Details
| Original language | English |
|---|---|
| Article number | 123550 |
| Number of pages | 15 |
| Journal | Applied energy |
| Volume | 371 |
| Early online date | 14 Jun 2024 |
| Publication status | Published - 1 Oct 2024 |
Abstract
In this study, we propose to adopt a novel framework, Knowledge-integrated Machine Learning, for advancing Proton Exchange Membrane Water Electrolysis (PEMWE) development. Given the significance of PEMWE in green hydrogen production and the inherent challenges in optimizing its performance, our framework aims to provide a systematic overview of incorporating data-driven models with domain-specific insights to address the domain challenges. We first identify the uncertainties originating from data acquisition conditions, data-driven model mechanisms, and domain expertise, highlighting their complementary characteristics in carrying information from different perspectives. Building upon this foundation, we showcase how to adeptly decompose knowledge and extract unique information to contribute to the data augmentation, modeling process, and knowledge discovery. We demonstrate a hierarchical three-level framework, termed the ”Ladder of Knowledge-integrated Machine Learning,” in the PEMWE context, applying it to three case studies within a context of cell degradation analysis to affirm its efficacy in interpolation, extrapolation, and information representation. Initial results demonstrate improvements in interpolation accuracy by up to 30%, robustness in extrapolation by enhancing predictive stability across varied operational conditions, and enriched information representation that supports autonomous knowledge discovery. This research lays the groundwork for more knowledge-informed enhancements in ML applications in engineering.
Keywords
- Degradation analysis, Knowledge engineering, Machine learning, Proton exchange membrane water electrolysis, Uncertainty analysis
ASJC Scopus subject areas
- Engineering(all)
- Building and Construction
- Energy(all)
- Renewable Energy, Sustainability and the Environment
- Engineering(all)
- Mechanical Engineering
- Energy(all)
- General Energy
- Environmental Science(all)
- Management, Monitoring, Policy and Law
Sustainable Development Goals
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Applied energy, Vol. 371, 123550, 01.10.2024.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Machine learning in proton exchange membrane water electrolysis
T2 - A knowledge-integrated framework
AU - Chen, Xia
AU - Rex, Alexander
AU - Woelke, Janis
AU - Eckert, Christoph
AU - Bensmann, Boris
AU - Hanke-Rauschenbach, Richard
AU - Geyer, Philipp
N1 - Publisher Copyright: © 2024 The Author(s)
PY - 2024/10/1
Y1 - 2024/10/1
N2 - In this study, we propose to adopt a novel framework, Knowledge-integrated Machine Learning, for advancing Proton Exchange Membrane Water Electrolysis (PEMWE) development. Given the significance of PEMWE in green hydrogen production and the inherent challenges in optimizing its performance, our framework aims to provide a systematic overview of incorporating data-driven models with domain-specific insights to address the domain challenges. We first identify the uncertainties originating from data acquisition conditions, data-driven model mechanisms, and domain expertise, highlighting their complementary characteristics in carrying information from different perspectives. Building upon this foundation, we showcase how to adeptly decompose knowledge and extract unique information to contribute to the data augmentation, modeling process, and knowledge discovery. We demonstrate a hierarchical three-level framework, termed the ”Ladder of Knowledge-integrated Machine Learning,” in the PEMWE context, applying it to three case studies within a context of cell degradation analysis to affirm its efficacy in interpolation, extrapolation, and information representation. Initial results demonstrate improvements in interpolation accuracy by up to 30%, robustness in extrapolation by enhancing predictive stability across varied operational conditions, and enriched information representation that supports autonomous knowledge discovery. This research lays the groundwork for more knowledge-informed enhancements in ML applications in engineering.
AB - In this study, we propose to adopt a novel framework, Knowledge-integrated Machine Learning, for advancing Proton Exchange Membrane Water Electrolysis (PEMWE) development. Given the significance of PEMWE in green hydrogen production and the inherent challenges in optimizing its performance, our framework aims to provide a systematic overview of incorporating data-driven models with domain-specific insights to address the domain challenges. We first identify the uncertainties originating from data acquisition conditions, data-driven model mechanisms, and domain expertise, highlighting their complementary characteristics in carrying information from different perspectives. Building upon this foundation, we showcase how to adeptly decompose knowledge and extract unique information to contribute to the data augmentation, modeling process, and knowledge discovery. We demonstrate a hierarchical three-level framework, termed the ”Ladder of Knowledge-integrated Machine Learning,” in the PEMWE context, applying it to three case studies within a context of cell degradation analysis to affirm its efficacy in interpolation, extrapolation, and information representation. Initial results demonstrate improvements in interpolation accuracy by up to 30%, robustness in extrapolation by enhancing predictive stability across varied operational conditions, and enriched information representation that supports autonomous knowledge discovery. This research lays the groundwork for more knowledge-informed enhancements in ML applications in engineering.
KW - Degradation analysis
KW - Knowledge engineering
KW - Machine learning
KW - Proton exchange membrane water electrolysis
KW - Uncertainty analysis
UR - http://www.scopus.com/inward/record.url?scp=85195816248&partnerID=8YFLogxK
U2 - 10.1016/j.apenergy.2024.123550
DO - 10.1016/j.apenergy.2024.123550
M3 - Article
AN - SCOPUS:85195816248
VL - 371
JO - Applied energy
JF - Applied energy
SN - 0306-2619
M1 - 123550
ER -