Fuel Cells最新文献

Proton exchange membrane fuel cells (PEMFCs) serve as crucial components in renewable energy systems, owing to their exceptional efficiency and minimal emissions. This research presents a fused maximum power point tracking (MPPT) approach for a 6 kW PEMFC system, integrating fuzzy logic control (FLC) with genetic algorithm-augmented particle swarm optimization (GA-PSO). A rigorous mathematical model of the PEMFC is formulated and experimentally corroborated. A fuzzy logic controller addresses system nonlinearity, while the GA-PSO algorithm dynamically optimizes the fuzzy rule base to adapt to varying operating conditions. Simulations compare the Mamdani controller and the GA-PSO hybrid controller interfaced with a DC–DC boost converter (45–85.34 V). Results demonstrate that the GA-PSO controller achieves 99.7% tracking efficiency (vs. 96.33% for Mamdani) with shorter rise time (5.15 vs. 5.03 ms), lower overshoot (9.17% vs. 10.34%), and enhanced robustness. The hybrid controller effectively tracks maximum power under dynamic loads and environmental changes, proving its superiority in steady-state accuracy and adaptability. This work provides a practical solution for optimizing PEMFC energy output.

Direct Methanol Fuel Cells (DMFCs) are attractive for portable applications but face persistent challenges, including methanol crossover, poor catalyst layer adhesion, and inefficient mass transport associated with conventional microporous layers (MPLs). These deficiencies limit catalyst utilization and water management, resulting in reduced power output and stability. To address these challenges, this study developed a titanium dioxide–carbon nanofiber (TiO₂–CNF) hybrid MPL via slurry seeping fabrication. The composite structure leverages CNF's high conductivity and TiO₂’s catalytic stability to achieve optimized porosity (69.85%) and balanced micro/mesopore distribution. Electrochemical testing revealed a 17.58% enhancement in peak power density at 4 M methanol concentration compared with CNF-based MPLs, alongside a reduction in crossover-induced losses from 71.9% to 39.46%. The CNF–TiO₂ interface promoted efficient charge transfer, maintained stable operation, and improved reactant/product transport, thereby enhancing overall DMFC efficiency. These results demonstrate that the TiO₂–CNF hybrid MPL provides a robust and scalable solution to overcome mass transport and stability limitations, offering a significant advancement toward practical DMFC systems for compact and portable power devices.

Long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM) neural networks are utilized to predict the performance degradation of proton exchange membrane fuel cells using a dataset of 550 h obtained from the Federation for Fuel Cell Research (FCLAB). The model performance is optimized using Bayesian optimization long short-term memory (BO-LSTM), ant colony optimization long short-term memory (ACO-LSTM), Bayesian optimization bidirectional long short-term memory (BO-Bi-LSTM), and ant colony optimization bidirectional long short-term memory (ACO-Bi-LSTM). For each above model, how different parameters such as the number of hidden nodes, dropout rate, learning rate, and number of hidden layers affect the prediction results are carefully examined. The results show that the mean absolute percent error (MAPE) of BO-LSTM, ACO-LSTM, BO-Bi-LSTM, and ACO-Bi-LSTM models with a training rate of 80% are approximately 0.000230, 0.000394, 0.000218, and 0.000181, respectively. Note that the obtained MAPE values are improved significantly as compared with those (MAPE = 0.0518–0.0097) of previous reports, leading to the potential application of proposed models for similar fuel cell systems.

Proton exchange membrane fuel cells (PEMFCs) play a central role in the transition to clean hydrogen-based energy systems. However, conventional models with fixed empirical parameters often fail to predict performance under variable operating conditions accurately. This paper introduces two novel PEMFC models with load-dependent formulations of the activation overpotential constant and its temperature coefficient, parameters shown to have the greatest sensitivity to load variation. Using the artificial hummingbird algorithm (AHA) for parameter optimization, the models were tested on four representative PEMFC configurations (Ballard-Mark-V 5 kW PEMFC, BCS 500 W, NedStack PS6 6 kW PEMFC, and Horizon 500 W). The results demonstrate a consistent reduction in prediction error compared with state-of-the-art models, with an improvement of up to 89.97% in RMSE for the Horizon cell. Sensitivity and robustness analyses further confirm stable performance under varying temperature and pressure conditions. These findings suggest that the proposed models offer a reliable and computationally efficient foundation for advanced simulation, control, and optimization of PEMFC systems in real-world applications.

