Development and neural network optimization of a renewable-based system for hydrogen production and desalination

Adel Balali, Mohammad Javad Raji Asadabadi, Javad Rezazadeh Mehrenjani, Ayat Gharehghani and Mahdi Moghimi

Renewable Energy, 2023, vol. 218, issue C

Abstract: This study introduces an integrated system based on geothermal and solar energy to provide useful products such as electricity, freshwater, and hydrogen. In the proposed system, a solar unit including parabolic trough collectors has been used to improve the performance of the system and increase the mentioned products. The low-temperature geothermal stream returns to the ground after passing through a thermoelectric generator unit. A combination of Rankine and organic Rankine cycles is used to supply electricity and run the water electrolysis unit. This study aims to address the inefficient heat recovery in a combined solar and geothermal resource system by utilizing waste heat to generate clean hydrogen. A parametric study and sensitivity analysis are considered to investigate the effect of design parameters on the main outputs of the system. After evaluating the system from energy, exergy, and economic perspectives, a multi-objective optimization process with a combination of artificial neural network and genetic algorithm was performed on the system. The optimization problem is divided into two cases (scenarios). Each case considers energy efficiency and total cost rate as objective functions. In addition, hydrogen and freshwater production rates are considered as the third objective function in cases A and B, respectively. The optimization results showed that in case A, the optimal values of exergy efficiency, hydrogen production, and total cost rate are 15.54%, 6.18 kg/h, and 85.9 $/h, respectively. Also, in case B, values of 15.09%, 3527.79 kg/h, and 89.44 $/h are calculated for exergy efficiency, freshwater production, and total cost rate, respectively. A case study conducted in Tehran revealed that the peak production of various products is observed in May, which leads to the production of 623.14 kW of electricity, 5.35 kg/h of hydrogen, and 1948.9 kg/h of freshwater in the base condition.

Keywords: Renewable energy; Multi-generation system; Machine learning; Sensitivity analysis; Freshwater production; Hydrogen production (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0960148123012715
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:renene:v:218:y:2023:i:c:s0960148123012715

DOI: 10.1016/j.renene.2023.119356

Access Statistics for this article

Renewable Energy is currently edited by Soteris A. Kalogirou and Paul Christodoulides

More articles in Renewable Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().