Pasar al contenido principal

TECNICAS DE ANALITICA VISUAL PARA LA MEJORA DE LA EFICIENCIA EN PROCESOS Y EDIFICIOS

DPI2015-69891-C2-2-R

•
Nombre agencia financiadora Ministerio de Economía y Competitividad
Acrónimo agencia financiadora MINECO
Programa Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Convocatoria Proyectos I+D+i Retos de Investigación
Año convocatoria 2015
Plan Estatal 2013-2016 Plan Estatal de Investigación Científica y Técnica y de Innovación
Unidad de gestión Dirección General de Investigación Científica y Técnica
Centro beneficiario UNIVERSIDAD DE OVIEDO
Identificador persistente http://dx.doi.org/10.13039/501100003329

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

A Deep Learning Approach for Fusing Sensor Data from Screw Compressors

  • Domínguez González, Manuel
  • Alonso Castro, Serafín
  • Pérez López, Daniel
  • Morán Álvarez, Antonio
  • Fuertes Martínez, Juan José
  • Diaz Blanco, Ignacio
  • Domínguez González, Manuel
[EN] Chillers are commonly used for thermal regulation to maintain indoor comfort in medium and large buildings. However, inefficiencies in this process produce significant losses, and optimization tasks are limited because of accessibility to the system. Data analysis techniques transform measurements coming from several sensors into useful information. Recent deep learning approaches have achieved excellent results in many applications. These techniques can be used for computing new data representations that provide comprehensive information from the device. This allows real-time monitoring, where information can be checked with current working operation to detect any type of anomaly in the process. In this work, a model based on a 1D convolutional neural network is proposed for fusing data in order to predict four different control stages of a screw compressor in a chiller. The evaluation of the method was performed using real data from a chiller in a hospital building. Results show a satisfactory performance and acceptable training time in comparison with other recent methods. In addition, the model is capable of predicting control states of other screw compressors different than the one used in the training. Furthermore, two failure cases are simulated, providing an early alarm detection when a continuous wrong classification is performed by the model., SI, This research was funded by the Spanish Ministry of Science and Innovation and the European Regional Development Fund under project DPI2015-69891-C2-1-R/2-R., Ministerio de Economía y Competitividad
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

A Data-Driven Approach for Enhancing the Efficiency in Chiller Plants: A Hospital Case Study

  • Alonso Castro, Serafín
  • Morán Álvarez, Antonio
  • Prada Medrano, Miguel Ángel
  • Reguera Acevedo, Perfecto
  • Fuertes Martínez, Juan José
  • Domínguez González, Manuel
This article belongs to the Special Issue Energy Performance and Indoor Climate Analysis in Buildings), [EN] Large buildings cause more than 20% of the global energy consumption in advanced countries. In buildings such as hospitals, cooling loads represent an important percentage of the overall energy demand (up to 44%) due to the intensive use of heating, ventilation and air conditioning (HVAC) systems among other key factors, so their study should be considered. In this paper, we propose a data-driven analysis for improving the efficiency in multiple-chiller plants. Coefficient of performance (COP) is used as energy efficiency indicator. Data analysis, based on aggregation operations, filtering and data projection, allows us to obtain knowledge from chillers and the whole plant, in order to define and tune management rules. The plant manager software (PMS) that implements those rules establishes when a chiller should be staged up/down and which chiller should be started/stopped according different efficiency criteria. This approach has been applied on the chiller plant at the Hospital of León., SI, This research was funded by the Spanish Ministerio de Ciencia e Innovación and the European FEDER under project CICYT DPI2015-69891-C2-1-R/2-R.
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Feature Extraction from Building Submetering Networks Using Deep Learning

  • Morán Álvarez, Antonio
  • Alonso Castro, Serafín
  • Pérez López, Daniel
  • Prada Medrano, Miguel Ángel
  • Fuertes Martínez, Juan José
  • Domínguez González, Manuel
[EN] The understanding of the nature and structure of energy use in large buildings is vital for defining novel energy and climate change strategies. The advances on metering technology and low-cost devices make it possible to form a submetering network, which measures the main supply and other intermediate points providing information of the behavior of different areas. However, an analysis by means of classical techniques can lead to wrong conclusions if the load is not balanced. This paper proposes the use of a deep convolutional autoencoder to reconstruct the whole consumption measured by the submeters using the learnt features in order to analyze the behavior of different building areas. The display of weights and information of the latent space provided by the autoencoder allows us to obtain precise details of the influence of each area in the whole building consumption and its dependence on external factors such as temperature. A submetering network is deployed in the León University Hospital building in order to test the proposed methodology. The results show different correlations between environmental variables and building areas and indicate that areas can be grouped depending on their function in the building performance. Furthermore, this approach is able to provide discernible results in the presence of large differences with respect to the consumption ranges of the different areas, unlike conventional approaches where the influence of smaller areas is usually hidden., SI, This research was funded by the Spanish Ministry of Science and Innovation and the European Regional Development Fund under project DPI2015-69891-C2-1-R/2-R and the University of León.
BULERIA. Repositorio Institucional de la Universidad de León
Publicación Artículo científico (JournalArticle)

Interactive data visualization of chatter conditions in a cold rolling mill

  • Pérez López, Daniel
  • Díaz Blanco, Ignacio
  • Cuadrado Vega, Abel Alberto
  • Rendueles, José Luis
  • García Pérez, Diego
[EN] Rolling of flat steel products is an industrial process in the field of metalworking where two or more pairs of rolls reduce the thickness of a steel strip to produce a uniform thickness material. Despite it has been studied for many years, there are still unpredictable problems that can affect the final quality of the product. One of them is the so-called chatter, that is a powerful self-excited vibration that appears suddenly and limits the productivity of the process. In this paper, a visual analytics approach is considered for exploratory analysis in order to discover and understand the factors and conditions under which chatter appears. An interactive web-based interface is presented here which allows the user to explore a map of dynamical conditions and visualize relevant details of each chatter onset. A validation case is performed using real data where normal/fault conditions have been identified automatically. By means of interactive exploration, the tool allows to refine an automatic chatter detection method. Moreover, it is shown to reveal correlations between variables, providing in some expected cases data-based confirmation, but also revealing less obvious relationships. Finally, it provides context, allowing to carry out comparative analysis, both qualitative and quantitative, for different subsets of coils (e.g. different years) as well as for different working conditions., SI, The authors would like to thank financial support from the Spanish Ministry of Economy (MINECO), FEDER funds from the EU under grant DPI2015-69891-C2-1/2-R and from the Principado de Asturias government through the predoctoral grant Severo Ochoa.