Proton Exchange Membrane Fuel Cell (PEMFC), as an innovative renewable and clean energy device, holds immense market application value. PEMFCs are susceptible to water management faults when operating continuously for extended periods under complex and varying conditions. However, traditional fault diagnosis methods struggle to effectively extract key fault features from dynamically changing monitoring data. To address this, a PEMFC fault diagnosis method based on a Deep Parallel Residual Network (DP-ResNet) is proposed. This method initially processes the collected multi-source signals, such as current and voltage. Subsequently, a DP-ResNet is designed to overcome the limitation of residual networks in multi-scale feature extraction. Finally, the proposed algorithm is applied to a dataset of PEMFC water management faults under varying load conditions for diagnostic verification. Experimental results demonstrate that the proposed DP-ResNet model achieves a diagnostic accuracy of up to 99.46% for flooding faults in real PEMFC experimental datasets. Compared to traditional machine learning algorithms such as Decision Tree, GaussianNB, KNN, and CNN, this method exhibits superior feature extraction capabilities and diagnostic accuracy.