Machine-learning-driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturing

Abstract

The protonic ceramic fuel cell (PCFC) is currently attracting attention as a promising energy-conversion device capable of generating electricity from hydrogen with high efficiency. However, when developing high-performance PCFCs, a wide range of material properties and manufacturing processes must be optimized, necessitating tremendous time and manpower investments as well as a high cost. To address these issues, this study proposes a method by which to analyze the effects of certain materials and manufacturing processes on the fabrication of PCFCs, assisted by machine learning (ML). Based on data from earlier work, we first evaluate the performance-predicting capabilities of 6 ML models, showing the best-predicting performance with XGBoost model. Based on the selected model of XGBoost, we also conduct the feature analysis using Shapley additive explanations, which successfully determine the factors contributing most to the PCFC performance in terms of the materials and manufacturing processes for the anode, cathode, and electrolyte in each case. These results can give us guidelines for the efficient manufacturing of the PCFC.