Improving the detection of thermal insulation failures in buildings includes the development of models for heating process and fabric gain -heat flux
through exterior walls in the building-. Thermal insulation standards are now
contractual obligations in new buildings, the energy efficiency in the case of
buildings constructed before the regulations adopted is still an open issue, and
the assumption is that it will be based on heat flux and conductivity measurement. A three-step procedure is proposed in this study that begins by considering the local building and heating system regulations as well as the specific features of the climate zone. Firstly, the dynamic thermal performance of different
variables is specifically modeled. Secondly, an exploratory projection pursuit
method called Cooperative Maximum-Likelihood Hebbian Learning is used to
extract the relevant features. Finally, a supervised neural model and identification techniques are applied, in order to detect the heat flux through exterior
walls in the building. The reliability of the proposed method is validated for a
winter zone, associated to several cities in Spain.
