Artificial intelligence models for predicting the performance of proton exchange membrane water electrolyzers under steady and dynamic power

Proton exchange membrane water electrolyzers (PEMWEs) are one of the leading technologies to produce hydrogen from renewable power sources. Predicting the effect of degradation in PEMWEs is crucial for determining economic feasibility, maintenance schedules, and optimal control. However, existing se...

Full description

Saved in:
Bibliographic Details
Main Authors: Thomas Waite, Alireza Sadeghi, Mohammad Yazdani-Asrami
Format: Article
Language:English
Published: IOP Publishing 2025-01-01
Series:JPhys Energy
Subjects:
Online Access:https://doi.org/10.1088/2515-7655/add95e
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849718088044380160
author Thomas Waite
Alireza Sadeghi
Mohammad Yazdani-Asrami
author_facet Thomas Waite
Alireza Sadeghi
Mohammad Yazdani-Asrami
author_sort Thomas Waite
collection DOAJ
description Proton exchange membrane water electrolyzers (PEMWEs) are one of the leading technologies to produce hydrogen from renewable power sources. Predicting the effect of degradation in PEMWEs is crucial for determining economic feasibility, maintenance schedules, and optimal control. However, existing semi-empirical and data-driven models for degradation are typically rudimentary or system-specific. Artificial Intelligence (AI) offers a method to improve and generalize models by implicitly learning the system behavior through analysis of large experimental datasets. This paper evaluated the ability of a range of AI techniques to model PEMWE performance degradation under steady-state and dynamic operation. Data from 39 distinct experiments were collated into a training dataset with 19 input features consisting of (i) construction parameters, (ii) static operating parameters, (iii) dynamic operating parameters, and (iv) the recording time. The target for modeling was cell voltage, selected as a systemic proxy for degradation. Over 6900 data points were collected with a maximum experimental duration of 5600 H. The duration studied, the number of input features, and the variety of PEMWE constructions considered make this the most comprehensive AI model on the subject, to date. The model offered a goodness of fit or coefficient of determination ( R ^2 ) value of 0.9991 for the testing data and can predict the performance of untrained electrolyzers and their operation with similar accuracy.
format Article
id doaj-art-a476c87e1371404fb82bbb8e5ae77cc0
institution DOAJ
issn 2515-7655
language English
publishDate 2025-01-01
publisher IOP Publishing
record_format Article
series JPhys Energy
spelling doaj-art-a476c87e1371404fb82bbb8e5ae77cc02025-08-20T03:12:27ZengIOP PublishingJPhys Energy2515-76552025-01-017303501310.1088/2515-7655/add95eArtificial intelligence models for predicting the performance of proton exchange membrane water electrolyzers under steady and dynamic powerThomas Waite0https://orcid.org/0009-0001-1158-1002Alireza Sadeghi1Mohammad Yazdani-Asrami2https://orcid.org/0000-0002-7691-3485CryoElectric Research Lab, Propulsion, Electrification & Superconductivity group, Autonomous Systems and Connectivity division, James Watt School of Engineering, University of Glasgow , Glasgow G12 8QQ, United KingdomCryoElectric Research Lab, Propulsion, Electrification & Superconductivity group, Autonomous Systems and Connectivity division, James Watt School of Engineering, University of Glasgow , Glasgow G12 8QQ, United KingdomCryoElectric Research Lab, Propulsion, Electrification & Superconductivity group, Autonomous Systems and Connectivity division, James Watt School of Engineering, University of Glasgow , Glasgow G12 8QQ, United KingdomProton exchange membrane water electrolyzers (PEMWEs) are one of the leading technologies to produce hydrogen from renewable power sources. Predicting the effect of degradation in PEMWEs is crucial for determining economic feasibility, maintenance schedules, and optimal control. However, existing semi-empirical and data-driven models for degradation are typically rudimentary or system-specific. Artificial Intelligence (AI) offers a method to improve and generalize models by implicitly learning the system behavior through analysis of large experimental datasets. This paper evaluated the ability of a range of AI techniques to model PEMWE performance degradation under steady-state and dynamic operation. Data from 39 distinct experiments were collated into a training dataset with 19 input features consisting of (i) construction parameters, (ii) static operating parameters, (iii) dynamic operating parameters, and (iv) the recording time. The target for modeling was cell voltage, selected as a systemic proxy for degradation. Over 6900 data points were collected with a maximum experimental duration of 5600 H. The duration studied, the number of input features, and the variety of PEMWE constructions considered make this the most comprehensive AI model on the subject, to date. The model offered a goodness of fit or coefficient of determination ( R ^2 ) value of 0.9991 for the testing data and can predict the performance of untrained electrolyzers and their operation with similar accuracy.https://doi.org/10.1088/2515-7655/add95eartificial intelligence techniquedata-driven modelingelectrolyzer lifetimeperformance degradationartificial intelligence modelPEMWE
spellingShingle Thomas Waite
Alireza Sadeghi
Mohammad Yazdani-Asrami
Artificial intelligence models for predicting the performance of proton exchange membrane water electrolyzers under steady and dynamic power
JPhys Energy
artificial intelligence technique
data-driven modeling
electrolyzer lifetime
performance degradation
artificial intelligence model
PEMWE
title Artificial intelligence models for predicting the performance of proton exchange membrane water electrolyzers under steady and dynamic power
title_full Artificial intelligence models for predicting the performance of proton exchange membrane water electrolyzers under steady and dynamic power
title_fullStr Artificial intelligence models for predicting the performance of proton exchange membrane water electrolyzers under steady and dynamic power
title_full_unstemmed Artificial intelligence models for predicting the performance of proton exchange membrane water electrolyzers under steady and dynamic power
title_short Artificial intelligence models for predicting the performance of proton exchange membrane water electrolyzers under steady and dynamic power
title_sort artificial intelligence models for predicting the performance of proton exchange membrane water electrolyzers under steady and dynamic power
topic artificial intelligence technique
data-driven modeling
electrolyzer lifetime
performance degradation
artificial intelligence model
PEMWE
url https://doi.org/10.1088/2515-7655/add95e
work_keys_str_mv AT thomaswaite artificialintelligencemodelsforpredictingtheperformanceofprotonexchangemembranewaterelectrolyzersundersteadyanddynamicpower
AT alirezasadeghi artificialintelligencemodelsforpredictingtheperformanceofprotonexchangemembranewaterelectrolyzersundersteadyanddynamicpower
AT mohammadyazdaniasrami artificialintelligencemodelsforpredictingtheperformanceofprotonexchangemembranewaterelectrolyzersundersteadyanddynamicpower