Thermodynamic Analysis and Neural Network Model of Open Cycle Desiccant Cooling Systems with Silica Gel.

This paper examines three different approaches for desiccant wheel performance of Type I silica gel as a component of the desiccant cooling system combined with evaporative coolers. A neural network model based on the training of a black box model with real data was developed and compared to a non-linear analogy method as well as a prediction method based on experimental results for the state of air at the process and regeneration stream. The key parameters are the effectiveness of the desiccant wheel, the effectiveness of the sensible heat exchanger and of the evaporative cooler as well as the regeneration temperature, the sensible heat factor of the room and the ratio of the mass flow rate in the regeneration and process stream. The results of this analysis reveal that all the parameters investigated affect the performance of the desiccant cooling system in all models. Apart from components effectiveness, low regeneration temperatures, suitable for silica gel, associated with sources of waste heat as the regeneration energy source, have been investigated. The proposed Neural Network Model for Desiccant Cooling Systems follows satisfactorily the model that is based on the interpolation of experimental data obtained from the industry. [ABSTRACT FROM AUTHOR]