Statistical investigation of a dehumidification system performance using Gaussian process regression

Abstract

Swift performance assessment of dehumidification systems, in design stage and while operation of the system is of substantial importance for commercialization and wide implementation of this technology. This paper presents a novel statistical model, employing Gaussian Process Regression (GPR) to investigate performance of a solar/waste energy driven dehumidification/regeneration cycle with a solid adsorbent bed. The statistical model takes thousands of operating conditions derived from a numerical model to predict the performance of the system. This predictive tool directly correlates the main operating parameters with the performance parameters of the system. The operating parameters considered in this study are: temperature, relative humidity and flow rate of process air, temperature of regeneration air, length of the desiccant bed, solar radiation intensity and operating time, and the selected performance parameters are: moisture extraction efficiency for the dehumidification cycle and moisture removal efficiency for the regeneration cycle. The model is evaluated by three metrics, namely: root mean square error (RSME), mean absolute percentage error (MAPE), and coefficient of determination (R2). The maximum RSME and MAPE for moisture extraction are only 0.045, 0.21%, and for moisture removal efficiencies are 0.082 and 0.39%, respectively, while the R2 value is derived as 0.97. The developed model is used to investigate the impact of four selected operating parameters on system performance. Additionally, the system performance is predicted for randomly generated operating conditions as well as warm and humid climates. The developed GPR model provides a swift and highly accurate predictive tool for design of the dehumidification systems and for commercialization of the investigated dehumidification systems.