This paper proposes a long short-term memory (LSTM) network to predict the power degradation of proton exchange membrane fuel cells (PEMFCs), and in order to promote the performance of the LSTM network, the ant colony algorithm (ACO) is introduced to optimize the hyperparameters of the LSTM network. First, the degradation mechanism of PEMFCs is analyzed. Second, the ACO algorithm is used to set the learning rate and dropout probability of the LSTM network combined with partial aging data, which can show the characteristics of the dataset. After that, the aging prediction model is built by using the LSTM and ACO (ACO-LSTM) method. Moreover, the convergence of the method is verified with previous studies. Finally, the fuel cell aging data provided by the Xiangyang Da’an Automotive Testing Center are used for verification. The results show that, compared with the traditional LSTM network, ACO-LSTM can predict the aging process of PEMFCs more accurately, and its prediction accuracy is improved by about 35%, especially when the training data are less. At the same time, the performance of the model trained by ACO-LSTM is also excellent under other operating conditions of the same fuel cell, and it has strong versatility.

Hydrogen starvation leads to the extreme deterioration of fuel cell performance due to the induced voltage reversal and carbon corrosion in the anode catalyst layer (ACL) and gas diffusion layer. In this paper, reversal-tolerant anodes (RTAs) with different ACL configurations are proposed, where IrO_x/C is used as a water electrolysis catalyst. Experimental results show that the separate IrO_x/C catalyst layer of MEA samples, layered reversal-tolerant catalyst-coated membrane (layered-RTA), and reversal-tolerant gas diffusion electrode (GDE-RTA) significantly enhance the reversal tolerance and cell performance compared to conventional anode and common RTA consisting of a homogeneous catalyst layer mixed with IrO_x/C and Pt/C (hybrid-RTA). Of these, GDE-RTA possessed a reversal tolerance time of 86 min, a power density of 1.42 W cm⁻², and a minimum degradation rate of 2.4 mV min⁻¹, suggesting it to be the best RTA structure. Cyclic voltammetry and electrochemical impedance spectrum were used to detect the properties of each sample. Additionally, the degradation mechanisms of the three RTAs are thoroughly investigated and discussed by means of microstructural characterization through scanning electron microscopy and transmission electron microscopy. This work provides novel ideas for the fabrication of a robust RTA by tuning the ACL configuration, which is practical for the commercialization of fuel cells.