Artificial intelligence for predicting solar still production and comparison with stepwise regression under arid climate

摘要: Forecasting the efficiency of solar still production (SSP) can reduce capital risks involved in a desalination project. Solar is an attractive method water and offers more reliable source. In this study, to estimate SSP, we employed data obtained from experimental fieldwork. SSP assumed be function ambient temperature, relative humidity, wind speed, radiation, feed flow rate, temperature water, total dissolved solids water. back-propagation artificial neural network (ANN) models with two transfer functions were adopted for predicting SSP. The best performance was by ANN model one hidden layer having eight neurons which hyperbolic function. Results compared those stepwise regression (SWR) model. produced accurate results SWR all modeling stages. Mean values coefficient determination root mean square error 0.960 0.047 L/m 2 /h, respectively. Relative errors predicted about ±10%. conclusion, showed greater potential accurately whereas poor performance.