Buscador

Encontrado(s) 2247974 resultado(s)
Encontrada(s) 224798 página(s)

Fault detection and identification methodology under an incremental learning framework applied to industrial electromechanical systems

  • Cariño Corrales, Jesús Adolfo
Condition Based Maintenance is a program that recommends actions based on the information collected and interpreted through condition monitoring and has become accepted since a decade ago by the industry as a key factor to avoiding expensive unplanned machine stoppages and reaching high production ratios. Among the condition based maintenance strategies, data-driven fault diagnosis methodologies have gained increased attention because of the high performance and widen range of applicability due to less restrictive constrains in comparison to other approaches. Therefore, an increased effort is been made to develop reliable methodologies that could diagnose multiple known faults on a machine with initial applications in controlled environments like laboratory test benches. However, applying those methods to industry applications still represent an ongoing challenge due to the multiple limitations involved and the high reliability and robustness required. One of the most important challenges in the industrial sector refers to the management of unexpected events, in respect of how to detect new faults or anomalies in the machine. In addition, the information initially available of the monitored industrial machine is usually limited to the healthy condition, therefore is not only necessary to detect these new scenarios but also incorporate this information to the initial base knowledge. In this regard, this thesis present a series of complementary methodologies that leads to the implementation of a fault detection and identification system capable to detect multiple faults and new scenarios of industrial electromechanical machines under an incremental learning framework to include the new scenarios detected to the initial base knowledge while achieving a high performance and generalization capabilities. Initially, a methodology to increase the performance of novelty detection models to detect unexpected events in electromechanical system is proposed. Then, a methodology to implement a sequential fault detection and identification system composed by a novelty detection and a fault diagnosis stages with high accuracy is proposed. Finally, two different methodologies are proposed to provide the sequential fault detection and identification system the capacity to include new scenarios to the base knowledge. The proposed methodologies have been validated by means of experimental data of laboratory test benches and industrial electromechanical systems., "Mantenimiento basado en la condición" es un programa que recomienda una serie de medidas preventivas basadas en la información recopilada e interpretada mediante el constante monitoreo de la condición de la maquinaria y ha sido aceptado desde hace una década por la industria como un factor clave para evitar paradas no planificadas de la maquinaria y alcanzar altos índices de producción. Entre las estrategias de mantenimiento basadas en la condición, las metodologías de diagnóstico de fallos basadas en datos han recibido mucha atención debido al alto rendimiento y amplio rango de aplicabilidad, esto se debe que cuentan con menos limitaciones en comparación con otros enfoques. Por lo tanto, se ha hecho un mayor esfuerzo para desarrollar metodologías fiables que puedan diagnosticar múltiples fallos conocidas en una máquina, siendo aplicado inicialmente en entornos controlados como bancadas de laboratorio. Sin embargo, aplicar estos métodos en la industria sigue representando un desafío debido a las múltiples limitaciones implicadas y la alta fiabilidad y robustez requeridas. Uno de los desafíos más importantes en el sector industrial consiste en la gestión de eventos inesperados, específicamente en cómo detectar nuevos fallos o anomalías máquina. Además, la información inicialmente disponible de la máquina industrial monitorizada se limita generalmente al estado sano, por lo tanto, no sólo es necesario detectar estos nuevos escenarios, sino también incorporar esta información al conocimiento base inicial. En este sentido, esta tesis presenta una serie de metodologías complementarias que conducen a la implementación de un sistema de detección e identificación de fallos capaz de detectar múltiples fallos y nuevos escenarios de máquinas electromecánicas industriales en un marco de aprendizaje incremental para incluir los nuevos escenarios detectados al conocimiento base inicial manteniendo un alto rendimiento y capacidades de generalización. Inicialmente, se propone una metodología para aumentar el rendimiento de los modelos de detección de novedad para detectar eventos inesperados en el sistema electromecánico. Después, se propone una metodología para implementar un sistema secuencial de detección e identificación de fallas con alta precisión compuesto por una etapa de detección de novedades y otra de diagnóstico de fallos. Finalmente, se proponen dos metodologías diferentes para proporcionar al sistema secuencial de detección e identificación de fallas la capacidad de incluir nuevos escenarios al conocimiento base. Las metodologías propuestas han sido validadas mediante datos experimentales de bancadas de laboratorio y sistemas electromecánicos industriales.
Proyecto:


