Reliable operation of proton exchange membrane fuel cells (PEMFCs) is crucial for their widespread commercialization, and accurate fault diagnosis is the key to ensuring their long-term stable operation. However, traditional fault diagnosis methods not only lack sufficient interpretability, making it difficult for users to trust their diagnostic decisions, but also one-dimensional (1D) feature extraction methods highly rely on manual experience to design and extract features, which are easily affected by noise. This paper proposes a new interpretable fault diagnosis algorithm that integrates Gramian angular field (GAF) transform, convolutional neural network (CNN), and gradient-weighted class activation mapping (Grad-CAM) for enhanced fault diagnosis and analysis of proton exchange membrane fuel cells. The algorithm is systematically validated using experimental data to classify three critical health states: normal operation, membrane drying, and hydrogen leakage. The method first converts the 1D sensor signal into a two-dimensional GAF image to capture the temporal dependency and converts the diagnostic problem into an image recognition task. Then, the customized CNN architecture extracts hierarchical spatiotemporal features for fault classification, while Grad-CAM provides visual explanations by highlighting the most influential regions in the input signal. The results show that the diagnostic accuracy of the proposed model reaches 99.8%, which is 4.18%, 9.43% and 2.46% higher than other baseline models (SVM, LSTM, and CNN), respectively. Furthermore, the explainability analysis using Grad-CAM effectively mitigates the “black box” problem by generating visual heatmaps that pinpoint the key feature regions the model relies on to distinguish different health states. This validates the model’s decision-making rationality and significantly enhances the transparency and trustworthiness of the diagnostic process.

Urban bus operations under signalized traffic conditions are characterized by frequent stop-and-start behaviors which significantly degrade fuel economy, especially for fuel cell buses (FCB). In this paper, a collaborative optimization method is proposed that combines speed planning and energy management for FCB in this situation. The method calculates the target speed of FCB using traffic light phase information and the remaining signal time. With an intelligent driving model, the vehicle can adjust its speed in advance when approaching intersections so it can pass through intersections without stopping. At the same time, a learning-based energy management strategy is used to reasonably share power between the fuel cell and the battery. The results indicate that the method proposed in this paper reduces hydrogen consumption by approximately 11.3% compared to the standard method.

Accurate voltage degradation prediction is essential for health management and lifetime extension of proton exchange membrane fuel cell (PEMFC) systems. During long-term constant-current operation, stack voltage evolves nonlinearly and is influenced by coupled variations in temperature, pressure, flow rate, and humidity, while many deep learning-based models lack physical interpretability. This study proposes an interpretable Transformer-based framework for PEMFC voltage degradation prediction under constant-current operation. The framework integrates outlier correction, interpolation, Savitzky–Golay filtering, Z-score normalization, sliding-window reconstruction, Transformer-based prediction, and feature-ablation interpretation. Using multivariate sensor measurements and historical voltage as inputs, the Transformer was compared with RNN, LSTM, and GRU baselines under identical preprocessing and evaluation conditions. The models were evaluated chronologically by continuously applying the sliding-window model over the held-out final 20% of the aging sequence. The Transformer achieved the best performance, with MAE of 8.2 × 10⁻⁴, RMSE of 1.18 × 10⁻³, MAPE of 0.0256%, and R² of 0.9961. Compared with the second-best RNN model, it reduced MAE, RMSE, and MAPE by 9.89%, 7.81%, and 9.86%, respectively. Feature ablation showed that flow- and pressure-related variables contributed 50.08% and 26.78% of the total importance, respectively.