Digital Correlation Analysis and Optimization of Microporous Layer Through a Machine Learning Workflow for PEMFC Applications

The Microporous Layer (MPL) plays a crucial role in Proton Exchange Membrane Fuel Cells (PEMFCs), as its microstructure significantly influences the overall transport properties within these devices. This study introduces a novel Machine Learning (ML) approach to optimize the MPL microstructure and properties. Synthetic datasets were generated by considering key manufacturing parameters, including carbon particle diameter, carbon Solid Volume Percentage (SVP), and polytetrafluoroethylene (PTFE) SVP, and used to calculate MPL output properties such as relative diffusivity, thermal conductivity, and electrical conductivity. A correlation analysis revealed that among the three input parameters, carbon SVP strongly influenced MPL output properties. Our ML framework achieved an R2 score of 0.92, with a decrease in computational time for predicting MPL properties from ~1 hour (using physics-based methods) to ~7 seconds (using the ML model). Finally, the optimizer suggested low solid weight % (carbon and PTFE) for maximum diffusivity, while high carbon SVP and low PTFE SVP for maximum conductivities. Among the three evaluated MPL output properties, the electrical conductivity is consistent with experimental literature. In contrast, the thermal conductivity is one to two orders of magnitude higher than experimental values, and this difference can be explained by the dispersion of experimental data found in the literature. For relative diffusivity, this is the first time an optimal value is reported.