RT info:eu-repo/semantics/bookPart
T1 Improving Energy Efficiency in Buildings Using Machine Intelligence
A1 Sedano, Javier
A1 Villar, José Ramón
A1 Curiel Herrera, Leticia Elena
A1 Cal, Enrique de la
A1 Corchado, Emilio
K1 Feature selection
K1 Heating System
K1 Machine Intelligence
K1 Improve Energy Efficiency
K1 Indoor Temperature
K1 Informática
K1 Computer science
AB Improving the detection of thermal insulation in buildings –whichincludes the development of models for heating and ventilation processes andfabric gain - could significantly increase building energy efficiency and substantially contribute to reductions in energy consumption and in the carbonfootprints of domestic heating systems. Thermal insulation standards are nowcontractual obligations in new buildings, although poor energy efficiency is often a defining characteristic of buildings built before the introduction of thosestandards. Lighting, occupancy, set point temperature profiles, air conditioningand ventilation services all increase the complexity of measuring insulationefficiency. The identification of thermal insulation failure can help to reduceenergy consumption in heating systems. Conventional methods can be greatlyimproved through the application of hybridized machine learning techniques todetect thermal insulation failures when a building is in operation. A three-stepprocedure is proposed in this paper that begins by considering the local buildingand heating system regulations as well as the specific features of the climatezone. Firstly, the dynamic thermal performance of different variables is specifically modelled, for each building type and climate zone. Secondly, CooperativeMaximum-Likelihood Hebbian Learning is used to extract the relevant features.Finally, neural projections and identification techniques are applied, in order todetect fluctuations in room temperatures and, in consequence, thermal insulation failures. The reliability of the proposed method is validated in three winterzone C cities in Spain. Although a great deal of further research remains to bedone in this field, the proposed system is expected to outperform conventionalmethods described in Spanish building codes that are used to calculate energeticprofiles in domestic and residential buildings.
PB Springer Nature
SN 0302-9743
YR 2009
FD 2009
LK http://hdl.handle.net/10259/8580
UL http://hdl.handle.net/10259/8580
LA eng
NO Trabajo presentado en: International Conference on Intelligent Data Engineering and Automated Learning, 2009
DS Repositorio Institucional de la Universidad de Burgos
RD 10-may-2024