Artificial neural network analysis of liquid desiccant dehumidifier performance in a solar hybrid air-conditioning system

A new solar hybrid liquid desiccant air conditioning system has been tested and simulated to investigate the technical feasibility of cooling systems for greenhouse applications using weather data for Malaysia. In this paper, experimental tests are carried out to investigate the performance of a counter flow dehumidifier using lithium chloride (LiCl) solution as the desiccant. A single and multilayer artificial neural network is used to predict the performance of the dehumidifier. Five parameters are used as inputs to the ANN, namely: air and desiccant flow rates, air inlet humidity ratio, and air and desiccant inlet temperatures. The outputs of the ANN are the temperature, humidity ratio, moisture removal rate, and the effectiveness. ANN predictions for these parameters are compared with the experimental values. The results show that the optimum testing model for moisture removal rate in the dehumidifier was the 5-5-5-1 structure with R2 = 0.91, whereas the optimum testing model for effectiveness was the 5-11-11-1 structure with R2 = 0.79. The maximum temperature and humidity ratio difference between the ANN model and experimental are 1.2 °C and 1.9 g/kg, respectively.