This study presents a machine learning-enhanced optimization framework for proton exchange membrane fuel cell (PEMFC), designed to address critical challenges in dynamic load adaptation and thermal management for automotive applications. A high-fidelity model of a 65-cell stack (45 V, 133.5 A, 6 kW) is developed in MATLAB/Simulink, integrating four core subsystems: PID-controlled fuel delivery, humidity-regulated air supply, an electrochemical-thermal stack model (incorporating Nernst voltage and activation, ohmic, and concentration losses), and a 97.2–efficient SiC MOSFET-based DC/DC boost converter. The framework employs the NSGA-II algorithm to optimize key operational parameters—membrane hydration (λ = 12–14), cathode stoichiometry (λO₂ = 1.5–3.0), and cooling flow rate (0.5–2.0 L/min)—to balance efficiency, voltage stability, and dynamic performance. The optimized model achieves a 38% reduction in model-data discrepancies (RMSE < 5.3%) compared to experimental data from the Toyota Mirai, and demonstrates a 22% improvement in dynamic response, recovering from 0 to 100% load steps within 50 ms with a voltage deviation of less than 0.15 V. Peak performance includes 77.5% oxygen utilization at 250 L/min air flow (1.1236 V/cell) and 99.89% hydrogen utilization at a nominal voltage of 48.3 V, yielding a peak power of 8112 W at 55% stack efficiency. Furthermore, fuzzy-PID control of fuel ramping (50–85 L/min in 3.5 s) and thermal management (ΔT < 1.5 °C via 1.0–1.5 L/min cooling) reduces computational overhead by 29% in the resulting digital twin platform. The framework demonstrates compliance with ISO 14687-2 and SAE J2574 standards, offering a scalable and efficient solution for next-generation fuel cell electric vehicle (FCEV) aligned with global decarbonization targets, including the EU’s 2035 CO₂ neutrality mandate.

This work focuses on the design of a hybrid proton exchange membrane fuel cell (PEMFC) solution for any micro vehicle such as an unmanned aerial vehicle (UAV). A hydrogen fuel cell can provide extended operation, low emissions, and a highly efficient form of energy storage compared with alternative methods, while a battery can be used as an additional energy storage system to support the transient and higher loads required by the UAV, which are not suitable for normal fuel cell operation. The choice of hydrogen storage is one of the main challenges in using hydrogen as an energy carrier. The current study discusses a range of hydrogen storage technologies and provides a methodology for selection for a given application. A sizing design methodology for a hybrid fuel cell system is proposed. Then, it is applied to a case study to demonstrate its implementation.

Understanding and accurately modelling mass transport phenomena in anode-supported solid oxide fuel cells (SOFCs) is essential for improving efficiency and mitigating performance losses due to concentration polarization. This study presents a one-dimensional, isothermal, multi-component diffusion framework based on the Stefan–Maxwell (SM) formulation to evaluate hydrogen, water vapour, and nitrogen transport in two different porous ceramic support materials: calcia-stabilized zirconia (CSZ) and magnesia magnesium aluminate (MMA). Both SM binary and SM ternary models are implemented to capture species interactions under varying hydrogen concentrations and operating temperatures. The SM formulation enables direct calculation of concentration polarization as well as the spatial distribution of gas species across the anode support’s thickness. Simulations are conducted for two representative fuel mixtures—20% H₂ (steam-rich, depleted fuel) and 50% H₂ (steam-lean)—across a temperature range of 500–1000 °C and varying electrode thicknesses. They are validated against experimental data from the literature, and the influence of electrode thickness and fuel composition on polarization losses is systematically assessed. The results show that the ternary SM model provides superior accuracy in predicting overpotentials, especially under low-hydrogen conditions where multi-component interactions dominate. MMA consistently exhibits lower polarization losses than CSZ due to enhanced gas diffusivity. This work offers a validated, computationally efficient framework for evaluating mass transport limitations in porous anode supports and offers insights for optimizing electrode design and operational strategies, bridging the gap between simplified analytical models and full-scale multiphysics simulations.

This study presents an integrated, open-source process simulation for converting agricultural biogas into high-purity liquid hydrogen using DWSIM (Distillation, Water, Separation and Inorganic Modules), an open-source sequential-modular simulator. The model simulates a farm-scale biogas feed and is optimised to enhance liquid hydrogen yield while reducing specific energy consumption under set operating conditions. The proposed model links biogas upgrading via dual pressure swing adsorption, steam–methane reforming, two-stage water–gas shift, hydrogen purification, and cryogenic liquefaction within a single optimisation framework. Using a representative farm-scale feed (103.7 kg h⁻¹ biogas containing 60 mol% CH₄), the optimised process produces 16.5 kg h⁻¹ of liquid hydrogen with 99.2% para-hydrogen purity while simultaneously capturing 104 kg h⁻¹ of CO₂ at 98% purity and 16 bar. Optimal operating conditions include SMR at 909 °C and 16 bar with a steam-to-carbon ratio of 3.0, followed by high- and low-temperature water–gas shifts at 413 °C and 210 °C, respectively. The overall cold-gas efficiency (LHV basis, excluding liquefaction electricity) reaches 78%, and the specific electricity demand for liquefaction is 32.4 kWh per kg of liquid hydrogen, which is consistent with reported values for small-scale hydrogen liquefiers. Sensitivity analysis over a methane content range of 40–75% confirms near-linear scalability of hydrogen output (R² = 0.998), demonstrating feedstock flexibility without re-parameterisation. The developed process in this work provides a transparent and extensible digital twin for early-stage design and optimisation of decentralised biogas-to-hydrogen systems. Using the open-source DWSIM platform ensures full transparency, reproducibility, and accessibility compared with proprietary simulators.