Ingeniería en Sistemas, Electrónica e Industrial
Permanent URI for this communityhttp://repositorio.uta.edu.ec/handle/123456789/1
Browse
15 results
Search Results
Item Aplicación del algoritmo de aprendizaje por refuerzo Q-Learning para la generación de trayectorias óptimas en plataformas robóticas(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Tecnologías de la Información, 2024-09) Moya Quinatoa, Kevin Alejandro; Álvarez Mayorga, Edison HomeroTechnological innovation is fundamental for business development and efficiency in Industry 4.0, which demands staying updated with the latest technologies. The rapid growth in the use of artificial intelligence (AI) offers high benefits and low operational costs, creating more stable and automated work environments. However, one of the greatest challenges in applying AI is the complexity of trajectory planning for mobile robots, as their behavior varies according to the scenario and algorithms used, making it difficult to compare learning and performance between different methods. This research, as part of the project titled "Use of Deep Learning Techniques for Trajectory Planning of Mobile Robots within an Industrial Process," developed a trajectory planning algorithm using Q-learning and a multi-agent system that collaborate in decision-making. This algorithm employs odometry and laser sensor signals to manage states and rewards. Tests were conducted in a ROS simulation environment and replicated in a real-world scenario with the KUKA Youbot robot to implement the algorithm's actions. The simulated environment recreates a space with obstacles, where a master agent evaluates the decisions made by the odometry agent and the laser sensor agent to autonomously make a final decision. This contributes to the comparison of AI algorithms in terms of efficiency and effectiveness within the mentioned project, laying a foundation for future improvements in trajectory planning on mobile platforms.Item Aplicación del algoritmo de aprendizaje por refuerzo state-action-reward-state-action (SARSA) para la generación de trayectorias óptimas en plataformas robóticas(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Tecnologías de la Información, 2024-08) Sarzosa Villarroel, José Jeanpierre; Álvarez Mayorga, Edison HomeroPath planning for mobile robots is crucial to improve efficiency and reduce operational risks in the 4.0 industry. Companies are looking to implement advanced technologies such as artificial intelligence and reinforcement learning to automate industrial processes. This study was developed using the Kanban methodology, allowing the work to be broken down into several stages and tasks for monitoring and control. The implementation of the reinforcement learning algorithm SARSA to generate optimal trajectories in mobile robotic platforms is addressed, focusing on adapting and applying this "on-policy" algorithm, which updates its action values based on the direct experience with the environment. The experimental process included implementing the SARSA algorithm in a simulated environment for the autonomous-capable KUKA YouBot robot and a LIDAR sensor on an Nvidia Jetson AGX Orin module. The agent interacted with the environment through training episodes, learning through ε-greedy policy exploration and exploitation of the current and next actions available and computed based on the current and next states, respectively. The trained models were tested in a real environment with the KUKA YouBot robot to validate their performance under practical conditions. Finally, the results were integrated with a larger project using Deep Learning techniques to optimize autonomous trajectories in mobile robots within industrial processes, demonstrating the feasibility and advantages of using reinforcement learning algorithms in advanced robotic applications.Item Construcción de un robot cilíndrico educativo basado en conceptos de la Industria 4.0(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Ingeniería Industrial en Procesos de Automatización, 2023-09) Altamirano Paredes, Alex Germán; Salazar Logroño, Franklin WilfridoA robotic cell has been developed with a cylindrical educational robot that has three degrees of freedom to control the movement of three stepper motors. This system is based on a SIEMENS S7 1200 DC/DC/DC PLC. Different interfaces have been designed for the interaction between the user and the system, allowing to control each type of movement independently, either with simple or sequential movements, using the Jog mode, absolute and relative positioning. In addition, the cylindrical robot can carry out a color classification process, and due to its flexibility, it can be configured and programmed according to the user's needs to carry out activities such as palletizing, packaging or labeling. The didactic system has been tested and has shown an effectiveness of 97% in the color classification process, which highlights the precision of the didactic module in the implemented control. It is important to mention that industry 4.0 is based on the use of advanced technologies such as the Internet of Things (IoT) an d cloud computing, which demands the adoption of new platforms and standards. The research project focused on developing a dynamic and interactive monitoring system that allows interaction with the robotic cell. This makes it possible to monitor the roboti c cell from anywhere in the world.Item Sistema inteligente de monitoreo y control para la planta de tratamiento de agua potable “El Carrizal - Salcedo” basado en IOT e inteligencia artificial(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2023-03) Contreras Clavijo, Saul Alexis; Rojano Mueses, Xavier Gonzalo; Castro Martin, Ana PamelaDrinking water treatment is essential to ensure that the water we consume is safe and free of contaminants. The treatment process includes steps such as coagulation, flocculation, filtration, and disinfection; that help to eliminate