Predictive model for assessing and optimizing solar still performance using artificial neural network under hyper arid environment

摘要: Abstract A mathematical model to forecast the solar still performance under hyper arid conditions was developed using artificial neural network technique. The expressed by different forms, water productivity (MD), operational recovery ratio (ORR) and thermal efficiency (ηth) requires ten input parameters. parameters included Julian day, ambient air temperature, relative humidity, wind speed, radiation, ultra violet index, temperature of feed brine water, total dissolved solids water. ANN trained, tested validated based on measured data. results showed that coefficient determination ranged from 0.991 0.99 0.94 0.98 for MD, ORR ηth during training testing process, respectively. average values root mean-square error all were 0.04 L/m2/h, 2.60% 3.41% Findings revealed effective accurate in predicting with insignificant errors.