A MACHINE LEARNING FRAMEWORK FOR PREDICTING ELECTROLYZER DEGRADATION AND EFFICIENCY IN GREEN HYDROGEN PRODUCTION SYSTEMS
The study suggests a comprehensive conceptual framework to predict electrolyzer degradation and performance for green hydrogen production using machine learning. The framework is closed-loop feedback system; domain knowledge-based feature engineering; mixture of traditional machine learning models and LSTM models; a comprehensive data preprocessing system; and solving issues of catalyst degradation, aging of membranes and fluctuation of renewable feedstocks. The proposed system architecture allows for capturing the temporal dependencies and for continuous learning in the system, which enables predictive maintenance, energy optimization and adaptive control. This study offers a theoretical framework for future empirical testing of intelligent monitoring systems for technologies powered by renewables.
Authors
- Stephen Eyitayo Obamiyi
- Bukola Badeji–Ajisafe (ORCID: https://orcid.org/0000-0002-0944-4615)
- Samuel Obinna Nwankwo
- Olugbenga Francis Akomolehin
- Omowumi. H. Fred-Ahmadu
- Aanuoluwapo Aina Aburo
- Olusola Adewale
- Ayodeji Ogundana
Institutions
- Afe Babalola University (NG)
- Federal University of Technology and Environmental Sciences (NG)
Publication Details
- Journal
- International Journal of Energy Research Science and Engineering
- Published
- 2026-11-17
- DOI
- https://doi.org/10.53982/ijerse.2026.0102.07-j
- Primary Topic
- Hybrid Renewable Energy Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00