impurities and harmful microorganisms.A prototype was designed which fulfills the functions of monitoring important variables for compliance with the regulations (temperature, flow, pH, conductance, turbidity), in addition to the control of pumps and solenoid valves that serve to control the supply of water that flows in each stage. The prototype was based on the three-layer IoT architecture. Two Arduino and ESP8266 microcontrollers are used as a processing unit, which collect information from the sensors and send it through the websocket protocol to a database hosted in a central server in the "Google platform" cloud. The control of solenoid valves and pumps are managed under the MQTT protocol, allowing rapid control in real time and dosage. The design of the web application was designed with the combination of the Grafana service and programming languages such as PHP, JavaScript, and HTML, for the representation of the behavior of the variables as a function of time. The system uses a Python script coded under a machine learning model (polynomial regression model), which processes the received temperature data to calculate the inactivation time and execute the dosing process. The prototype went through the design, implementation, and validation phases, which served to present a final proposal for implementation at the industrial level using equipment for the design of control architectures under the concept of industry 4.0. Proposal that was based on the architecture of the "El Carrizal" treatment plant, which is currently operationalItem Diseño de comunicación basado en contenedores para la industria 4.0(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Ingeniería Industrial en Procesos de Automatización, 2023-03) Puca Morales, Christian Emilio; Marcelo, GarcíaIt is necessary to know that industry 4.0 is based on the management of advanced technologies such as the Internet of Things (IoT) and cloud computing, which requires the adoption of new platforms and standards. The research project had as objective the development of an adaptable, dynamic and interactive control system to any process of a manufacturing industry. This interaction poses challenges in terms of security, scalability, and interoperability. The program design methodology was based on the parameters of the international standard IEC 61499 and uses containers to virtualize production processes, proposing the visualization of predictable errors during program management. The system design includes data acquisition via a CPU 1515SP PC2 F (IPC) and sending this data via Transmission Control Protocol/Internet Protocol (TCP/IP) to the running Docker containers. on the Raspberry Pi. The containers are stored in a repository and uploaded and downloaded to the card through FBs created for container control. The container based ommunication system allows monitoring the process through a graphical interface using the Message Queuing Telemetry Transport (MQTT) communication protocol. The results during the performance tests of the system behavior in relation to the expected outputs were that: for the TCP/IP protocol the response range was from 0.006 to 0.109 ms and for the MQTT protocol the interval was from 0.00095 µs to 0.000561 µs.Item Sistema de dosificación inteligente basado en el internet industrial de las cosas (IIOT) para los tanques de mezcla en la empresa Licoval S.A.S.(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Ingeniería en Electrónica y Comunicaciones, 2023-03) Pico Aldas, Marco Javier; Altamirano Meléndez, Santiago MauricioThis research project describes an intelligent dosing system, which is based on Industry 4.0 for the company Licoval S.A.S. The problem existed by having a manual control on and off the water and alcohol pumps, which fill the mixing tanks and through a visual control of the amount of liquid entering the tanks the pumps were turned off. This intelligent system consists of three layers. The first layer is the device layer, which is made up of ultrasonic sensors that are connected to an ESP8266 to wirelessly transmit the acquired data and actuators such as pumps and motors that are connected to the Amsamotion PLC. The second layer is processing, which establishes the communication between the PLC and the ESP32, this is a TTL serial communication for processing the acquired data and in turn establishes the functions to be performed. At this stage an HMI is elaborated, with the TM6138 display module for direct interaction with the operator. The third layer is the cloud, which through a SaaS infrastructure such as the Blynk IoT application platform, a dashboard was created to visualize the system data in real time, and this platform also provides historical data storage with reports and notifications of the actions performed in the intelligent dosing system. The project was implemented and tested for three weeks in which dosing was performed depending on the demand of the company's orders and the intelligent dosing was verified in the mixing tanks, supplying the raw material accurately and controlling the mixing times of the tanks.Item Optimización de trayectorias y tiempos para navegación autónoma de robots dentro de un proceso industrial aplicando Industria 4.0(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Maestría en Producción y Operaciones Industriales, 2022) Escobar Naranjo, Juan Camilo; García Sánchez, Marcelo VladimirThe present work is based on the design of a control algorithm for the optimization of trajectories and their travel time, implementing the model in a simulated environment for the autonomous navigation of robots, focusing for its development on industry-based tools. 