Techno-economic estimation of a non-cover box solar still with thermoelectric and antiseptic nanofluid using machine learning models

Abstract

• Robust Machine Learning models were used to study the performance of PDCBSSTCDAN. • The energy effiicncy prediction with high accuracy was obtained by MARS technique. • The EPR model was the best result in exergy efficiency estimation of PDCBSSTCDAN. • The ML models could effectively detect the variations in effective variables of PDCBSSTCDAN. • The mathematical expressions of ML models could cover limitations of previous studies. With rapid rise of advancement in soft computing models, application of Machine Learning (ML) techniques has increasingly grown to successfully evaluate thermal characterizations of solar systems in the last decade. Compared with related literature, this research aimed to obtain accurate relationships based on the ML techniques for predicting the energy and exergy efficiencies of the parabolic dish concentrator box solar still fitted with thermoelectric condensing duct and antiseptic nanofluid (PDCBSSTCDAN) system. Effective variables that affect energy and exergy efficiencies are listed as the nanoparticle volume fraction, fan power, solar radiation, basin temperature, nanofluid temperature, ambient temperature, wind velocity, and productivity. By adding 0.05% and 0.1% by volume of Fe 3 O 4 @Ag nanoparticles to the basin water, the maximum production of distilled water has increased by 410 (ml/m 2 ) and 580 (ml/m 2 ), respectively, compared to the pure fluid. At the most optimal case, the cost of producing distilled water and the payback period are 0.0072 ($/L/m2) and 141 day, respectively. After having completed the development of ML techniques, empirical equations based on nature-inspired properties of ML models were obtained to estimate energy and exergy efficiencies with a reasonable degree of accuracy level. Results of ML models indicated that Evolutionary Polynomial Regression (EPR) technique yielded comparatively performance in the prediction of energy (Root Mean Square Error [RMSE] = 0.827) and exergy (Root Mean Square Error [RMSE] = 0.1078) efficiencies than Multivariate Adaptive Regression Analysis (MARS), Gene-Expression Programming (GEP), and M5Model Tree (MT). ML techniques could outperform the results of the previous investigations in terms of precision level and applicability of proposed empirical equations. Overall, the proposed equations can be conveniently utilized to perceive the physical characterizations of solar still systems.