Machine learning-assisted optimization of NbTa alloy coating thickness via DC magnetron sputtering for SS316L bipolar plates in PEMFCs

Abstract

Corrosion and high interfacial contact resistance (ICR) in metallic bipolar plates (BPPs) remain critical challenges limiting the durability of proton exchange membrane fuel cells (PEMFCs). This study employs a dual experimental-machine learning (ML) approach to optimize NbTa alloy coatings deposited on SS316L BPPs via DC-balanced magnetron sputtering. Electrochemical testing and surface characterization were conducted under simulated and accelerated PEMFC conditions, while an artificial neural network (ANN) model was developed to predict performance trends across coating thicknesses. A 2.5 μm coating exhibited the best overall performance, reducing corrosion current density to below 0.2 μA cm^-2 and ICR to 0.9 mΩ cm². Notably, the 1.7 μm coating also met U.S. DOE targets, representing a practical balance between cost and durability. The ANN model achieved high predictive accuracy (R² = 0.992), validating its use in guiding experimental optimization. A preliminary techno-economic assessment indicated that NbTa alloy coatings could achieve favorable payback periods of only a few years under plausible manufacturing scenarios, reinforcing their potential for large-scale PEMFC deployment. This integrated experimental-ML framework offers a powerful strategy for accelerating the development of corrosion-resistant, conductive coatings tailored for advanced PEMFC applications.