Machine learning prediction approach for dynamic performance modeling of an enhanced solar still desalination system

Abstract

An enhanced design for a solar still desalination system which has been proposed in the previously conducted study of the research team is considered here, and the experimental data obtained during a year are employed to develop ANN models for that. Different types of artificial neural network (ANN), as one of the most popular machine learning approaches, are developed and compared together to find the best of them to predict the hourly produced distillate and water temperature in the basin, which are two key performance criteria of the system. Feedforward (FF), backpropagation (BP), and radial basis function (RBF) types of ANN are examined. According to the results, by having the coefficients of determination of 0.963111 and 0.977057, FF and RBF types are the best ANN structures for estimation of the hourly water production and water temperature in the basin, respectively. In addition, the annual error analysis done for the data not used to develop ANN models demonstrates that the average error in prediction of the hourly distillate production and water temperature in the basin varies from 9.03 and 5.13% in January (the highest values) to 4.06 and 2.07% in July (the lowest values), respectively. Moreover, the error for prediction of the daily water production is in the range of 2.41 to 5.84% in the year.