The flow channel design of bipolar plates plays a significant role in the proton exchange membrane fuel cells operation, particularly in thermal and water management. The pursuit of low-pressure drop supply and flow field uniformity in PEM fuel cells has not stopped, resulting in numerous new bipolar plate flow channel designs. The biomimetic leaf vein shape-based flow channel and lung flow channel designs can significantly improve gas supply uniformity and reduce pressure drop. Therefore, we propose a snowflake-shaped bionic channel design by integrating the advantages of the leaf vein shape and lung shape channel. A 3D multi-physics fuel cell model is used to verify the feasibility and superiority of the bionic snowflake design in improving fuel cell performance, especially in reducing the pumping work. The local pressure distribution, oxygen distribution, water distribution, and current density distribution are used to reveal the enhancement mechanism of the new snowflake flow channel. The flow uniformity is further enhanced by using multi-objective (13 target parameters) and multi-parameter (18 independent variables) genetic algorithm optimization. The general goal of this work is to provide a new strategy for the thermal and water management of PEM fuel cells.

Precise and efficient calculations are necessary to accurately assess the effects of thermal protection system (TPS) uncertainties on aerospacecrafts. This paper presents a probabilistic design methodology for TPSs based on physics-informed neural networks (PINNs) with parametric uncertainty. A typical thermal coating system is used to investigate the impact of uncertainty on the thermal properties of insulation materials and to evaluate the resulting temperature distribution. A sensitivity analysis is conducted to identify the influence of the parameters on the thermal response. The results show that PINNs can produce quick and accurate predictions of the temperature of insulation materials. The accuracy of the PINN model is comparable to that of a response surface surrogate model. Still, the computational time required by the PINN model is only a fraction of the latter. Considering both computational efficiency and accuracy, the PINN model can be used as a high-precision surrogate model to guide the TPS design effectively.