DopLa solar cells with texturized front surface

  • Martín García, Isidro
  • Coll Valentí, Arnau
  • López Rodríguez, Gema
  • Ortega Villasclaras, Pablo Rafael
  • López González, Juan Miguel
  • Alcubilla González, Ramón
In this work, we report on improving efficiency of DopLa cells fabricated on p-type substrates. This type of solar cells has all the highly-doped regions based on laser doping from dielectric films resulting in a very simple fabrication process. Depending on the dopant type, emitter regions or high/low doping junctions related to base contacts can be created. The emitter regions are located at the rear surface in order to be contacted by a continuous metal film without penalizing in shadowing losses, while the front surface shows a typical finger grid configuration with the base contacts under the metal. In a previous work, the reported efficiency was limited by optical losses at the front planar surface. As a consequence, we focus on the introduction of a texturized front surface to the device. Firstly, we characterize the contact formation by laser processing on texturized surfaces by SEM image showing that the size of the contacted region is difficult to determine. By measuring contact resistance and surface recombination velocity, we deduce that the laser process of such surfaces leads to a contacted region which is smaller than the one where passivation is lost. The obtained information is included in 3D simulations to get the optimum size of the contacts, i.e. optimum laser power. Additionally, a new front grid metallization is introduced in order to reduce shadowing. Due to the rear emitter configuration of these devices, front surface recombination is crucial for collecting photogenerated carriers. Thus, optimum laser power is very close to the minimum to obtain a reliable contact. Finally, 2x2 cm 2 solar cells are fabricated with a best efficiency of 17.0 %., Peer Reviewed
Proyecto:


Preliminary studies of moored power cables

  • Arbós, Alejandro
  • Prat Farran, Joana d'Arc
  • Río Fernandez, Joaquín del
  • Sales Casals, Lluís Ramon
New green energy sources deployed at sea, in mobile platforms, will use power cables in order to transport the energy generated at sea surface to the bottom. Theses power cables will be exposed to the dynamic behaviour of the platform movements, due to waves, currents and wind. A preliminary study of the static behaviour of these cables in function of parameters like mass, bending stiffness, length, water density or seabed friction is presented in this article. Simulations are been done with Orcaflex 9.4 environment. Three different cables have been simulated to observe their deformation and forces., Peer Reviewed
Proyecto:


Análisis del régimen general de vientos en el Mediterráneo : Su relación con episodios meteorológicos extremos

  • Ferrer Sundahl, Carlos
La meteorología del mar Mediterráneo siempre ha destacado por su imprevisibilidad, su bravura durante episodios meteorológicos extremos y por tener cambios radicales en las condiciones atmosféricas en periodos muy cortos de tiempo. Además de sus conocidos contrastes también posee unos regímenes de vientos bastante característicos en función de la zona y la época del año. Son bien conocidos en el norte de Cataluña los episodios de tramontana, los levantes en el Estrecho de Gibraltar o el mistral en el Golfo de León y en la zona del Delta del Ebro. Se puede llegar a pensar que estos vientos son fruto del azar, pero realmente el viento del Mediterráneo se rige por unas leyes muy concretas que si son conocidas permiten llegar a prever lo que va a pasar. El objetivo de este trabajo consiste en entender cuáles son estas leyes fundamentales que gobiernan la dinámica del Mediterráneo a través del conocimiento de sus particularidades geográficas, atmosféricas y locales, con el fin de entender cuáles son los vientos reinantes que se establecen en determinadas zonas de la cuenca durante el transcurso de las estaciones y las consecuencias que acarrean.
Proyecto:


Estudio de alternativas para pavimentos urbanos

  • Camargo Ramírez, Roberto José
Uno de los problemas en las ciudades es la densificación de los núcleos urbanos, debido a la migración de la población rural hacia las ciudades. La sostenibilidad se vuelve un aspecto importante en los nuevos desarrollos de las ciudades. Teniendo en cuenta que un gran porcentaje de la superficie urbana se encuentra cubierta por pavimento, es necesario el desarrollo de nuevas tecnologías y materiales para que estos pavimentos contribuyan al objetivo de la sostenibilidad. De acuerdo con esto, este Trabajo Final de Máster se enfocará en los pavimentos urbanos.
Proyecto:


Automatització d'oficines

  • Ribera Bergós, Joan Ricard
Antes de actuar nos es preciso reflexionar sobre la función de la oficina. La oficina es un centro de recogida, manipulación, proceso y emisión de información o documentos producto, con un evidente valor añadido. La información o los documentos, así como las fuentes de recogida y el proceso o manipulación, pueden efectuarse sobre distintos medios, los más corrientes de los cuales son el texto, la grafia, la imagen, el sonido o la voz, o incluso datos instrumentales (topografía, ingenieria,medicina, etc.).
Proyecto:


