Fuel Cells最新文献

Fuel Cell Electric Vehicles (FCEVs) require more capable influence on adaptation schemes to ensure smooth operation and maximum energy utilization. Strong Maximum Power Point Tracking (MPPT) in the systems is challenging due to the fuel cell nonlinearity, dynamic loads, and fluctuating ambient conditions. Conventional MPPT methods are marred by slow convergence, local optimum trapping, and poor tracking of sudden transients. To eliminate these limitations, this manuscript presented a high-gain interleaved DC–DC converter (HGIDCDCC)-based optimum MPPT control method with the Starfish Optimization Algorithm (SFOA) and Putterfish Algorithm (PFA). The method benefits from the high voltage gain (VG) and ripple rejection of the interleaved converter, while SFOA–PFA hybrid optimization improves the MPPT displays in terms of higher convergence rate, global search ability, and steady-state stability. The designed converter structure and MPPT controller enhance the power conversion efficiency, voltage regulation, fuel cell temperature change response, and output power in all validated environments. In addition to FCEVs, the approach is also supportive of hybrid renewable power and storage systems, in which stable voltage, efficiency, and reliability are essential. The accuracy of the proposed approach is 99%.

Operating parameters of Proton Exchange Membrane Fuel Cells (PEMFCs) are important for its output performance and real time control. However, in existing studies, the methods for optimizing its operating parameters either focus on only one aspect, or the multi-objective optimization process, and is excessively time-consuming. This study proposes a novel hybrid framework that couples a deep neural network surrogate model with the Non-dominated Sorting Genetic Algorithm II (NSGA-II) for multi-objective optimization of fuel cell operating parameters. Seven key operating parameters—including voltage, temperature, pressure, stoichiometric ratios, and humidity—are selected as decision variables, while power density, system efficiency, and oxygen distribution uniformity serve as optimization objectives. The surrogate model is constructed using an Adam-optimized backpropagation neural network (Adam-BP), trained on a dataset generated through orthogonal design and numerical simulations. The model achieves high accuracy in performance prediction and is integrated with NSGA-II to rapidly generate Pareto-optimal solutions. The optimal operating parameters are further selected using the CRITIC method, which enables adaptive weighting based on data variability and correlation. Results show that the proposed method improves power density by 27%, system efficiency by 9.7%, and oxygen distribution uniformity by 6.6% compared to baseline conditions. This approach offers a fast, accurate, and systematic tool for PEMFC performance optimization, with strong potential for engineering application.

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.