Contribution to the development of a thermal comfort model using artificial neural networks to predict thermal sensation
Project Description
An essential role in sustainable building planning plays the so-called thermal comfort of humans. The exploration of first comfort or human models has its origins in aerospace engineering and found its way into the building sector in the 1970s. The first standardised model is based on investigations in closed, thermally uniform rooms. In recent years, more unconditioned and personalised ventilation measures have become more important again, as both the energy efficiency of buildings and the individual thermal comfort could be improved. Various physiological models have been developed in recent decades to illustrate the associated effects, but there is still a lack of reliable derivation or prediction of the thermal sensation. In this dissertation, a model will be developed on the basis of a physiological-thermal human model and be using artificial neural networks to be able to make statements about the thermal perception of building users. The meaningful use of this numerical method requires a significant amount of different experimental data. For the choice of the input features as well as network architecture causal interactions of the human receptors and neural pathways should be considered.
