Sensitivity analysis and performance evaluation of the PEMFC using wave-like porous ribs

Abstract

An approachable way to improve proton exchange membrane fuel cell’s (PEMFC) performance at low current densities is to enhance the convective heat transfer in the gas flow channel (GFC). This article aims to devise porous ribs in GFC to change the velocity and temperature profiles with subsequent performance improvement. This fact leads to higher Nu number and heat transfer rate. However, the geometrical characteristics of these porous ribs should be determined. In this manner, seven wave-like porous ribs with different slopes, heights, and entrance lengths are utilized to perform 30 simulations. In these simulations, friction factor and Nu number are considered as the outputs, which lower and higher values of them are preferred, respectively. The performance evaluation criterion (PEC) is introduced to compare the cell’s performance in different cases. Results indicate that the slope of the ribs has a direct relationship with PEC. Finally, the results are used to train an artificial neural network (ANN). This ANN model produces a large number of random points with different input parameters. After the calculation of the outputs, big data analysis and sensitivity study would be possible. Results indicate that the height of the first porous rib plays the crucial role in Nu number and PEC, while the entrance length has the least effect on these outputs.