Data-driven modeling of polymer electrolyte fuel cells: Towards predictive analytics with explainable artificial intelligence

Energy and AI, vol. 21, pp. 100577

Abstract

• Developed a comprehensive data-driven framework using advanced machine learning models to accurately predict polarization behavior of polymer electrolyte fuel cells. • Integrated explainable AI techniques such as Gini importance or SHAP to reveal how key operational and design parameters especially voltage, relative humidity, platinum loading, and ionomer-to-carbon ratio influence performance. • Identified voltage is the top predictor, followed by relative humidity, platinum loading, and ionomer-to-carbon ratio. • Model-based support for optimization of fabrication, real-time control, and durability improvements. • Providing actionable insights for optimization of the fabrication and operation of polymer electrolyte fuel cells. Polymer electrolyte fuel cells will be an essential technology of the emerging hydrogen economy. However, optimizing their cost and performance necessitates understanding of how different parameters affect their operation. This optimization problem involves numerous interrelated design and operational parameters. However, developing the required understanding through experimental studies alone would be inefficient. Physical modelling is a much-needed complement to experiment but is constrained by simplifying assumptions that diminish the models' predictive capabilities. As a supplement to experiment and physical modelling, we employ a data-based assessment that leverages machine learning techniques to support and enhance decision-making. We first evaluate the predictive accuracy of various machine learning models, including artificial neural networks, to predict the polarization behavior of polymer electrolyte fuel cells, harnessing an extensive experimental dataset. We then apply explainable artificial intelligence techniques, including Gini feature importance and Shapley additive explanations value analyses, to understand how these models incorporate data into the prediction process. Probabilistic analyses can help identify relationships between predictions and feature values. We demonstrate that insights derived from Shapley additive explanations value analysis are consistent with literature data on the thermodynamics and kinetics of relevant electrochemical reaction and transport processes. Our study highlights the potential of interpretable and explainable tools to offer a holistic analysis of the impacts of various interrelated operational and design parameters on the performance of the fuel cell. In the future, such explainable tools could help identify gaps in experimental data and pinpoint research priorities.

Authors 7

1. Ali Malek

   National Research Council Canada

   Affiliation as printed

   Clean Energy Innovation Research Centre, National Research Council Canada, Vancouver, BC V6T 1W5, Canada

2. Max Dreger

   Forschungszentrum Jülich

   Affiliation as printed

   Institute of Energy Technologies (IET): Theory and Computation of Energy Materials (IET-3), Forschungszentrum Jülich GmbH, 52425 Jülich, Germany

3. Nima Shaigan

   National Research Council Canada

   Affiliation as printed

   Clean Energy Innovation Research Centre, National Research Council Canada, Vancouver, BC V6T 1W5, Canada

4. Chaojie Song

   National Research Council Canada

   Affiliation as printed

   Clean Energy Innovation Research Centre, National Research Council Canada, Vancouver, BC V6T 1W5, Canada

5. Kourosh Malek corresponding

   Forschungszentrum Jülich

   Affiliation as printed

   Institute of Energy Technologies (IET): Theory and Computation of Energy Materials (IET-3), Forschungszentrum Jülich GmbH, 52425 Jülich, Germany

6. Jasna Janković

   University of Connecticut

   Affiliation as printed

   Center for Clean Energy Engineering, University of Connecticut, Storrs, CT 06269, United States

7. Michael Hermann Eikerling Aachen Chair of Theory and Computation of Energy Materials Faculty of Georesources and Materials Engineering

   Forschungszentrum Jülich · RWTH Aachen University

   Affiliation as printed

   Chair of Theory and Computation of Energy Materials, Faculty of Georesources and Materials Engineering, RWTH Aachen University, 52062 Aachen, Germany

   Institute of Energy Technologies (IET): Theory and Computation of Energy Materials (IET-3), Forschungszentrum Jülich GmbH, 52425 Jülich, Germany