In the intensive care unit of hospitals, retaining the relative humidity at a comfortable level, removing air-borne pollutants or microbial bacteria, filtering ambient air, and eradicating the condensed water vapor are crucial. Therefore, a desiccant coated energy exchanger (DCEE) is designed for fulfilling this purpose. In the present investigation, a quick prediction of the exit parameters of desiccant coated energy exchanger is made using three data-driven models: artificial neural network artificial intelligence tool (ANN-AI), k-nearest neighbors machine learning tool (KNN-ML), and principal component analysis (PCA). From the model validation and error analysis, it has been found that the ANN-AI tool predicts the exit parameters with the least error. The advantages of ANN -AI tool are its exceptional learning capability and fast output prediction. Artificial neural networks are adaptive and flexible. ANN obtains information from their surroundings by adapting to input and output parameters, thus solving complicated problems which are challenging to handle. The design parameters chosen for designing the desiccant coated energy exchanger are tube diameter, fin depth, thickness of coated desiccant, and flow channel length. Silica gel is used as a desiccant-coated material. Thermal effectiveness and moisture effectiveness are chosen as performance parameters, inlet air humidity ratio, inlet air temperature, inlet cooling water temper-ature, liquid to air mass flow rate, and cycle time are chosen as inlet parameters and outlet air temperature, outlet cooling water temperature, outlet air humidity ratio as the exit parameters. Further, optimal and design operating parameters of the desiccant coated energy exchanger is predicted for a particular operating/design range utilizing the ANN-AI tool. Moreover, a case study has been carried out first by integrating a desiccant coated energy exchanger with a M-cooler and second by integrating a desiccant coated energy exchanger with a solar heater to assess the air conditioning and drying performance. The findings of the case study reveal that inlet cooling water temperature and inlet air temperature are the most significant parameters for the M-cooler and solar heater, which produce the lowest/largest temperature at the M-cooler/solar heater outlet, respectively.
