for their collaborators to prepare and advance together with technology; the oil industry was no exception. It develops its activities in dangerous and dynamic environments and needs to protect its human resources, equipment and infrastructure. This article presents a scoping review, based on the PRISMA guidelines, of pipeline maintenance methodologies based on industry 4.0. From the first collection of 123 articles from prestigious databases such as SpringerLink, MDPI, Scopus, IEEEXplore and ACM, a final sample of 31 articles was obtained. Here, technologies that enhance preventive and predictive maintenance systems are discussed. The results show that predictive maintenance compared to preventive maintenance has a percentage difference in upkeep time optimization of 38% in the last five years. This difference was corroborated with a T-Student for independent samples, with a significance of 0.023. Likewise, the most used technologies were analyzed, with artificial intelligence standing out with 45.16%.Item Diseño de un controlador multivariable utilizando herramientas de inteligencia artificial aplicado al proceso de incubación de embriones de Gallus Gallus Domesticus(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Maestría en Electrónica y Automatización, 2022) Balseca Chicaiza, Alvaro Bladimiro; Herrera Garzón, Marco AntonioThis project presents, a multivariable control using fuzzy logic and genetic algorithms (GA) as Artificial Intelligence (AI) tools, applied to the hatching process of “Gallus gallus domesticus” embryos. The incubation process is a system with high interactions among its input and output variables. To reduce these interactions, a dynamic decoupling network is used through Relative Gain Array (RGA) analysis. The proportional integral (PI) controllers and the linear decoupler are designed from singlevariable control structures obtained from a parametric identification for systems that can be pproximated to first order and first order with delay (FOPDT) models. Performance of PI, PI-Fuzzy and PI-Fuzzy controllers tuned with Genetic Algorithms (GA), are evaluated through a comparison of the integral squared error (ISE), integral absolute error (IAE) and total variation control (TVu) through simulations in MATLAB® and experimental tests using the NODEMCU ESP-WROOM-32 embedded system.Item Evaluación con red neuronal del proceso de desgaste abrasivo de placas de un material compuesto de látex con partículas de caucho reciclado(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Maestría en Físisca Aplicada, 2022-02) Muñoz Valverde, Pablo Rafael; Pérez Salinas, Cristian FabiánIn this thesis, a Machine Learning approach was investigated in the field of manufacturing new materials for industry. In particular, artificial neural networks were used to predict the Taber wear index (TDI) of latex plates and recycled rubber particles. In recent years, the application of Artificial Intelligence and in particular Machine Learning to scientific disciplines has increased substantially. The purpose was to evaluate how machine learning works, in particular neural networks, and how it should be applied to make a prediction. The preliminary phase of the work was to create the experimentally obtained data set necessary for the secondary phase, which includes the analysis and modeling of neural networks. The generation of the data set involved the manufacture of the material and wear tests based on the ISO 9352 standard. In the context of the neural network, the Google TensorFlow software was used through the Python3 interface. The model developed allows to predict the IDT of the plate taking as independent variables; the volumetric percentage of material, the rotational speed, applied load and the number of cycles. The performance of the network will be evaluated through statistical tests such as the mean square error (MSE), the mean absolute error (MAE) and the coefficient of determination (R2).Item Implementación de un sistema inteligente para la identificación vehicular(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Maestría en Matemática Aplicada, 2021) Cáceres Mayorga, Paúl Alejandro; Reinoso Astudillo, Cristina IsabelThe main objective of this research work was to implement an intelligent system capable of classifying vehicle and automotive license plates, as well as self-correcting recognition errors, for which it was based on the design of an algorithm capable of detecting and classifying vehicles, implementing artificial intelligence. Once the process to be followed was identified, a source code was implemented for the detection of the types of license plates using the convolutional neural network WPOD in which the data of the edge, width and height of the plate were specified so that it only provides the photo of license plate. For the binarization process used in the research, the Otsu algorithm was used, which converts the images into the gray, blur, binary and dilation scales, applying filters that can obtain the location segments of the letters and numbers. Finally, an effective system was obtained, with acceptable detection capacity, since design parameters of the architecture of each type of red were established, which achieved a satisfactory solution to the problem of identification, classification and validation of the characters of Ecuadorian license plates.