Modelling Anti-Corrosion Coating Performance of Metallic Bipolar Plates for PEM Fuel Cells: A Machine Learning Approach

Abstract

Proton exchange membrane (PEM) fuel cells have significant potential for clean power generation, yet challenges remain in enhancing their performance, durability, and cost-effectiveness, particularly concerning metallic bipolar plates, which are pivotal for lightweight compact fuel cell stacks. Protective coatings are commonly employed to combat metallic bipolar plate corrosion and enhance water management within stacks. Conventional methods for predicting coating performance in terms of corrosion resistance involve complex physical-electrochemical modelling and extensive experimentation, with significant time and cost. In this study machine learning techniques are employed to model metallic bipolar plate coating performance, diamond-like-carbon coatings of varying thicknesses deposited on SS316L are considered, and coating performance is evaluated using potentiodynamic polarization and electrochemical impedance spectroscopy. The obtained experimental data is split into two datasets for machine learning modelling: one predicting corrosion current density and another predicting impedance parameters. Machine learning models, including extreme gradient boosting (XGB) and artificial neural networks (ANN), are developed, and optimized to predict coating performance attributes. Data preprocessing and hyperparameter tuning are carried out to enhance model accuracy. Results show that ANN outperforms XGB in predicting corrosion current density, achieving an R2 > 0.98, and accurately predicting impedance parameters with an R2 > 0.99, indicating that the models developed are very promising for accurate prediction of the corrosion performance of coated metallic bipolar plates for PEM fuel cells.

Keywords

• Fuel cell
• Metallic bipolar plate
• Coating performance
• Machine learning
• Extreme gradient boosting
• Artificial neural networks