A quadruple power generation system for very high efficiency and its performance optimization using an artificial intelligence method

The demand for highly efficient power generation systems is ever escalating to reduce carbon dioxide emissions. This study proposes a novel quadruple power generation system, investigates its performance characteristics, and optimizes its efficiency using an artificial intelligence method based on the results of a thermodynamic simulation. The quadruple system integrates four power blocks consisting of a solid oxide fuel cell (SOFC), a molten carbonate fuel cell (MCFC), a gas turbine, and an organic Rankine cycle to achieve high efficiency. A parametric analysis of the main design parameters was conducted. An artificial intelligence method combining an artificial neural network and a genetic algorithm was devised to avoid the slow speed of the calculation for the thermodynamically optimal solution and used to find the optimized design parameters that produce the maximum efficiency. The results of the thermodynamic parametric analysis were used to train the artificial neural network. The results of the optimization method were verified through comparison with the results of thermodynamic analysis. A very high maximum efficiency of 78.1% was predicted. The performance of the optimized quadruple system was examined by comparing it with that of other hybrid power systems.