Authors: Rousseau Clément, Jean-Louis Comlan Fannou, Louis Lamarche, Stanislaw Kajl, and Mohamed Ouzzane
Geothermal heat pump technology is currently one of the most interesting technologies used to heat buildings. There are two designs used in the industry: geothermal heat pump using a secondary ground loop and Direct Expansion (DX) ground source heat pump. The latter is less used, with one of the possibly reasons being that no model of estimation has been developed for the industry. In this study, we used a finite element model of a DX geothermal heat pump in heating mode with R22 and use the result to develop a fast neural networks (ANN) model. After this, we used this model to develop a design model to have a fast estimation of the minimal depth of a pipe with some imposed parameters. This model is a first step to develop a unique item for the development of DX ground source heat pump in the industry.
Keywords: Direct Expansion geothermal heat pump, modeling, Artifical neural network (ANN), fast design method