Payload bay design and manufacturing for a fixed wing UAV with VTOL capability

  • Mateu Civera, Antoni
The company Venturi is designing a drone for inspection, and it has to be able to carry some different payloads as a LiDAR, electro-optical and thermal sensors and a gas sensor to methane leakages. All these payloads need a mount to be held to the drone, so this thesis will explain how all these mounts were designed and the future steps to continue improving these fixations. The drone will be sold, and the company will also operate with it. My labour in the company consisted in to do market research and a study of the different payloads to be able to implement it in the drone. In this thesis, there is a review of the market research but is more focused on all the mounts of the different payloads that will be used in the aerial inspections to be sure that these payloads will be well fixed. There are also some other components that were designed and constructed for the drone.
Proyecto:


Alternative processing for micro rain radar (MRR) observations

  • Garcia Benadí, Albert
  • Bech, Joan
  • González Herrero, Sergi
  • Río Fernandez, Joaquín del
The most common function of weather radars is to provide a description of the precipitation field, typically in four dimensions: temporal evolution of a 3D field, including characteristics of precipitation and rainfall intensity. Some radars, as the one used in this study, are designed to observe only vertical profiles. The radar used in this work is a Frequency Modulated Continuous Wave Radar (FMCW) (Strauch et al, 1976) radar, unlike traditional pulsed radar systems. The main difference is that FMCW systems transmit continuously and can change their frequency modulation to change the vertical resolution while the pulsed radar emits a great power in short time a pulse. Pulsed transmitters are typically used in weather radars systems working at mid and long ranges while FMCW systems are used in low power transmitters often for short-range applications. The MRR manufacturer offers the equipment with its own software of analysis, but some researchers (for example Maahn and Kollias (2012), Adirosi et al (2016) among others) have proposed other approaches. The premise of the software is to consider that the raindrop is falling at terminal velocity, which is usually valid for stratiform precipitation, but not for convective storms. Another hypothesis is that the hydrometeors always are in liquid phase, but in numerous occasions, this is not the case. The shape of ice crystals or snowflakes is completely different from water drops, also the terminal velocity, and the complex refractive index. The aim of this study is to propose a new technique to process data for the raw MRR's files to achieve a better active and configurable noise detection. The technique is related to that described by Maahn and Kollias (2012) but under the assumption of hydrometer fall terminal speed, thus Mie scattering is used. The different parameters analysed include: Signal detection, Active noise level determination, Spectrum average, Dealiasing processing (Velocity unfolding), Drop size distribution, Path Integrated rain attenuation and Reflectivity calcula- tion. The presentation will compare and discuss results obtained with the new methodology and other existing approaches. This study was partly supported by projects CGL2015-65627-C3-2-R (MINECO/FEDER) and CGL2016-81828-REDT (MINECO).
Proyecto:


La línea orbital de ferrocarriles en Barcelona

  • Moliner Martínez, Jordi
En la actualidad las conexiones por ferrocarril, en servicios de cercanias, entre el norte y el sur de Barcelona, se realizan mediante lineas que discurren por el interior de esta población. Ello se traduce en problemas de capacidad que limitan la calidad del servicio ferroviario. En este contexto, desde hace algun tiempo, se analizan las posibilidades técnicas y el interés económico de construir una nueva linea, podriamos denominar de circunvalación, que evite el paso por el centro de Barcelona. El presente TFM tiene por finalidad profundizar en este análisis.
Proyecto:


Tracking and approaching persons using Deep Learning techniques

  • Laplaza Galindo, Javier
This project proposes a solution in order to enable a social robot to approach and follow one specific person using a vision based system. The idea is to introduce this features to the robot so that it will be able, int he futur, to autonomously interact with people. To do so, the algorithms developed in the project use Convolutional Neural Networks to identify where is the person given an image provided by the robot camera. In order to accomplish these tasks, two algorithms are created: an object detector using YOLO algorithm and an object tracker using a Siamese network. In order to fully understand how these algorithms work, the methods and architectures on which they are based are explained. Also, one of the algorithms is attempted to train with Google Colaboratory, even though the training results aren’t used in the final implementation. Different recordings are filmed teleoperating the robot simulating real approaching and following operations. Each recording is then labelled frame by frame to use this data in the training. Since the results of the training aren’t used in the final implementation, the recordings are used to test how well the final implementation is able to track the target in a frame. Therefore, different metrics are evaluated in the recordings, separating the ”approaching operation” videos from the ”following operation” videos, thus obtaining separated results for the two operations. Also, since the recordings where filmed considering different light conditions, it is possible to analyze how light variations affect the results when performing both approaching and following operations. These algorithms are run and tested in a Jetson TX2, using the GPU of the embedded device to enhance the performance of the algorithms. The implementation is build using PyTorch
Proyecto:


Buscador avanzado