Multi-objective optimization of gradient porosity of gas diffusion layer and operation parameters in PEMFC based on recombination optimization compromise strategy

Proton exchange membrane fuel cell (PEMFC) is one of the most promising power energy sources in the world, and its mechanism research has become the main starting point to improve the comprehensive performance of fuel cells. The gas diffusion layer (GDL) of a proton exchange membrane fuel cell has a significant impact on the overall performance of the cell as an important component in supporting the catalytic layer, collecting the current, conducting the gas and discharging the reaction product water. In this paper, a three-dimensional two-phase isothermal fuel cell model is established based on COMSOL, the gradient porosity of the GDL, thickness of the GDL, operating voltage and working pressure of proton exchange membrane fuel cell are analyzed, the consistency problem of fuel cell performance improvement and life extension that is easily overlooked in numerous studies is found. On this basis, a neural network proxy model is constructed through a large amount of data, and a multi-objective genetic optimization algorithm based on the compromise strategy of recombination optimization is proposed to optimize the uniformity of fuel cell power and oxygen molar concentration distribution, which improves the performance of the fuel cell by 1.45% compared with the power increase when it is not optimized. At the same time, the uniformity of oxygen distribution is improved 10.28%, which makes the oxygen distribution more uniform, prolongs the life of the fuel cell, and fills the gap in the optimization direction of the comprehensive performance of the fuel cell.