Maestría en Ingeniería de Control Industrial

URI permanente para esta colección

https://hdl.handle.net/20.500.12313/2397

Navegar

Envíos recientes

Mostrando1 - 5 de 7
  • Miniatura
    Publicación
    Acceso abierto
    Desarrollo de planta piloto para la obtención de bioproductos para aplicación en cultivos de interés económico operada mediante control programado
    (Universidad de Ibagué, 2022) Urrego Sánchez, Luis Fabian; Araque de los Ríos, Oscar Javier; García Beltrán, Olimpo José
    En el presente trabajo de investigación se diseñó, construyo e implemento una planta piloto cuya función principal es la de obtener extractos y bioproductos para su uso en cultivos de interés económico. La planta consta de cuatro módulos; siendo el primero de ellos el de molienda, por medio del cual se pican las hojas de vegetales en tamaños establecidos; el módulo de agitado; el cual implica el uso de dos tanques de 100 litros de capacidad cada uno, dentro del cual se mezclan las hojas molidas con solventes establecidos y se agitan bajo un régimen turbulento. Por último, se tienen los módulos de dosificado y envasado; los cuales se encargan de dosificar determinada cantidad de bioproducto dentro de un envase y luego sellarlo respectivamente. Para la construcción de cada uno de estos subsistemas se aplicaron técnicas de manufactura tradicionales combinadas con técnicas novedosas como la impresión 3D. Finalmente, para permitir que el operador pudiese programar y controlar los procesos involucrados se desarrolló una interfaz de usuario donde se pueden visualizar y definir parámetros como velocidad de molienda, tiempo de agitado, velocidad de agitado y volumen dosificado. Utilizando el software de desarrollo de código abierto basado en lenguaje C++ se pudo procesar las señales de cada uno de los sensores y sintonizar sus respectivos filtros de media móvil exponencial.
  • Miniatura
    Publicación
    Acceso abierto
    Clasificación automática de Heliconias a partir de imágenes RGB
    (Universidad de Ibagué., 2020) González Santos, Christian Saúl; Forero Vargas, Manuel Guillermo; Beltran Reyes, Carlos Eduardo
    Colombia is the country with the largest number of plant species in the world. Within it, the heliconias play an important ecological role within the ecosystems, since they are frequent components of the interior and limits of the forests, as well as of open environments such as pastures, roadsides and riverbanks. In some ecosystems they act as pioneers in the process of natural regeneration of vegetation and restoration of degraded soil. In addition, they maintain important co-evolutionary relationships with other animal and plant species, becoming an important element within the complex framework of life in the tropics. The classification of plant species is crucial for the protection and conservation of biodiversity. Manual classification is time-consuming, costly and requires experts who are often limited in their availability. To address these problems, three methods of classification of SVM (Support Vector Machine), ANN (Neural Networks), KNN (Nearest Neighbors) images with Euclidean distance and intersection were used in this work, which gave good results in the classification of four species of heliconias found at the University of Ibagué. The data used for training, testing and validation of the methods were RGB images taken in the natural habitat of the heliconias, in order to have information from their germination to their optimal cutting time. The images were pre-processed, making an adjustment of white balance, contrast and color temperature. To separate the heliconias from the background, a graphical segmentation technique using GPS was used. The descriptors were obtained using the technique known as BoW (Bag of Words), finding that the number of visual words most suitable for classification was between 20 and 30. The method with which the best results were obtained was the KNN; using the three closest neighbors, with an accuracy of 97%
  • Miniatura
    Publicación
    Acceso abierto
  • Miniatura
    Publicación
    Acceso abierto
    Diseño, implementación y validación de un algoritmo de geolocalización de alta precisión para un vehículo de navegación terrestre tipo Rover de la Universidad de Ibagué
    (Universidad de Ibagué., 2018) Bolívar Marín, Fabián; Barrero Mendoza, Oscar
    This thesis shows the design, implementation and validation of two high precision geolocation algorithms for a land vehicle of the University of Ibagué. This rover is designed to be used in projects related to precision agriculture, a line of research in which the D + TEC group is currently working. The document illustrates two alternatives that were developed to achieve the implementation of a position and orientation estimator for the aforementioned rover. The first alternative consisted of the design of a two-stage algorithm that integrates a Kalman filter assembled with an adaptive Kalman filter in the first stage and allows merging the data obtained from an Inercial Measurement Unit housed in a navigation card Navio2 with encoder data installed on the axes of the rover wheels. The output of this stage feeds the second stage of the algorithm, developed through a Kalman filter integrating the data of a GPS and magnetometer installed also in the rover. The second alternative that was also implemented was a two-stage algorithm that integrated an extended Kalman filter with an adaptive one in the first stage and a conventional Kalman filter in the second stage merging the same data from the sensors mentioned in the first alternative. Finally, the results obtained are shown and a detailed analysis of what is found in each designed algorithm is made.
  • Miniatura
    Publicación
    Restringido