Yiming Bai

Cathode flow field optimization is crucial for improving the overall performance of proton exchange membrane fuel cells (PEMFCs), yet conventional optimization strategies are hindered by the heavy reliance on iterative experiments and computationally intensive simulations. This work developed an AI-assisted framework for multi-objective optimization of PEMFC cathode flow fields, integrating high-fidelity simulations, surrogate modeling, and optimization algorithms. The proposed framework was demonstrated by optimizing a trapezoidal baffle flow field. First, the key parameters of the three-dimensional (3D) PEMFC model were automatically calibrated using a small set of experimental data. The calibrated model was then used to generate training datasets, from which a physics-informed neural network (PINN) surrogate model was developed to rapidly predict key performance metrics, including the I-V curve, pressure drop, and current density uniformity. To enable system efficiency evaluation, a data-driven air compressor model capturing nonlinear operating characteristics was established and coupled with the PEMFC surrogate model. The flow field was subsequently optimized for improved system efficiency and current density uniformity. The results showed that the PEMFC and air compressor surrogate models exhibited high prediction accuracy, substantially reducing the computational cost of system-level optimization. The multi-objective optimization revealed a trade-off between system efficiency and current density uniformity, and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) was employed to identify the best-compromise solution from the Pareto-optimal set over the common operating voltage range of 0.6-0.8 V. The proposed framework provides a generalizable approach for advancing PEMFC flow field optimization from single-cell performance evaluation to system-level design.

Pt-based intermetallic compounds, featuring ordered atomic arrangements, exhibit superior oxygen reduction reaction (ORR) activity and durability. However, the formation of ordered alloys typically relies on high-temperature annealing to drive atom migration and rearrangement, which readily leads to sintering and agglomeration of metal nanoparticles, thereby posing significant challenges for the synthesis of intermetallic catalysts. In this work, a two-step synthesis strategy enabled by a continuous-flow system is developed for the scalable preparation of high-performance Pt3Co intermetallic catalysts. Owing to the efficient heat transfer, thorough mixing, and continuous feeding in the continuous-flow reactor, the rapid sequential reduction of Pt followed by Co is achieved, yielding precursor nanoparticles with a Pt core and a Co-enriched surface. This structured precursor effectively mitigates nanoparticle sintering during subsequent annealing. After high-temperature annealing and acid leaching, the resulting Pt3Co intermetallic catalyst exhibits excellent ORR activity and durability, delivering a mass activity (MA) of 3.4 times that of commercial Pt/C, while the degradation rates of electrochemical surface area (ECSA) and MA after accelerated stress tests are only one-quarter and two-fifths, respectively, of those of commercial Pt/C. Moreover, a practical fuel cell incorporating this catalyst also demonstrates significant performance advantages, achieving a peak power density exceeding 1.87 W·cm-2.

By shortening the Ir–O bond and maintaining a robust rutile [IrO ₆ ] framework, IrO ₂ (sub-2 nm) synergistically enhances both activity and stability, breaking the long-standing OER dilemma.

Electrochemical exfoliation of graphite is a cost-effective and eco-friendly method for producing graphene, which is regarded as a promising electrode material for supercapacitor, and the electrolyte may affect the product structure and capacitance properties remarkably. In this work, we examine the effects of anions in the electrolyte on the internal and surficial structures of the synthesized graphene. SO₄^2- anions help produce graphene with the highest specific surface area and a moderate amount of oxygen groups, leading to optimal double-layer capacitance and pseudocapacitance. When used in a symmetric supercapacitor, it achieves an energy density of 20.47 μWh cm^-2 at a power density of 0.25 mW cm^-2. In contrast, ClO₄^- and CO₃^2- are less effective in controlling the graphene thickness and oxygen species. This research provides insights into optimizing electrochemical exfoliation and enhancing the capacitance performance of graphene-based supercapacitors.