Experimental and theoretical evaluation of a hybrid solar still integrated with an air compressor using ANN

An experimental study has been performed to evaluate the single slope hybrid solar still integrated with heat pump (SSDHP). The purpose of this study is to determine the effectiveness of solar still and its modeling using artificial neural networks (ANNs) with the help of experimental data. Most influencing parameters (the solar radiation, glass cover temperature, basin temperature, water temperature and temperature of the evaporator) at an hour interval on the performance of hybrid solar still using ANNs model are discussed in this paper. Effect of an air compressor on the productivity of SSDHP and assess the sensitivity of the ANN predictions for different combinations of input parameters as well as to determine the minimum amount of inputs necessary to accurately model solar still a performance for the prediction of actual distiller output results. The experimental result SSDHP with air will give 100% higher yield as compared to the SSDHP without air but SSDHP dramatically maintains its lead by 25% at 9 h. While this duration maximum difference in yield of SSDHP with and without air observed that SSDHP with air gives 34.61% higher yield as compared to without air during 11 to 12 hour due to the influence of basin temperature. SSDHP with air was recorded 33.33% higher yield as compared to the SSDHP without air. For training, validation, test and all, value of R is equal to 0.99454, 0.99121, 0.99974 and 0.99374 respectively in ANNs proposed model which shows very good agreement with the experimental result. Satisfactory results for the SSDHP with air will pave the way to predict performance result for different climate regimes, with sufficient input data, the ANN method could be extended to predict the performance of other solar still designs also.