4.0 and the application of neural networks to evaluate the actions executed by the controller in such a way that the error in the path of the trajectory is reduced, a reinforcement learning method is also added to the system that allows the model to know when an executed action was correct or incorrect, this is because its objective is to maximize its reward level, due to this the system will learn by exploring the environment to avoid obstacles and reach the objective, thus allowing the path to be followed to be optimal, The controller is based on the RMSprop optimizer algorithm, which allows it to give greater importance to the current paths than to the earlier, allowing learning to grow gradually, since over time the robot in its first training scenarios collides due to the fact that the amount of information is null or almost null, which is considered as an insufficient data source , however, as the training progresses, the robot, trying to increase its reward level, reaches the goal more frequently, giving greater importance to the routes where it began to learn than those where it collided. The communication of the system occurs through nodes controlled by a ROS master, this allows the exchange of information through messages published on topics, which gives rise to an adequate reading of the LIDAR sensor in charge of determining objects around the robot and a correct sending. of data by the DQN network to control the actions.Item Dispensador inteligente de frutos secos basado en arquitectura IoT para producción personalizada orientado a la industria 4.0 para la empresa Lula Organic(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Telecomunicaciones, 2022-09) Silva Naranjo, Bryan Patricio; Castro Martin, Ana PamelaThis research project focused on the implementation of an intelligent dispenser of four varieties of nuts categorized in three different sizes, based on an IoT architecture proposed by the researcher, which serves as a reference model for more IoT projects of interest, because, in the world of IoT, there is no standardized architecture that serves as the basis for projects focused on Industry 4.0. The architecture consists of three layers. The devices layer, which has sensors and actuators that allow the acquisition and visualization of data together with the actuation of mechanisms designed and printed in 3D that dispense the nuts in an appropriate way into a single common container. The data processing layer, which is from Fog computing, since the Arduino Mega microcontroller together with the NodeMCU are in charge of making decisions and sending valid data to the server, which is inside the third and last layer, the layer of services in the Cloud, which consists of multiple web programming files elaborated with knowledge in PHP, HTML, CSS, SQL and JavaScript that together form Web Interfaces so that both the owner of the company , like customers, have access to an IoT visualization environment, the same one that interacts with a database, registering multiple variables such as user data, orders and the values acquired by the smart dispenser sensors. It is expected that the design of this prototype will be helpful to Lula Organic company in terms of improving its services to customers, in such a way that their demand for participation and product customization is satisfied through a pleasant and innovative experience and that is willing to be rewarded with an additional charge in exchange for enjoying it, facts that are supported by the characteristics of Industry 4.0.Item Diseño de una metodología para implementación de indicadores de producción (KPIs) basado en conceptos de Industria 4.0(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera de Ingeniería Industrial en Procesos de Automatización, 2022-07) Guizado Freire, Diego Alexis; García Sánchez, Marcelo VladimirIndustry 4.0 has revolutionized the methods for automatize and analyze a process. As for example, adding indicators that show the right performance of a task. The present project includes the design of a methodology that contains stages of analysis of the process, design, implementation and validation to obtain an interface that displays key production indicators (KPIs) in a simple and friendly way. In this case the objects of study are level and pressure controls of the FESTO MPS PA Workstation Compact. This equipment is a didactic station very helpful in order to implement examples of efficiency indicators which are calculated by transferring information from the station to a raspberry pi using OPC and MQTT protocols. In addition a system is implemented in the cloud so the production indicator can be visible worldwide by applying the OPC UA protocol and exposing them in a web server named AnyViz. The results of the investigation show values for the efficiency indicators such as 100% and 66% for the level and pressure controls respectively.Item Internet de las cosas basado en redes definidas por software(Universidad Técnica de Ambato. Facultad de Ingeniería en Sistemas, Electrónica e Industrial. Carrera Ingeniería Electrónica y Comunicaciones, 2020-01) Chiliquinga Rodríguez, Cristian Santiago; Manzano Villafuerte, Víctor SantiagoEl presente proyecto diseña e implementa un testbed SDN-IoT, con el objetivo de mostrar la influencia que tienen las redes definidas por software sobre las aplicaciones del IoT aplicado a la industria 4.0. La arquitectura IoT-SDN es considerada como base para la implementación del prototipo, la cual se presenta en tres capas principales: capa de procesos, capa SDN y capa de aplicación IoT. En la capa de procesos se implementan 2 procesos de la industria 4.0, en la capa SDN se implementan dos puntos de acceso, un conmutador, un controlador SDN y una aplicación firewall para el control centralizado del tráfico sobre la red, finalmente en la capa de aplicación IoT se implementa una interfaz gráfica que permite controlar y monitorizar los procesos de la industria 4.0. En la implementación de la SDN se utilizan elementos de bajo costo y de código libre que son configura dos para trabajar con el protocolo OpenFlow en la versión 1.3, evidenciando el intercambio de mensajes entre los dispositivos de red y el controlador SDN en las pruebas realizadas.