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

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...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinwoo Kim, Jaewan Baek, Mingi Choi
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:Array
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590005625000347
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850218987635343360
author Jinwoo Kim
Jaewan Baek
Mingi Choi
author_facet Jinwoo Kim
Jaewan Baek
Mingi Choi
author_sort Jinwoo Kim
collection DOAJ
description 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.
format Article
id doaj-art-ff459ec7e4654b26bb372e36b6cce5d6
institution OA Journals
issn 2590-0056
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series Array
spelling doaj-art-ff459ec7e4654b26bb372e36b6cce5d62025-08-20T02:07:31ZengElsevierArray2590-00562025-07-012610040710.1016/j.array.2025.100407Machine-learning-driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturingJinwoo Kim0Jaewan Baek1Mingi Choi2Department of Future Energy Convergence, Seoul National University of Science and Technology, Seoul, 01811, South KoreaDepartment of Future Energy Convergence, Seoul National University of Science and Technology, Seoul, 01811, South KoreaCorresponding author.; Department of Future Energy Convergence, Seoul National University of Science and Technology, Seoul, 01811, South KoreaThe 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.http://www.sciencedirect.com/science/article/pii/S2590005625000347Machine-learningProtonic ceramic fuel cellsFeature-importance analysis
spellingShingle Jinwoo Kim
Jaewan Baek
Mingi Choi
Machine-learning-driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturing
Array
Machine-learning
Protonic ceramic fuel cells
Feature-importance analysis
title Machine-learning-driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturing
title_full Machine-learning-driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturing
title_fullStr Machine-learning-driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturing
title_full_unstemmed Machine-learning-driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturing
title_short Machine-learning-driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturing
title_sort machine learning driven feature importance analysis for guiding the protonic ceramic fuel cell manufacturing
topic Machine-learning
Protonic ceramic fuel cells
Feature-importance analysis
url http://www.sciencedirect.com/science/article/pii/S2590005625000347
work_keys_str_mv AT jinwookim machinelearningdrivenfeatureimportanceanalysisforguidingtheprotonicceramicfuelcellmanufacturing
AT jaewanbaek machinelearningdrivenfeatureimportanceanalysisforguidingtheprotonicceramicfuelcellmanufacturing
AT mingichoi machinelearningdrivenfeatureimportanceanalysisforguidingtheprotonicceramicfuelcellmanufacturing