Search Results

Life prediction is a major focus for a commercial fuel cell stack, especially applied in fuel cell electric vehicles (FCEV). This paper proposes a data driven fuel cell lifetime prediction model using particle swarm optimized back-propagation neural network (PSO-BPNN). For the prediction model PSO-BP, PSO algorithm is used to determine the optimal hyper parameters of BP neural network. In this paper, total voltage of fuel cell stack is employed to represent the health index of fuel cell. Then the proposed prediction model is validated by the aging data from PEMFC stack in FCEV at the actual road condition. The experimental results indicate that PSO-BP model can predict the voltage degradation of PEMFC stack at actual road condition precisely and has a higher prediction accuracy than BP model.

In the assembling process of proton exchange membrane fuel cell (PEMFC) stack, the clamping load is known to have direct effect on the contact pressure of interfaces. Compression on the membrane electrode assembly (MEA) results in change in gas diffusion layer (GDL), porosity and electrical resistance, thus affecting the performance, durability and reliability of the PEMFC stack. In this paper, the relation between clamping load and performance of PEMFC stack was obtained by experimental study, and the influence of clamping load on the contact pressure of MEAs was analyzed by finite element analysis. The performance test rig was established and the approach of polarization curve testing was introduced. Both the effect of magnitude and distribution of the bolt torques on the performance were taken into account. The finite element model was adopted to figure out the magnitude and uniformity of contact pressure of MEAs, which provides a new angle to understand the experimental results.