Next-generation proton exchange membrane (PEM) fuel cells of high power density and durability are a cornerstone technology for future sustainable energy systems. While traditional three-dimensional (3D) full-size computational fluid dynamics (CFD) modeling has been pivotal in fuel cell design by numerically resolving electrochemically coupled multi-physics transfers, it faces persistent challenges, including a major theoretical gap in channel two-phase flow physics, oversimplified representations of catalyst layer (CL) microstructures, outdated membrane correlations, inadequate validation, and lack of consideration on material degradation. This perspective paper identifies key challenges and opportunities for fuel cell design through multi-physics and artificial intelligence (AI) modeling. Data-driven sub-models describing specific physics (e.g., multi-physics transfers within CLs) can be integrated with traditional modeling frameworks to balance the trade-off between computational efficiency and accuracy. Moreover, by utilizing physics-informed operator learning (e.g., PI-DeepONet) for evolution of multi-physics distributions and generating datasets via transient 3D models incorporating balance of plant (BOP) components, it is foreseeable to ultimately pave the way for predictive digital twins enabling health monitoring and degradation analysis throughout the life cycle, crucial for developing next-generation high-power-density and durable PEM fuel cells.

In this study, a 3D + 1D (three-plus-one dimensional) multiphase PEM (proton exchange membrane) fuel cell model is developed, in which the detailed channel two-phase flow is also considered based on the two-phase Darcy’s law. Compared with conventional 3D fuel cell models, the 3D + 1D model improves calculation efficiency and stability. Utilizing this model, the simulation work is conducted on an automobile PEM fuel cell (309.12 cm²) with the full flow field morphology considered. Its accuracy is comprehensively validated at this scale against the experimentally measured polarization curves and HFR (high frequency resistance) under different anode and cathode stoichiometric ratios and pressures and operating temperatures, indicating the model reliability. Subsequently, we numerically investigate the influence of four flow field configurations on cell performance characteristics, including the wave-like, dotted, baffled, and straight flow fields. It is found that the dotted and baffled configuration effectively improved cell performance, but the wave-like flow field has little influence on cell performance compared with straight flow field. Moreover, it is found that decreasing the channel/rib width decreases the concentration loss, but it also increases the ionic ohmic loss, resulting in an optimal channel/rib width for cell performance improvement. GRAPHICAL ABSTRACT