Accurately predicting the performance degradation trend of fuel cells helps take measures in advance and prolong the stack's service life, leading to a novel hybrid forecasting approach. The first grey model prediction method based on residual exponential smoothing optimization (ES-R-GM) can capture the voltage deterioration trend. We explore the integration of two different ES techniques, specifically the double ES (ES2) and cubic ES (ES3), to investigate their effect on enhancing the predictive accuracy of the GM model. The second method of the adaptive network fuzzy inference system (ANFIS) can characterize local nonlinear behavior. We utilize the simulated annealing (SA) algorithm to optimize ANFIS results under different fuzzy rule selection strategies. The outcomes of the two prediction methods mentioned above are combined to create a hybrid prediction using the data fusion method and the moving window technique. Various hybrid methods are evaluated under general conditions and further detailed optimization. The data collected from the experimental platform confirms the suggested hybrid framework. The results show that the hybrid ES3-R-GM + ANFIS-SC method outperformed the single models in final prediction accuracy and can effectively track both global trends and local changes. Simultaneously, it takes less time to calculate than the literature. Moreover, when applied to consistent public datasets, the hybrid approach maintains its robustness and accuracy compared with other hybrid prognostic methods.

This study designs an energy management strategy for fuel cell hybrid vehicles aimed to alleviating the performance degradation of Proton Exchange Membrane Fuel Cells (PEMFC), fuel consumption, and battery State of Charge (SOC) fluctuations during vehicle operation. The research focuses on the decrease in Electrochemical Surface Area (ECSA) due to Platinum (Pt) catalyst degradation, which is a key factor influencing PEMFC durability. An ECSA model based on the Pt dissolution mechanism is established, and a dynamic condition accelerated stress test (DC-AST) is designed to specifically investigate the impacts of key parameters, such as cycle period, amplitude, and duty cycle on the degradation of ECSA. This reveals the association between ECSA degradation and irregular potential fluctuations. A hierarchical power allocation strategy is then proposed, combining the global search capabilities of optimization algorithms with heuristic strategies in light of these features. The upper level employs Pontryagin's Minimum Principle (PMP) strategy for global power allocation optimization, while the lower level uses a satisfaction-based heuristic strategy that is tailored to the ECSA degradation characteristics, to dynamically adjust power output. Simulation results demonstrate that, compared to traditional rule-based strategies and classical PMP-based strategies, the proposed energy management strategy more effectively mitigates ECSA degradation of PEMFC under typical vehicle conditions.

The solid oxide fuel cell (SOFC) is known as the most hopeful clean energy source in the 21st century due to its higher efficiency and lower pollution, but its performance degradation and durability have become bottlenecks hindering its large-scale commercialization. Accurately predicting the performance degradation trend of SOFC and timely diagnostic failures can maintain and adjust the equipment in advance, which is conducive to extending its service life. Data-driven and model-based both have certain limitations, and they are two traditional prediction methods. This paper proposes a solid oxide fuel cell hybrid prediction method based on the combination of empirical model and data-driven. Model-based prediction can capture the degradation trend of voltage. Data-driven prediction can describe local nonlinear characteristics in the degradation process. Then, according to the dynamically adjusted weight factor, the results predicted by the different methods are merged to get the culminating prediction result. Finally, the experimental results indicate the hybrid prediction method has higher forecasting accuracy.

Solid oxide fuel cell system is complex with multiple variables strongly coupled. Once a fault occurs, if it cannot be found in time, the initial minor fault may slowly evolve and spread to subsequent components. Therefore, fault diagnosis is a promising approach to guarantee the stability of the system. In this paper, the impact of air leakage and fuel starvation is investigated. To diagnose the two types of faults, a novel data-driven online fault diagnosis method based on principal component analysis and support vector machine is developed. Data comes from the entire stage of the solid oxide fuel cell system experiment. The results show that the proposed method can effectively identify the air leakage and fuel starvation fault in real time. Through comparison with traditional machine learning methods, this method shows higher accuracy and better generalization performance. Moreover, it combines prior knowledge and statistical characteristics to extract effective features, thereby reducing the calculation burden. Furthermore, with proper modifications, the proposed method can be extended to other types of solid oxide fuel cell system faults, which is significant in enhancing the reliability of the system.