Techno-economic appraisal and machine learning-based gray wolf optimization of enhanced fuel cell integrated with stirling engine and vanadium-chlorine cycle

Abstract

Researchers' interest in Fuel Cells (FCs), a cutting-edge technology for producing heat and electricity simultaneously, has grown significantly in recent years. FC technology is a non-renewable yet unconventional distributed energy source with a number of benefits for the economic, environmental, and dependable operation of energy systems. In the present study, a highly efficient FC type is integrated with a Stirling engine and vanadium chlorine scheme. The proposed cycles are efficient not only in power generation but also in hydrogen production since it uses waste heat to generate hydrogen. The system is investigated from technical, economic, and environmental aspects through the scrutiny of parameters affecting the system's performance. A cutting-edge method of machine learning-based optimization with a gray wolf algorithm is used to identify the ideal solution point when different optimization goals are selected. The results indicate that the TOPSIS point matches the maximum efficiency and hydrogen production of 81% and 0.008 kg/s, and the ζ equals 0.21. Also, maximum net power output and hydrogen production of 7500 kW and 0.0045 kg/s happens in the TOPSIS point with the levelized cost of the products of 0.14 $/kWh.