Proton exchange membrane fuel cells (PEMFCs) are highly efficient electrochemical energy converters utilized for the production of sustainable, renewable, and clean power. A cell contains a membrane, bipolar plates housing flow channels, gas diffusion, and catalyst layers. The channel geometry influences pressure loss along the channel and transporting the reactant gases to porous layers. In this article, the influence of distinct widened sections in a square channel having a small cross-sectional area of 0.2 × 0.2 mm² on PEMFC performance is examined via ANSYS Fluent for 0.4–0.6 V. The enlarged section length varies 1/4, 1/2, and 3/4 of the length of cell (L = 70 mm). The results revealed that the new configurations with enlarged sections significantly diminished the pressure loss in the channels with a slight decline in the current density. The innovative channel configuration having a widened section with a length of 3L/4 reduces the current density, anode and cathode pressure drops of 5.8%, 40.4%, and 46.0%, respectively, compared to the square channel for 0.4 V. Considering pressure losses through the flow channels, this channel configuration is a better choice to enhance PEMFC efficiency.

Proton exchange membrane fuel cells (PEMFC) have been widely utilized in transportation and power generation due to their high efficiency and low pollution. However, their durability remains insufficient, and their output power decreases over time during operation. Therefore, it is important to predict the remaining useful life (RUL) of the PEMFC to ensure its efficient operation. In this paper, an improved TCN-iTransformer model is proposed for predicting the RUL of PEMFC, which integrates temporal convolutional network (TCN), iTransformer, discrete cosine transform (DCT), and the channel attention mechanism. The reliability of the model was validated using both static and dynamic datasets of different lengths. And the results showed that the improved TCN-iTransformer achieved a significant improvement over the Transformer prototype in long sequence time-series forecasting. Furthermore, smaller mean absolute percentage error (MAPE) and root mean square error (RMSE) were obtained compared to other improved models, such as long short-term memory (LSTM) and gated recurrent unit (GRU). In addition, the RUL prediction error of the model was found to not exceed 1 h.

This research compares the performance of plug-in fuel cell electric vehicles (PFCEVs), battery electric vehicles (BEVs), and fuel cell electric vehicles (FCEVs) using MATLAB Simulink. The simulations were run for 1800 s using the Worldwide Harmonized Light Vehicles Test Cycle (WLTC 3a), spanning a distance of 23 km, to assess important performance characteristics such as energy efficiency, consumption, emissions, and life cycle costs. The PFCEV architecture, which combines a medium-sized fuel cell and a sizable battery pack, has a strategic advantage because it requires fewer charging stations than BEVs and fewer hydrogen filling stations than FCEVs. The findings reveal that PFCEVs provide a unique combination of high efficiency, low emissions, rapid recharging, and greater driving range while requiring minimal hydrogen infrastructure. Compared to BEVs, PFCEVs minimize range anxiety while improving grid stability, and unlike FCEVs, they maximize hydrogen utilization via a complicated power management system. This study highlighted PFCEVs as a viable choice for sustainable mobility, serving as a valuable link between BEVs and FCEVs in the evolution of electric transportation. The findings indicate that PFCEVs have a good possibility of becoming a preferred vehicle technology, bridging the gap between battery and hydrogen-powered electric vehicles while addressing infrastructure and efficiency challenges.

Nowadays, green hydrogen technology is a pivotal innovation for reducing environmental pollution and combating global climate change. In the pursuit of sustainability, proton exchange membrane fuel cells (PEMFCs) are considered a promising solution for optimizing the utilization of green hydrogen and enhancing energy storage capabilities. This article presents a novel application of the mirage search optimization (MSO) algorithm for developing an accurate PEMFC model. Through a comprehensive study of four typical PEMFC stacks, the results demonstrate the superior performance of the proposed MSO algorithm when compared to other optimizers in terms of accuracy and convergence speed. The optimization algorithms used for comparison with MSO include the grey wolf optimizer, whale optimization algorithm, chimpanzee optimization algorithm, and other optimizers from the literature. The enhancement in modeling accuracy by obtaining a better fitness value using MSO over other optimizers is up to 10.7% for NedStack PS6, 7.1% for Ballard Mark 5 kW, 31.5% for BCS 500 W, and 85.39% for Horizon H-500. Furthermore, a sensitivity analysis is carried out to validate the results obtained by MSO and to verify the accuracy of the developed model. Through comprehensive performance assessments, it can be confirmed that MSO is a promising algorithm for accurately estimating the parameters of PEMFC models, as it demonstrates high efficiency and robustness.