Performance-Based Material Screening of Low-Temperature Direct Ammonia Fuel Cells Using Artificial Neural Networks

This study employs artificial neural networks (ANNs) to optimize material screening and design parameters for low-temperature direct ammonia fuel cells (DAFCs). Using 241 experimental data sets from prior studies, the ANN is trained on 22 categorical and numerical parameters, including catalyst types, membrane thickness, anode loading, and operating conditions, to predict cell current density with high accuracy. The box-whisker analysis identifies the anode catalyst type, cathode catalyst, and anode support material as key determinants of power density, with the anode catalyst type exerting the greatest influence. The ANN, featuring six hidden layers with ReLU activation and trained via the Adam algorithm, achieves mean absolute percentage errors (MAPEs) of 5.75% and 9.30% for training and testing data sets, respectively, and further demonstrates robust generalization with an average training MAPE of 5.81% ± 1.34% and validation MAPE of 8.60% ± 2.10% across 5-fold cross-validation. The ANN accurately reproduces polarization and power density curves for two DAFC configurations (MAPEs of 7.62% and 8.13%). Sensitivity analyses reveal that thinner membranes enhance performance by reducing ohmic resistance, though gains diminish below 18 μm due to interfacial limitations, while an optimal anode loading of 2 mg/cm2 maximizes power density at 255 mW/cm2. By capturing complex, nonlinear parameter interactions, the ANN surpasses traditional experimental approaches, reducing experimental overhead and accelerating DAFC optimization for sustainable energy applications.