P-073

Andrej Zvonimir Tomić

aztomic@fesb.hr

Nikola Franić, Ivan Pivac, Frano Barbir

Faculty of Electrical Engineering, Mechanical Engineering and Naval Architecture, University of Split, Croatia

Data-Driven Predictive Control of PEM electrolyzers for Mitigating Dynamic Degradation within Hybrid Renewable Energy Systems

In the context of global decarbonization efforts in industrial and grid-scale energy storage applications, the integration of proton exchange membrane (PEM) electrolyzers with intermittent renewable energy sources necessitates adaptive control strategies to prevent performance degradation caused by variable power, which is a significant barrier to sustainable hydrogen production. This study examines degradation in PEM electrolyzers under different operating regimes and proposes a predictive control framework. Systematic experiments assessed degradation through standardized profiles: stationary baselines, gradually dynamic conditions, and accelerated stress protocols that simulate operation with renewable energy sources. In addition to real-time data monitoring, analysis of polarization curves, electrochemical impedance spectroscopy, and cyclic voltammetry were used for performance diagnostic purposes. Results show that degradation is influenced by prolonged exposure to potentials greater than 1.95 V, which causes catalyst dissolution, and by extended dwell times at fixed potentials, even at nominal levels of 1.75 V, leading to an increase in membrane resistance. The predictive databased framework integrates voltage-dependent degradation dynamics with operating parameters dynamics to forecast efficiency losses under varying current densities. Trained on empirical datasets, the model achieved more than 95% accuracy predicting voltage drift and efficiency decline, enabling adaptive current modulation to avoid degradation critical voltage windows while maintaining hydrogen output. Future work will focus on validation of the developed framework under real-world renewable profiles and scalability to multi-stack systems.